3. Cross-species analysis

In this tutorial, we demonstrate how to perform prediction and evaluation on cross-species scenario. We train XChrom using sample from one species and evaluate the model on samples from other species, showcasing the model’s performance across different biological systems (effectively covering two dimensions: cross-sample and cross-species prediction).

We use a publicly available single-cell multiome dataset collected from the motor cortex of human, mouse, macaque, and marmoset. Each species contains multiple samples. In addition to providing raw sequencing data, the authors also offer pre-processed and cell-annotated scRNA data for each sample. We extracted paired data and assigned the annotated cell types to obtain the raw dataset for our study. We then concatenated scRNA data from different samples within each species, and performed cross-species integration based on 1-to-1 orthologous genes using Harmony. The resulting batch-corrected cell embeddings are stored in RNA.obsm['X_pca_harmony']. The processed scRNA and scATAC paired data (after filtering and batch correction) have been uploaded to https://doi.org/10.5281/zenodo.16959682. For detailed procedures, please refer to https://github.com/Miaoyuanyuan777/XChrom_analysis.

Data Preprocessing

As an example, we extract two samples from human and mouse respectively, labeled m1d1 and mop3c2. In this tutorial, we use mouse (mop3c2) as the training set and human (m1d1) as the test set. For the training scATAC data, we split it by cells and peaks to generate training/validation data for model training, following the same procedure as in the 1_Within-sample analysis tutorial to create model inputs. For the test scATAC data, we use the entire test set for evaluation. For the scRNA data, we directly use the batch-corrected cell embeddings (RNA.obsm['X_pca_harmony']) as inputs for model training and prediction.
Model Training

XChrom takes two inputs: ① DNA sequences (one-hot encoded, 1 × 1344bp) and ② cell embeddings (cell number × 32). The model is trained to predict chromatin accessibility probabilities for each genomic region across all cells. Importantly, the cell embeddings used here are derived from batch-corrected scRNA-seq data from both samples.
Prediction and Evaluation

After training, we evaluate the preprocessed test sample from two perspectives:
- Binary classification metrics: auROC and auPRC, as primary evaluation metrics, which were summarized at the overall, per-cell and per-peak levels.
- Cell state fidelity: Using the neighbor score (NS) to quantify cross-modality neighborhood concordance by comparing scATAC-seq and scRNA-seq data, and the label score (LS) to evaluate the consistency of cell-type labels within local neighborhoods. Both metrics depend on a parameter k, the number of nearest neighbors in the cell-cell graph. Together, these metrics demonstrate the model’s ability to generalize across species.
Interpretability analysis

We perform in silico saturation mutagenesis (ISM) on sequences of interest, predicting the change in accessibility for every cell when mutating each position to its three alternative nucleotides. For each mutation, we compare the mutant prediction with the reference to obtain the per-cell change in accessibility, producing a per-base ISM importance score that quantifies each position’s influence on the model’s predictions.

1. Download Data (Human: m1d1, Mouse: mop3c2)

The original data is available at GEO accession GSE229169. We have processed this data by performing batch correction using orthologous genes to generate raw cell embeddings for each sample as model inputs. The data were filtered (filtering threshold: 0.05) and are available for direct download at Zenodo: https://doi.org/10.5281/zenodo.16959682. In this tutorial, we use only the human sample (m1d1) and the mouse sample (mop3c2) as examples, training XChrom on the mouse data and evaluating on the human data.
Download the human sample files:
- m1d1_atac.h5ad and save to './data/3_cross_species/m1d1_atac.h5ad'
- m1d1_rna_harmony.h5ad and save to './data/3_cross_species/m1d1_rna_harmony.h5ad'
Download the mouse sample files:
- mop3c2_atac.h5ad and save to './data/3_cross_species/mop3c2_atac.h5ad'
- mop3c2_rna_harmony.h5ad and save to './data/3_cross_species/mop3c2_rna_harmony.h5ad'
Download the human genome file from: https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz and decompress it.
Download the mouse genome file from: https://hgdownload.soe.ucsc.edu/goldenPath/mm10/bigZips/mm10.fa.gz and decompress it.
The raw cell embeddings are stored in RNA.obsm['X_pca_harmony'], and cell type labels are available in RNA.obs['cell_type'] for computing LS.

[1]:

import scanpy as sc
import xchrom as xc
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

2. Read and filter data

The data hosted at Zenodo: https://doi.org/10.5281/zenodo.16959682 have already undergone comprehensive filtering and preprocessing, so you can skip the filtering step when using these files.

Ensure the species parameter matches your input data (human or mouse). XChrom uses this to remove sequences that don’t belong to the specified species—e.g., keep chr1–22, X, Y for human and chr1–19, X, Y for mouse . Also make sure chromosome naming schemes are consistent (e.g., chr1 vs 1).

After this step, the scATAC-seq AnnData will include a per-cell peak count in ATAC.obs['n_genes'], which XChrom automatically uses when generating training inputs.

[2]:

mop3c2_rna = sc.read_h5ad('./data/3_cross_species/mop3c2_rna_harmony.h5ad')
mop3c2_atac = sc.read_h5ad('./data/3_cross_species/mop3c2_atac.h5ad')
_, mop3c2_atac = xc.pp.filter_multiome_data(
    ad_rna = mop3c2_rna,
    ad_atac = mop3c2_atac,
    species = 'mouse',
    filter_ratio = 0
)

RNA data after filtering: View of AnnData object with n_obs × n_vars = 6668 × 1193
    obs: 'cell_type', 'n_genes', 'sampleID', 'species', 'batch'
    var: 'feature_types', 'ortho_h_id', 'ortho_h_names', 'n_cells'
    uns: 'batch_colors', 'cell_type_colors', 'hvg', 'log1p', 'neighbors', 'pca', 'sampleID_colors', 'species_colors', 'umap'
    obsm: 'X_pca', 'X_pca_harmony', 'X_umap', 'zscore32_perpc'
    varm: 'PCs'
    obsp: 'connectivities', 'distances'
ATAC data after filtering: View of AnnData object with n_obs × n_vars = 6668 × 107451
    obs: 'cell_type', 'n_genes'
    var: 'ids', 'names', 'feature_types', 'chr', 'start', 'end', 'n_cells'

[3]:

### Filter data
m1d1_rna = sc.read_h5ad('./data/3_cross_species/m1d1_rna_harmony.h5ad')
m1d1_atac = sc.read_h5ad('./data/3_cross_species/m1d1_atac.h5ad')
_, m1d1_atac = xc.pp.filter_multiome_data(
    ad_rna = m1d1_rna,
    ad_atac = m1d1_atac,
    species = 'human',
    filter_ratio = 0
)

RNA data after filtering: View of AnnData object with n_obs × n_vars = 4489 × 1193
    obs: 'cell_type', 'n_genes', 'sampleID', 'species', 'batch'
    var: 'feature_types', 'ortho_h_id', 'ortho_h_names', 'n_cells'
    uns: 'batch_colors', 'cell_type_colors', 'hvg', 'log1p', 'neighbors', 'pca', 'sampleID_colors', 'species_colors', 'umap'
    obsm: 'X_pca', 'X_pca_harmony', 'X_umap'
    varm: 'PCs'
    obsp: 'connectivities', 'distances'
ATAC data after filtering: View of AnnData object with n_obs × n_vars = 4489 × 37363
    obs: 'cell_type', 'n_genes'
    var: 'ids', 'names', 'feature_types', 'chr', 'start', 'end', 'n_cells'

[4]:

m1d1_atac.write('./data/3_cross_species/m1d1_atac.h5ad')
mop3c2_atac.write('./data/3_cross_species/mop3c2_atac.h5ad')

3. Training/test data prepare

[5]:

## Generate data for model training
train_folder = './data/3_cross_species/train_data/'
input_fasta = '/picb/bigdata/project/miaoyuanyuan/mm10.fa'
train_atac = sc.read_h5ad('./data/3_cross_species/mop3c2_atac.h5ad')
dict = xc.pp.process_train_test_single(
    ad_atac=train_atac, ## can be a str, Path, or anndata.AnnData object
    input_fasta=input_fasta,
    output_path=train_folder
)

train/test data is saved in:  data/3_cross_species/train_data
successful writing bed file.
successful writing train/test split file.
successful writing train/test anndata file.
successful writing sparse m.
Successfully saving all sequence h5 file...
Successfully saving trainval sequence h5 file...
Successfully saving test sequence h5 file...

[6]:

## Generate data for model evaluation
test_folder = './data/3_cross_species/test_data/'
test_atac = sc.read_h5ad('./data/3_cross_species/m1d1_atac.h5ad')
input_fasta = '/picb/bigdata/project/miaoyuanyuan/hg38.fa'
dict = xc.pp.process_test_dual(
    ad_atac=test_atac, ## can be a str, Path, or anndata.AnnData object
    input_fasta=input_fasta,
    output_path=test_folder
)

train/test data is saved in:  data/3_cross_species/test_data
successful writing bed file.
successful writing sparse m.
start saving all sequence h5 file...

We performed preprocessing on the filtered scATAC data of human (m1d1) and mouse (mop3c2) samples separately:

For the mop3c2 mouse training sample: Following the same procedure as in the 1. Within-sample analysis tutorial, we partitioned the data using 90% of cells and 90% of peaks to generate training/validation sets. This produced:

ad_trainval.h5ad: containing training cells and training peaks
m_trainval.npz: corresponding count matrix
trainval_seqs.h5: base sequence file for training peaks

All files were saved in './data/3_cross_species/train_data/'.

For the m1d1 human test sample: No partitioning was applied. The filtered scATAC data was directly converted into the required model input files:

ad.h5ad
m.npz
all_seqs.h5

These files were saved in './data/3_cross_species/test_data/'.

Note: The input_fasta parameter should be replaced with the path to the genome file corresponding to the species used in your specific dataset.

4. Train XChrom

We use the preprocessed data from the mouse (mop3c2) training set obtained above as sequence inputs for the model. The input_folder should contain all files generated during preprocessing. The batch-corrected X_pca_harmony embeddings derived from scRNA data are used as raw cell embeddings and serve as cell identity inputs to the model. If using dimensionality reduction results from other methods, they must be stored in cell_embedding_ad.obsm under the key cellembed_raw for extraction.
If you want to compute NS(k=100) and LS(k=100) for monitoring the XChrom training process, you need to set trackscore = True and specify the celltype in either the RNA or ATAC H5AD file. When print_scores = True is specified, the computed NS and LS values will be printed during each training epoch.
The model is set to train for 1000 epochs by default, but an early stopping mechanism will be triggered if the increase in training auROC remains below 1e-6 for 50 consecutive epochs.
The save_freq parameter determines the frequency of saving model parameters, with a default value of 1000 (meaning intermediate model parameters are not saved during training).

[7]:

history = xc.tr.train_XChrom(
    input_folder='./data/3_cross_species/train_data/',
    cell_embedding_ad='./data/3_cross_species/mop3c2_rna_harmony.h5ad',
    cellembed_raw='X_pca_harmony',
    out_path='./data/3_cross_species/train_out/',
    epochs = 1000,
    trackscore = True,
    print_scores = True,
    celltype = 'cell_type',
    verbose = 1
)

=== Start training XChrom model ===
Input folder: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/train_data
Cell embedding file: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/mop3c2_rna_harmony.h5ad
Raw cell embedding key: X_pca_harmony
Output path: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/train_out
Model parameters: bottleneck=32, batch_size=128, lr=0.01
1. Load raw cell embedding and make z-score normalization...
Raw cell embedding saved to: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/mop3c2_rna_harmony.h5ad.obsm['X_pca_harmony']
Initial cell embedding saved to: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/mop3c2_rna_harmony.h5ad.obsm['zscore32_perpc']
Initial cell embedding shape: (6668, 32)
2. Load training data...
3. Prepare train/val data split...
Training peak number: 87035, Validation peak number: 9671
4. Create TensorFlow dataset...

2025-08-18 10:30:14.683558: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-08-18 10:30:16.403718: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 17996 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:31:00.0, compute capability: 8.6
2025-08-18 10:30:16.404799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 19873 MB memory:  -> device: 1, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:4b:00.0, compute capability: 8.6
2025-08-18 10:30:16.405349: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:2 with 20401 MB memory:  -> device: 2, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:98:00.0, compute capability: 8.6
2025-08-18 10:30:16.405857: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:3 with 70 MB memory:  -> device: 3, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:b1:00.0, compute capability: 8.6

5. Build and compile model...
Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to
==================================================================================================
sequence (InputLayer)           [(None, 1344, 4)]    0
__________________________________________________________________________________________________
stochastic_reverse_complement ( ((None, 1344, 4), () 0           sequence[0][0]
__________________________________________________________________________________________________
stochastic_shift (StochasticShi (None, 1344, 4)      0           stochastic_reverse_complement[0][
__________________________________________________________________________________________________
gelu (GELU)                     (None, 1344, 4)      0           stochastic_shift[0][0]
__________________________________________________________________________________________________
conv1d (Conv1D)                 (None, 1344, 288)    19584       gelu[0][0]
__________________________________________________________________________________________________
batch_normalization (BatchNorma (None, 1344, 288)    1152        conv1d[0][0]
__________________________________________________________________________________________________
max_pooling1d (MaxPooling1D)    (None, 448, 288)     0           batch_normalization[0][0]
__________________________________________________________________________________________________
gelu_1 (GELU)                   (None, 448, 288)     0           max_pooling1d[0][0]
__________________________________________________________________________________________________
conv1d_1 (Conv1D)               (None, 448, 288)     414720      gelu_1[0][0]
__________________________________________________________________________________________________
batch_normalization_1 (BatchNor (None, 448, 288)     1152        conv1d_1[0][0]
__________________________________________________________________________________________________
max_pooling1d_1 (MaxPooling1D)  (None, 224, 288)     0           batch_normalization_1[0][0]
__________________________________________________________________________________________________
gelu_2 (GELU)                   (None, 224, 288)     0           max_pooling1d_1[0][0]
__________________________________________________________________________________________________
conv1d_2 (Conv1D)               (None, 224, 323)     465120      gelu_2[0][0]
__________________________________________________________________________________________________
batch_normalization_2 (BatchNor (None, 224, 323)     1292        conv1d_2[0][0]
__________________________________________________________________________________________________
max_pooling1d_2 (MaxPooling1D)  (None, 112, 323)     0           batch_normalization_2[0][0]
__________________________________________________________________________________________________
gelu_3 (GELU)                   (None, 112, 323)     0           max_pooling1d_2[0][0]
__________________________________________________________________________________________________
conv1d_3 (Conv1D)               (None, 112, 363)     586245      gelu_3[0][0]
__________________________________________________________________________________________________
batch_normalization_3 (BatchNor (None, 112, 363)     1452        conv1d_3[0][0]
__________________________________________________________________________________________________
max_pooling1d_3 (MaxPooling1D)  (None, 56, 363)      0           batch_normalization_3[0][0]
__________________________________________________________________________________________________
gelu_4 (GELU)                   (None, 56, 363)      0           max_pooling1d_3[0][0]
__________________________________________________________________________________________________
conv1d_4 (Conv1D)               (None, 56, 407)      738705      gelu_4[0][0]
__________________________________________________________________________________________________
batch_normalization_4 (BatchNor (None, 56, 407)      1628        conv1d_4[0][0]
__________________________________________________________________________________________________
max_pooling1d_4 (MaxPooling1D)  (None, 28, 407)      0           batch_normalization_4[0][0]
__________________________________________________________________________________________________
gelu_5 (GELU)                   (None, 28, 407)      0           max_pooling1d_4[0][0]
__________________________________________________________________________________________________
conv1d_5 (Conv1D)               (None, 28, 456)      927960      gelu_5[0][0]
__________________________________________________________________________________________________
batch_normalization_5 (BatchNor (None, 28, 456)      1824        conv1d_5[0][0]
__________________________________________________________________________________________________
max_pooling1d_5 (MaxPooling1D)  (None, 14, 456)      0           batch_normalization_5[0][0]
__________________________________________________________________________________________________
gelu_6 (GELU)                   (None, 14, 456)      0           max_pooling1d_5[0][0]
__________________________________________________________________________________________________
conv1d_6 (Conv1D)               (None, 14, 512)      1167360     gelu_6[0][0]
__________________________________________________________________________________________________
batch_normalization_6 (BatchNor (None, 14, 512)      2048        conv1d_6[0][0]
__________________________________________________________________________________________________
max_pooling1d_6 (MaxPooling1D)  (None, 7, 512)       0           batch_normalization_6[0][0]
__________________________________________________________________________________________________
gelu_7 (GELU)                   (None, 7, 512)       0           max_pooling1d_6[0][0]
__________________________________________________________________________________________________
conv1d_7 (Conv1D)               (None, 7, 256)       131072      gelu_7[0][0]
__________________________________________________________________________________________________
batch_normalization_7 (BatchNor (None, 7, 256)       1024        conv1d_7[0][0]
__________________________________________________________________________________________________
gelu_8 (GELU)                   (None, 7, 256)       0           batch_normalization_7[0][0]
__________________________________________________________________________________________________
reshape (Reshape)               (None, 1, 1792)      0           gelu_8[0][0]
__________________________________________________________________________________________________
dense (Dense)                   (None, 1, 32)        57344       reshape[0][0]
__________________________________________________________________________________________________
cell_embed (InputLayer)         [(None, 6002, 32)]   0
__________________________________________________________________________________________________
batch_normalization_8 (BatchNor (None, 1, 32)        128         dense[0][0]
__________________________________________________________________________________________________
lambda (Lambda)                 (None, 6002, 32)     0           cell_embed[0][0]
__________________________________________________________________________________________________
dropout (Dropout)               (None, 1, 32)        0           batch_normalization_8[0][0]
__________________________________________________________________________________________________
layer_normalization (LayerNorma (None, 6002, 32)     64          lambda[0][0]
__________________________________________________________________________________________________
gelu_9 (GELU)                   (None, 1, 32)        0           dropout[0][0]
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 6002, 64)     2112        layer_normalization[0][0]
__________________________________________________________________________________________________
tf.compat.v1.squeeze (TFOpLambd (None, 32)           0           gelu_9[0][0]
__________________________________________________________________________________________________
sequencing_depth (InputLayer)   [(None, 6002)]       0
__________________________________________________________________________________________________
final_cellembed (Dense)         (None, 6002, 32)     2080        dense_1[0][0]
__________________________________________________________________________________________________
tf.expand_dims (TFOpLambda)     (None, 32, 1)        0           tf.compat.v1.squeeze[0][0]
__________________________________________________________________________________________________
tf.expand_dims_1 (TFOpLambda)   (None, 6002, 1)      0           sequencing_depth[0][0]
__________________________________________________________________________________________________
tf.linalg.matmul (TFOpLambda)   (None, 6002, 1)      0           final_cellembed[0][0]
                                                                 tf.expand_dims[0][0]
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 6002, 1)      2           tf.expand_dims_1[0][0]
__________________________________________________________________________________________________
tf.compat.v1.squeeze_2 (TFOpLam (None, 6002)         0           tf.linalg.matmul[0][0]
__________________________________________________________________________________________________
tf.compat.v1.squeeze_1 (TFOpLam (None, 6002)         0           dense_2[0][0]
__________________________________________________________________________________________________
tf.__operators__.add (TFOpLambd (None, 6002)         0           tf.compat.v1.squeeze_2[0][0]
                                                                 tf.compat.v1.squeeze_1[0][0]
__________________________________________________________________________________________________
tf.math.sigmoid (TFOpLambda)    (None, 6002)         0           tf.__operators__.add[0][0]
==================================================================================================
Total params: 4,524,068
Trainable params: 4,518,218
Non-trainable params: 5,850
__________________________________________________________________________________________________
6. Set training callbacks...
7. Start training...
Model will be saved to: data/3_cross_species/train_out/E1000best_model.h5
Epoch 1/1000

2025-08-18 10:30:23.501891: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
2025-08-18 10:30:27.890841: I tensorflow/stream_executor/cuda/cuda_dnn.cc:369] Loaded cuDNN version 8800
2025-08-18 10:30:27.969441: I tensorflow/stream_executor/cuda/cuda_blas.cc:1760] TensorFloat-32 will be used for the matrix multiplication. This will only be logged once.

680/680 [==============================] - 168s 232ms/step - loss: 0.3234 - binary_accuracy: 0.8749 - auc: 0.7746 - pr: 0.3225 - val_loss: 0.3126 - val_binary_accuracy: 0.8760 - val_auc: 0.7962 - val_pr: 0.3724
Neighbors Score: 0.2596, Labels Score: 0.6347   Using time in epoch 1: 40.7640s
Epoch 2/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.3116 - binary_accuracy: 0.8781 - auc: 0.7914 - pr: 0.3629 - val_loss: 0.3117 - val_binary_accuracy: 0.8765 - val_auc: 0.7977 - val_pr: 0.3809
Neighbors Score: 0.2772, Labels Score: 0.6639   Using time in epoch 2: 35.7925s
Epoch 3/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.3099 - binary_accuracy: 0.8787 - auc: 0.7944 - pr: 0.3697 - val_loss: 0.3105 - val_binary_accuracy: 0.8780 - val_auc: 0.7988 - val_pr: 0.3842
Neighbors Score: 0.2904, Labels Score: 0.6946   Using time in epoch 3: 32.6157s
Epoch 4/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.3089 - binary_accuracy: 0.8790 - auc: 0.7964 - pr: 0.3736 - val_loss: 0.3104 - val_binary_accuracy: 0.8774 - val_auc: 0.7998 - val_pr: 0.3861
Neighbors Score: 0.2887, Labels Score: 0.6991   Using time in epoch 4: 35.3956s
Epoch 5/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.3082 - binary_accuracy: 0.8792 - auc: 0.7978 - pr: 0.3765 - val_loss: 0.3121 - val_binary_accuracy: 0.8762 - val_auc: 0.7993 - val_pr: 0.3840
WARNING:tensorflow:5 out of the last 5 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7ef98c4669d0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
Neighbors Score: 0.2901, Labels Score: 0.7303   Using time in epoch 5: 33.4384s
Epoch 6/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.3075 - binary_accuracy: 0.8794 - auc: 0.7992 - pr: 0.3793 - val_loss: 0.3115 - val_binary_accuracy: 0.8785 - val_auc: 0.7999 - val_pr: 0.3890
WARNING:tensorflow:6 out of the last 6 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7ef98c3c4a60> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
Neighbors Score: 0.2894, Labels Score: 0.7053   Using time in epoch 6: 36.7949s
Epoch 7/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.3070 - binary_accuracy: 0.8796 - auc: 0.8002 - pr: 0.3812 - val_loss: 0.3117 - val_binary_accuracy: 0.8787 - val_auc: 0.7996 - val_pr: 0.3889
Neighbors Score: 0.3055, Labels Score: 0.7336   Using time in epoch 7: 33.9053s
Epoch 8/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.3064 - binary_accuracy: 0.8798 - auc: 0.8012 - pr: 0.3834 - val_loss: 0.3107 - val_binary_accuracy: 0.8785 - val_auc: 0.8023 - val_pr: 0.3919
Neighbors Score: 0.3216, Labels Score: 0.7909   Using time in epoch 8: 31.1259s
Epoch 9/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.3059 - binary_accuracy: 0.8799 - auc: 0.8022 - pr: 0.3855 - val_loss: 0.3114 - val_binary_accuracy: 0.8780 - val_auc: 0.8039 - val_pr: 0.3946
Neighbors Score: 0.2996, Labels Score: 0.7235   Using time in epoch 9: 39.2971s
Epoch 10/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.3052 - binary_accuracy: 0.8801 - auc: 0.8036 - pr: 0.3878 - val_loss: 0.3081 - val_binary_accuracy: 0.8787 - val_auc: 0.8037 - val_pr: 0.3943
Neighbors Score: 0.3167, Labels Score: 0.8101   Using time in epoch 10: 27.1583s
Epoch 11/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.3048 - binary_accuracy: 0.8801 - auc: 0.8044 - pr: 0.3894 - val_loss: 0.3094 - val_binary_accuracy: 0.8787 - val_auc: 0.8032 - val_pr: 0.3927
Neighbors Score: 0.3052, Labels Score: 0.7592   Using time in epoch 11: 38.6105s
Epoch 12/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.3042 - binary_accuracy: 0.8803 - auc: 0.8056 - pr: 0.3915 - val_loss: 0.3074 - val_binary_accuracy: 0.8784 - val_auc: 0.8065 - val_pr: 0.3980
Neighbors Score: 0.3021, Labels Score: 0.7722   Using time in epoch 12: 33.8718s
Epoch 13/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.3036 - binary_accuracy: 0.8804 - auc: 0.8066 - pr: 0.3935 - val_loss: 0.3074 - val_binary_accuracy: 0.8786 - val_auc: 0.8048 - val_pr: 0.3936
Neighbors Score: 0.3187, Labels Score: 0.7981   Using time in epoch 13: 30.7452s
Epoch 14/1000
680/680 [==============================] - 152s 218ms/step - loss: 0.3031 - binary_accuracy: 0.8806 - auc: 0.8076 - pr: 0.3953 - val_loss: 0.3063 - val_binary_accuracy: 0.8789 - val_auc: 0.8066 - val_pr: 0.3987
Neighbors Score: 0.3070, Labels Score: 0.7923   Using time in epoch 14: 31.8505s
Epoch 15/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.3027 - binary_accuracy: 0.8807 - auc: 0.8084 - pr: 0.3974 - val_loss: 0.3062 - val_binary_accuracy: 0.8791 - val_auc: 0.8070 - val_pr: 0.3985
Neighbors Score: 0.3101, Labels Score: 0.8103   Using time in epoch 15: 31.7760s
Epoch 16/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.3023 - binary_accuracy: 0.8808 - auc: 0.8090 - pr: 0.3988 - val_loss: 0.3063 - val_binary_accuracy: 0.8793 - val_auc: 0.8061 - val_pr: 0.3990
Neighbors Score: 0.3075, Labels Score: 0.8233   Using time in epoch 16: 27.7196s
Epoch 17/1000
680/680 [==============================] - 155s 223ms/step - loss: 0.3018 - binary_accuracy: 0.8809 - auc: 0.8101 - pr: 0.4008 - val_loss: 0.3067 - val_binary_accuracy: 0.8791 - val_auc: 0.8074 - val_pr: 0.4001
Neighbors Score: 0.2781, Labels Score: 0.7023   Using time in epoch 17: 64.1304s
Epoch 18/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.3013 - binary_accuracy: 0.8810 - auc: 0.8109 - pr: 0.4024 - val_loss: 0.3065 - val_binary_accuracy: 0.8784 - val_auc: 0.8065 - val_pr: 0.3972
Neighbors Score: 0.2924, Labels Score: 0.7998   Using time in epoch 18: 56.8161s
Epoch 19/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.3010 - binary_accuracy: 0.8812 - auc: 0.8114 - pr: 0.4041 - val_loss: 0.3078 - val_binary_accuracy: 0.8769 - val_auc: 0.8062 - val_pr: 0.3947
Neighbors Score: 0.2739, Labels Score: 0.7017   Using time in epoch 19: 64.6538s
Epoch 20/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.3006 - binary_accuracy: 0.8813 - auc: 0.8121 - pr: 0.4056 - val_loss: 0.3073 - val_binary_accuracy: 0.8769 - val_auc: 0.8066 - val_pr: 0.3956
Neighbors Score: 0.2874, Labels Score: 0.7850   Using time in epoch 20: 58.5339s
Epoch 21/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.3003 - binary_accuracy: 0.8813 - auc: 0.8127 - pr: 0.4066 - val_loss: 0.3061 - val_binary_accuracy: 0.8787 - val_auc: 0.8070 - val_pr: 0.3981
Neighbors Score: 0.2876, Labels Score: 0.7339   Using time in epoch 21: 56.8782s
Epoch 22/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.3000 - binary_accuracy: 0.8814 - auc: 0.8133 - pr: 0.4079 - val_loss: 0.3058 - val_binary_accuracy: 0.8788 - val_auc: 0.8075 - val_pr: 0.3982
Neighbors Score: 0.2890, Labels Score: 0.8015   Using time in epoch 22: 58.3669s
Epoch 23/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2995 - binary_accuracy: 0.8816 - auc: 0.8140 - pr: 0.4098 - val_loss: 0.3061 - val_binary_accuracy: 0.8787 - val_auc: 0.8075 - val_pr: 0.3980
Neighbors Score: 0.2786, Labels Score: 0.7091   Using time in epoch 23: 61.0071s
Epoch 24/1000
680/680 [==============================] - 167s 244ms/step - loss: 0.2993 - binary_accuracy: 0.8816 - auc: 0.8144 - pr: 0.4107 - val_loss: 0.3054 - val_binary_accuracy: 0.8792 - val_auc: 0.8080 - val_pr: 0.4000
Neighbors Score: 0.2593, Labels Score: 0.6600   Using time in epoch 24: 86.2076s
Epoch 25/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2989 - binary_accuracy: 0.8817 - auc: 0.8153 - pr: 0.4119 - val_loss: 0.3073 - val_binary_accuracy: 0.8771 - val_auc: 0.8064 - val_pr: 0.3953
Neighbors Score: 0.2836, Labels Score: 0.7286   Using time in epoch 25: 56.3402s
Epoch 26/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2985 - binary_accuracy: 0.8817 - auc: 0.8159 - pr: 0.4134 - val_loss: 0.3054 - val_binary_accuracy: 0.8792 - val_auc: 0.8086 - val_pr: 0.4012
Neighbors Score: 0.2868, Labels Score: 0.7377   Using time in epoch 26: 55.5648s
Epoch 27/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2982 - binary_accuracy: 0.8819 - auc: 0.8166 - pr: 0.4148 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8094 - val_pr: 0.4036
Neighbors Score: 0.2861, Labels Score: 0.7357   Using time in epoch 27: 60.0166s
Epoch 28/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2980 - binary_accuracy: 0.8819 - auc: 0.8169 - pr: 0.4154 - val_loss: 0.3051 - val_binary_accuracy: 0.8793 - val_auc: 0.8090 - val_pr: 0.4013
Neighbors Score: 0.2834, Labels Score: 0.7222   Using time in epoch 28: 61.8453s
Epoch 29/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2976 - binary_accuracy: 0.8820 - auc: 0.8177 - pr: 0.4170 - val_loss: 0.3065 - val_binary_accuracy: 0.8790 - val_auc: 0.8088 - val_pr: 0.3986
Neighbors Score: 0.2873, Labels Score: 0.7373   Using time in epoch 29: 59.9457s
Epoch 30/1000
680/680 [==============================] - 156s 228ms/step - loss: 0.2972 - binary_accuracy: 0.8820 - auc: 0.8184 - pr: 0.4179 - val_loss: 0.3051 - val_binary_accuracy: 0.8787 - val_auc: 0.8094 - val_pr: 0.4008
Neighbors Score: 0.2931, Labels Score: 0.7556   Using time in epoch 30: 49.8141s
Epoch 31/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2970 - binary_accuracy: 0.8821 - auc: 0.8187 - pr: 0.4190 - val_loss: 0.3056 - val_binary_accuracy: 0.8791 - val_auc: 0.8080 - val_pr: 0.3994
Neighbors Score: 0.2895, Labels Score: 0.7816   Using time in epoch 31: 69.3337s
Epoch 32/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2968 - binary_accuracy: 0.8822 - auc: 0.8193 - pr: 0.4200 - val_loss: 0.3046 - val_binary_accuracy: 0.8793 - val_auc: 0.8099 - val_pr: 0.4031
Neighbors Score: 0.3013, Labels Score: 0.8010   Using time in epoch 32: 54.1505s
Epoch 33/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2964 - binary_accuracy: 0.8823 - auc: 0.8199 - pr: 0.4213 - val_loss: 0.3049 - val_binary_accuracy: 0.8789 - val_auc: 0.8097 - val_pr: 0.4006
Neighbors Score: 0.2859, Labels Score: 0.7322   Using time in epoch 33: 58.4731s
Epoch 34/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2962 - binary_accuracy: 0.8823 - auc: 0.8203 - pr: 0.4220 - val_loss: 0.3051 - val_binary_accuracy: 0.8789 - val_auc: 0.8109 - val_pr: 0.4037
Neighbors Score: 0.3138, Labels Score: 0.8509   Using time in epoch 34: 49.2989s
Epoch 35/1000
680/680 [==============================] - 168s 243ms/step - loss: 0.2959 - binary_accuracy: 0.8824 - auc: 0.8207 - pr: 0.4229 - val_loss: 0.3054 - val_binary_accuracy: 0.8790 - val_auc: 0.8091 - val_pr: 0.4011
Neighbors Score: 0.2900, Labels Score: 0.7512   Using time in epoch 35: 59.0502s
Epoch 36/1000
680/680 [==============================] - 158s 231ms/step - loss: 0.2955 - binary_accuracy: 0.8825 - auc: 0.8215 - pr: 0.4243 - val_loss: 0.3046 - val_binary_accuracy: 0.8794 - val_auc: 0.8109 - val_pr: 0.4048
Neighbors Score: 0.3075, Labels Score: 0.8577   Using time in epoch 36: 49.3392s
Epoch 37/1000
680/680 [==============================] - 167s 240ms/step - loss: 0.2955 - binary_accuracy: 0.8824 - auc: 0.8216 - pr: 0.4244 - val_loss: 0.3054 - val_binary_accuracy: 0.8791 - val_auc: 0.8094 - val_pr: 0.4008
Neighbors Score: 0.2801, Labels Score: 0.7215   Using time in epoch 37: 60.7498s
Epoch 38/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2951 - binary_accuracy: 0.8825 - auc: 0.8222 - pr: 0.4258 - val_loss: 0.3061 - val_binary_accuracy: 0.8792 - val_auc: 0.8104 - val_pr: 0.4030
Neighbors Score: 0.2930, Labels Score: 0.7657   Using time in epoch 38: 45.9519s
Epoch 39/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2948 - binary_accuracy: 0.8826 - auc: 0.8228 - pr: 0.4268 - val_loss: 0.3045 - val_binary_accuracy: 0.8792 - val_auc: 0.8107 - val_pr: 0.4031
Neighbors Score: 0.3157, Labels Score: 0.8579   Using time in epoch 39: 54.7439s
Epoch 40/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2945 - binary_accuracy: 0.8826 - auc: 0.8233 - pr: 0.4277 - val_loss: 0.3050 - val_binary_accuracy: 0.8793 - val_auc: 0.8101 - val_pr: 0.4034
Neighbors Score: 0.3027, Labels Score: 0.7590   Using time in epoch 40: 58.8478s
Epoch 41/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2943 - binary_accuracy: 0.8827 - auc: 0.8237 - pr: 0.4282 - val_loss: 0.3049 - val_binary_accuracy: 0.8790 - val_auc: 0.8104 - val_pr: 0.4035
Neighbors Score: 0.3099, Labels Score: 0.7830   Using time in epoch 41: 58.7770s
Epoch 42/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2941 - binary_accuracy: 0.8827 - auc: 0.8242 - pr: 0.4289 - val_loss: 0.3045 - val_binary_accuracy: 0.8794 - val_auc: 0.8109 - val_pr: 0.4044
Neighbors Score: 0.3294, Labels Score: 0.8789   Using time in epoch 42: 49.3580s
Epoch 43/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2939 - binary_accuracy: 0.8828 - auc: 0.8245 - pr: 0.4297 - val_loss: 0.3054 - val_binary_accuracy: 0.8791 - val_auc: 0.8110 - val_pr: 0.4038
Neighbors Score: 0.3260, Labels Score: 0.8071   Using time in epoch 43: 49.0609s
Epoch 44/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2936 - binary_accuracy: 0.8828 - auc: 0.8250 - pr: 0.4306 - val_loss: 0.3052 - val_binary_accuracy: 0.8790 - val_auc: 0.8089 - val_pr: 0.3996
Neighbors Score: 0.3186, Labels Score: 0.8047   Using time in epoch 44: 48.9006s
Epoch 45/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2935 - binary_accuracy: 0.8828 - auc: 0.8253 - pr: 0.4309 - val_loss: 0.3046 - val_binary_accuracy: 0.8788 - val_auc: 0.8105 - val_pr: 0.4034
Neighbors Score: 0.3363, Labels Score: 0.8834   Using time in epoch 45: 48.3915s
Epoch 46/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2932 - binary_accuracy: 0.8828 - auc: 0.8258 - pr: 0.4316 - val_loss: 0.3042 - val_binary_accuracy: 0.8793 - val_auc: 0.8109 - val_pr: 0.4038
Neighbors Score: 0.3340, Labels Score: 0.8449   Using time in epoch 46: 36.1434s
Epoch 47/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2929 - binary_accuracy: 0.8829 - auc: 0.8263 - pr: 0.4328 - val_loss: 0.3046 - val_binary_accuracy: 0.8792 - val_auc: 0.8111 - val_pr: 0.4035
Neighbors Score: 0.3489, Labels Score: 0.8699   Using time in epoch 47: 28.7461s
Epoch 48/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2928 - binary_accuracy: 0.8829 - auc: 0.8266 - pr: 0.4329 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4055
Neighbors Score: 0.3401, Labels Score: 0.8674   Using time in epoch 48: 30.6263s
Epoch 49/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2927 - binary_accuracy: 0.8829 - auc: 0.8268 - pr: 0.4334 - val_loss: 0.3038 - val_binary_accuracy: 0.8794 - val_auc: 0.8117 - val_pr: 0.4061
Neighbors Score: 0.3379, Labels Score: 0.8587   Using time in epoch 49: 32.3220s
Epoch 50/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2923 - binary_accuracy: 0.8830 - auc: 0.8274 - pr: 0.4344 - val_loss: 0.3038 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4056
Neighbors Score: 0.3376, Labels Score: 0.8654   Using time in epoch 50: 30.3013s
Epoch 51/1000
680/680 [==============================] - 168s 242ms/step - loss: 0.2922 - binary_accuracy: 0.8830 - auc: 0.8277 - pr: 0.4349 - val_loss: 0.3043 - val_binary_accuracy: 0.8791 - val_auc: 0.8113 - val_pr: 0.4041
Neighbors Score: 0.3509, Labels Score: 0.8757   Using time in epoch 51: 26.9339s
Epoch 52/1000
680/680 [==============================] - 168s 244ms/step - loss: 0.2919 - binary_accuracy: 0.8831 - auc: 0.8281 - pr: 0.4358 - val_loss: 0.3041 - val_binary_accuracy: 0.8792 - val_auc: 0.8114 - val_pr: 0.4043
Neighbors Score: 0.3566, Labels Score: 0.8883   Using time in epoch 52: 27.3166s
Epoch 53/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2918 - binary_accuracy: 0.8831 - auc: 0.8283 - pr: 0.4358 - val_loss: 0.3040 - val_binary_accuracy: 0.8793 - val_auc: 0.8114 - val_pr: 0.4041
Neighbors Score: 0.3566, Labels Score: 0.8812   Using time in epoch 53: 26.4427s
Epoch 54/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2917 - binary_accuracy: 0.8831 - auc: 0.8285 - pr: 0.4361 - val_loss: 0.3055 - val_binary_accuracy: 0.8794 - val_auc: 0.8114 - val_pr: 0.4046
Neighbors Score: 0.3575, Labels Score: 0.8936   Using time in epoch 54: 28.3369s
Epoch 55/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2915 - binary_accuracy: 0.8831 - auc: 0.8288 - pr: 0.4367 - val_loss: 0.3069 - val_binary_accuracy: 0.8789 - val_auc: 0.8117 - val_pr: 0.4048
Neighbors Score: 0.3582, Labels Score: 0.8925   Using time in epoch 55: 27.9466s
Epoch 56/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2914 - binary_accuracy: 0.8832 - auc: 0.8292 - pr: 0.4371 - val_loss: 0.3039 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4055
Neighbors Score: 0.3568, Labels Score: 0.8906   Using time in epoch 56: 25.8270s
Epoch 57/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2913 - binary_accuracy: 0.8832 - auc: 0.8294 - pr: 0.4374 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4056
Neighbors Score: 0.3429, Labels Score: 0.8860   Using time in epoch 57: 25.9176s
Epoch 58/1000
680/680 [==============================] - 169s 244ms/step - loss: 0.2911 - binary_accuracy: 0.8832 - auc: 0.8296 - pr: 0.4378 - val_loss: 0.3037 - val_binary_accuracy: 0.8793 - val_auc: 0.8119 - val_pr: 0.4056
Neighbors Score: 0.3518, Labels Score: 0.8866   Using time in epoch 58: 25.0842s
Epoch 59/1000
680/680 [==============================] - 166s 238ms/step - loss: 0.2910 - binary_accuracy: 0.8832 - auc: 0.8299 - pr: 0.4382 - val_loss: 0.3043 - val_binary_accuracy: 0.8792 - val_auc: 0.8117 - val_pr: 0.4047
Neighbors Score: 0.3543, Labels Score: 0.8891   Using time in epoch 59: 25.7932s
Epoch 60/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2907 - binary_accuracy: 0.8833 - auc: 0.8303 - pr: 0.4390 - val_loss: 0.3048 - val_binary_accuracy: 0.8794 - val_auc: 0.8111 - val_pr: 0.4049
Neighbors Score: 0.3616, Labels Score: 0.8879   Using time in epoch 60: 26.4854s
Epoch 61/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2906 - binary_accuracy: 0.8833 - auc: 0.8305 - pr: 0.4393 - val_loss: 0.3045 - val_binary_accuracy: 0.8790 - val_auc: 0.8114 - val_pr: 0.4029
Neighbors Score: 0.3568, Labels Score: 0.8894   Using time in epoch 61: 26.7751s
Epoch 62/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.2904 - binary_accuracy: 0.8833 - auc: 0.8308 - pr: 0.4397 - val_loss: 0.3044 - val_binary_accuracy: 0.8793 - val_auc: 0.8120 - val_pr: 0.4058
Neighbors Score: 0.3560, Labels Score: 0.8857   Using time in epoch 62: 25.9551s
Epoch 63/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2903 - binary_accuracy: 0.8833 - auc: 0.8310 - pr: 0.4400 - val_loss: 0.3048 - val_binary_accuracy: 0.8792 - val_auc: 0.8113 - val_pr: 0.4042
Neighbors Score: 0.3636, Labels Score: 0.8852   Using time in epoch 63: 27.9633s
Epoch 64/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2903 - binary_accuracy: 0.8833 - auc: 0.8311 - pr: 0.4401 - val_loss: 0.3048 - val_binary_accuracy: 0.8794 - val_auc: 0.8114 - val_pr: 0.4050
Neighbors Score: 0.3542, Labels Score: 0.8934   Using time in epoch 64: 25.5709s
Epoch 65/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2901 - binary_accuracy: 0.8834 - auc: 0.8315 - pr: 0.4409 - val_loss: 0.3040 - val_binary_accuracy: 0.8792 - val_auc: 0.8118 - val_pr: 0.4049
Neighbors Score: 0.3554, Labels Score: 0.8868   Using time in epoch 65: 25.4701s
Epoch 66/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2901 - binary_accuracy: 0.8833 - auc: 0.8315 - pr: 0.4406 - val_loss: 0.3055 - val_binary_accuracy: 0.8794 - val_auc: 0.8117 - val_pr: 0.4060
Neighbors Score: 0.3568, Labels Score: 0.8869   Using time in epoch 66: 26.3894s
Epoch 67/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2900 - binary_accuracy: 0.8834 - auc: 0.8317 - pr: 0.4407 - val_loss: 0.3044 - val_binary_accuracy: 0.8792 - val_auc: 0.8115 - val_pr: 0.4047
Neighbors Score: 0.3478, Labels Score: 0.8877   Using time in epoch 67: 27.0294s
Epoch 68/1000
680/680 [==============================] - 170s 246ms/step - loss: 0.2899 - binary_accuracy: 0.8834 - auc: 0.8319 - pr: 0.4411 - val_loss: 0.3042 - val_binary_accuracy: 0.8793 - val_auc: 0.8116 - val_pr: 0.4051
Neighbors Score: 0.3524, Labels Score: 0.8849   Using time in epoch 68: 27.1872s
Epoch 69/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2896 - binary_accuracy: 0.8834 - auc: 0.8322 - pr: 0.4419 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4058
Neighbors Score: 0.3490, Labels Score: 0.8819   Using time in epoch 69: 28.1986s
Epoch 70/1000
680/680 [==============================] - 170s 247ms/step - loss: 0.2896 - binary_accuracy: 0.8834 - auc: 0.8323 - pr: 0.4418 - val_loss: 0.3039 - val_binary_accuracy: 0.8792 - val_auc: 0.8115 - val_pr: 0.4047
Neighbors Score: 0.3550, Labels Score: 0.8830   Using time in epoch 70: 26.5124s
Epoch 71/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2895 - binary_accuracy: 0.8835 - auc: 0.8325 - pr: 0.4423 - val_loss: 0.3046 - val_binary_accuracy: 0.8792 - val_auc: 0.8114 - val_pr: 0.4046
Neighbors Score: 0.3642, Labels Score: 0.8806   Using time in epoch 71: 26.2156s
Epoch 72/1000
680/680 [==============================] - 168s 242ms/step - loss: 0.2894 - binary_accuracy: 0.8835 - auc: 0.8327 - pr: 0.4425 - val_loss: 0.3047 - val_binary_accuracy: 0.8791 - val_auc: 0.8114 - val_pr: 0.4036
Neighbors Score: 0.3593, Labels Score: 0.8859   Using time in epoch 72: 24.8393s
Epoch 73/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2893 - binary_accuracy: 0.8835 - auc: 0.8329 - pr: 0.4429 - val_loss: 0.3049 - val_binary_accuracy: 0.8791 - val_auc: 0.8115 - val_pr: 0.4045
Neighbors Score: 0.3657, Labels Score: 0.8837   Using time in epoch 73: 25.4754s
Epoch 74/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2892 - binary_accuracy: 0.8835 - auc: 0.8330 - pr: 0.4431 - val_loss: 0.3041 - val_binary_accuracy: 0.8793 - val_auc: 0.8118 - val_pr: 0.4058
Neighbors Score: 0.3639, Labels Score: 0.8872   Using time in epoch 74: 27.4441s
Epoch 75/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2891 - binary_accuracy: 0.8835 - auc: 0.8332 - pr: 0.4433 - val_loss: 0.3049 - val_binary_accuracy: 0.8788 - val_auc: 0.8109 - val_pr: 0.4021
Neighbors Score: 0.3704, Labels Score: 0.8858   Using time in epoch 75: 26.2960s
Epoch 76/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2891 - binary_accuracy: 0.8835 - auc: 0.8332 - pr: 0.4430 - val_loss: 0.3038 - val_binary_accuracy: 0.8793 - val_auc: 0.8118 - val_pr: 0.4052
Neighbors Score: 0.3607, Labels Score: 0.8816   Using time in epoch 76: 24.9156s
Epoch 77/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.2889 - binary_accuracy: 0.8835 - auc: 0.8335 - pr: 0.4437 - val_loss: 0.3038 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4066
Neighbors Score: 0.3616, Labels Score: 0.8820   Using time in epoch 77: 25.9712s
Epoch 78/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2889 - binary_accuracy: 0.8835 - auc: 0.8336 - pr: 0.4438 - val_loss: 0.3039 - val_binary_accuracy: 0.8794 - val_auc: 0.8117 - val_pr: 0.4063
Neighbors Score: 0.3675, Labels Score: 0.8838   Using time in epoch 78: 25.7065s
Epoch 79/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2888 - binary_accuracy: 0.8836 - auc: 0.8337 - pr: 0.4442 - val_loss: 0.3048 - val_binary_accuracy: 0.8791 - val_auc: 0.8116 - val_pr: 0.4047
Neighbors Score: 0.3710, Labels Score: 0.8860   Using time in epoch 79: 25.9834s
Epoch 80/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2888 - binary_accuracy: 0.8835 - auc: 0.8337 - pr: 0.4440 - val_loss: 0.3050 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4066
Neighbors Score: 0.3680, Labels Score: 0.8838   Using time in epoch 80: 25.8499s
Epoch 81/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2887 - binary_accuracy: 0.8835 - auc: 0.8339 - pr: 0.4442 - val_loss: 0.3045 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4066
Neighbors Score: 0.3729, Labels Score: 0.8832   Using time in epoch 81: 27.7426s
Epoch 82/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2886 - binary_accuracy: 0.8836 - auc: 0.8341 - pr: 0.4446 - val_loss: 0.3046 - val_binary_accuracy: 0.8792 - val_auc: 0.8115 - val_pr: 0.4054
Neighbors Score: 0.3688, Labels Score: 0.8825   Using time in epoch 82: 25.6480s
Epoch 83/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2887 - binary_accuracy: 0.8835 - auc: 0.8340 - pr: 0.4442 - val_loss: 0.3058 - val_binary_accuracy: 0.8793 - val_auc: 0.8108 - val_pr: 0.4048
Neighbors Score: 0.3677, Labels Score: 0.8841   Using time in epoch 83: 26.2671s
Epoch 84/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2885 - binary_accuracy: 0.8836 - auc: 0.8343 - pr: 0.4447 - val_loss: 0.3037 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4068
Neighbors Score: 0.3654, Labels Score: 0.8820   Using time in epoch 84: 25.0156s
Epoch 85/1000
680/680 [==============================] - 160s 234ms/step - loss: 0.2885 - binary_accuracy: 0.8836 - auc: 0.8343 - pr: 0.4447 - val_loss: 0.3044 - val_binary_accuracy: 0.8793 - val_auc: 0.8119 - val_pr: 0.4062
Neighbors Score: 0.3678, Labels Score: 0.8858   Using time in epoch 85: 25.5975s
Epoch 86/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2883 - binary_accuracy: 0.8836 - auc: 0.8346 - pr: 0.4454 - val_loss: 0.3038 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4062
Neighbors Score: 0.3627, Labels Score: 0.8839   Using time in epoch 86: 25.4751s
Epoch 87/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2882 - binary_accuracy: 0.8836 - auc: 0.8347 - pr: 0.4455 - val_loss: 0.3037 - val_binary_accuracy: 0.8793 - val_auc: 0.8121 - val_pr: 0.4065
Neighbors Score: 0.3738, Labels Score: 0.8822   Using time in epoch 87: 25.8740s
Epoch 88/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2882 - binary_accuracy: 0.8836 - auc: 0.8347 - pr: 0.4455 - val_loss: 0.3047 - val_binary_accuracy: 0.8793 - val_auc: 0.8116 - val_pr: 0.4057
Neighbors Score: 0.3718, Labels Score: 0.8842   Using time in epoch 88: 27.0818s
Epoch 89/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2881 - binary_accuracy: 0.8837 - auc: 0.8349 - pr: 0.4459 - val_loss: 0.3054 - val_binary_accuracy: 0.8793 - val_auc: 0.8116 - val_pr: 0.4057
Neighbors Score: 0.3726, Labels Score: 0.8849   Using time in epoch 89: 25.8252s
Epoch 90/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2881 - binary_accuracy: 0.8836 - auc: 0.8349 - pr: 0.4458 - val_loss: 0.3046 - val_binary_accuracy: 0.8792 - val_auc: 0.8117 - val_pr: 0.4054
Neighbors Score: 0.3703, Labels Score: 0.8866   Using time in epoch 90: 25.6432s
Epoch 91/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2881 - binary_accuracy: 0.8837 - auc: 0.8350 - pr: 0.4457 - val_loss: 0.3048 - val_binary_accuracy: 0.8792 - val_auc: 0.8114 - val_pr: 0.4051
Neighbors Score: 0.3712, Labels Score: 0.8837   Using time in epoch 91: 25.8475s
Epoch 92/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2879 - binary_accuracy: 0.8837 - auc: 0.8352 - pr: 0.4463 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4064
Neighbors Score: 0.3749, Labels Score: 0.8859   Using time in epoch 92: 26.7891s
Epoch 93/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2879 - binary_accuracy: 0.8837 - auc: 0.8353 - pr: 0.4465 - val_loss: 0.3049 - val_binary_accuracy: 0.8793 - val_auc: 0.8114 - val_pr: 0.4051
Neighbors Score: 0.3807, Labels Score: 0.8878   Using time in epoch 93: 25.5804s
Epoch 94/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2879 - binary_accuracy: 0.8836 - auc: 0.8353 - pr: 0.4461 - val_loss: 0.3046 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4060
Neighbors Score: 0.3706, Labels Score: 0.8827   Using time in epoch 94: 25.9757s
Epoch 95/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2878 - binary_accuracy: 0.8837 - auc: 0.8355 - pr: 0.4466 - val_loss: 0.3045 - val_binary_accuracy: 0.8792 - val_auc: 0.8118 - val_pr: 0.4058
Neighbors Score: 0.3759, Labels Score: 0.8855   Using time in epoch 95: 25.1642s
Epoch 96/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2877 - binary_accuracy: 0.8837 - auc: 0.8355 - pr: 0.4468 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8117 - val_pr: 0.4066
Neighbors Score: 0.3804, Labels Score: 0.8867   Using time in epoch 96: 27.3567s
Epoch 97/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2877 - binary_accuracy: 0.8837 - auc: 0.8356 - pr: 0.4466 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4072
Neighbors Score: 0.3762, Labels Score: 0.8858   Using time in epoch 97: 27.2061s
Epoch 98/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2877 - binary_accuracy: 0.8837 - auc: 0.8356 - pr: 0.4467 - val_loss: 0.3042 - val_binary_accuracy: 0.8793 - val_auc: 0.8119 - val_pr: 0.4065
Neighbors Score: 0.3726, Labels Score: 0.8855   Using time in epoch 98: 25.2735s
Epoch 99/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2876 - binary_accuracy: 0.8837 - auc: 0.8358 - pr: 0.4471 - val_loss: 0.3036 - val_binary_accuracy: 0.8794 - val_auc: 0.8122 - val_pr: 0.4069
Neighbors Score: 0.3735, Labels Score: 0.8849   Using time in epoch 99: 26.6835s
Epoch 100/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2875 - binary_accuracy: 0.8838 - auc: 0.8359 - pr: 0.4475 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8122 - val_pr: 0.4069
Neighbors Score: 0.3788, Labels Score: 0.8864   Using time in epoch 100: 26.1599s
Epoch 101/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2875 - binary_accuracy: 0.8837 - auc: 0.8359 - pr: 0.4474 - val_loss: 0.3043 - val_binary_accuracy: 0.8793 - val_auc: 0.8117 - val_pr: 0.4054
Neighbors Score: 0.3787, Labels Score: 0.8884   Using time in epoch 101: 25.6366s
Epoch 102/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2875 - binary_accuracy: 0.8837 - auc: 0.8360 - pr: 0.4472 - val_loss: 0.3046 - val_binary_accuracy: 0.8792 - val_auc: 0.8118 - val_pr: 0.4063
Neighbors Score: 0.3754, Labels Score: 0.8877   Using time in epoch 102: 27.6916s
Epoch 103/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2875 - binary_accuracy: 0.8837 - auc: 0.8360 - pr: 0.4473 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4069
Neighbors Score: 0.3796, Labels Score: 0.8871   Using time in epoch 103: 28.2777s
Epoch 104/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2874 - binary_accuracy: 0.8837 - auc: 0.8361 - pr: 0.4475 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4076
Neighbors Score: 0.3805, Labels Score: 0.8843   Using time in epoch 104: 25.6754s
Epoch 105/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2874 - binary_accuracy: 0.8837 - auc: 0.8362 - pr: 0.4477 - val_loss: 0.3046 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4059
Neighbors Score: 0.3797, Labels Score: 0.8864   Using time in epoch 105: 31.0918s
Epoch 106/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2873 - binary_accuracy: 0.8838 - auc: 0.8363 - pr: 0.4478 - val_loss: 0.3039 - val_binary_accuracy: 0.8793 - val_auc: 0.8120 - val_pr: 0.4060
Neighbors Score: 0.3782, Labels Score: 0.8853   Using time in epoch 106: 29.1876s
Epoch 107/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2874 - binary_accuracy: 0.8837 - auc: 0.8362 - pr: 0.4475 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4075
Neighbors Score: 0.3851, Labels Score: 0.8866   Using time in epoch 107: 25.7348s
Epoch 108/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2873 - binary_accuracy: 0.8838 - auc: 0.8363 - pr: 0.4478 - val_loss: 0.3035 - val_binary_accuracy: 0.8794 - val_auc: 0.8124 - val_pr: 0.4077
Neighbors Score: 0.3792, Labels Score: 0.8853   Using time in epoch 108: 26.4708s
Epoch 109/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2872 - binary_accuracy: 0.8838 - auc: 0.8365 - pr: 0.4481 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8122 - val_pr: 0.4077
Neighbors Score: 0.3770, Labels Score: 0.8885   Using time in epoch 109: 25.7877s
Epoch 110/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2872 - binary_accuracy: 0.8838 - auc: 0.8365 - pr: 0.4480 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4072
Neighbors Score: 0.3858, Labels Score: 0.8888   Using time in epoch 110: 26.5648s
Epoch 111/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2872 - binary_accuracy: 0.8838 - auc: 0.8365 - pr: 0.4481 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4070
Neighbors Score: 0.3846, Labels Score: 0.8887   Using time in epoch 111: 27.4412s
Epoch 112/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2872 - binary_accuracy: 0.8838 - auc: 0.8366 - pr: 0.4481 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4075
Neighbors Score: 0.3894, Labels Score: 0.8894   Using time in epoch 112: 27.6545s
Epoch 113/1000
680/680 [==============================] - 155s 226ms/step - loss: 0.2871 - binary_accuracy: 0.8838 - auc: 0.8366 - pr: 0.4483 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4071
Neighbors Score: 0.3835, Labels Score: 0.8880   Using time in epoch 113: 29.2374s
Epoch 114/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2870 - binary_accuracy: 0.8838 - auc: 0.8367 - pr: 0.4485 - val_loss: 0.3044 - val_binary_accuracy: 0.8793 - val_auc: 0.8119 - val_pr: 0.4067
Neighbors Score: 0.3852, Labels Score: 0.8868   Using time in epoch 114: 27.3317s
Epoch 115/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2870 - binary_accuracy: 0.8838 - auc: 0.8368 - pr: 0.4485 - val_loss: 0.3045 - val_binary_accuracy: 0.8792 - val_auc: 0.8114 - val_pr: 0.4058
Neighbors Score: 0.3855, Labels Score: 0.8914   Using time in epoch 115: 26.4893s
Epoch 116/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2870 - binary_accuracy: 0.8838 - auc: 0.8368 - pr: 0.4487 - val_loss: 0.3045 - val_binary_accuracy: 0.8793 - val_auc: 0.8115 - val_pr: 0.4060
Neighbors Score: 0.3834, Labels Score: 0.8875   Using time in epoch 116: 28.0825s
Epoch 117/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2869 - binary_accuracy: 0.8838 - auc: 0.8370 - pr: 0.4490 - val_loss: 0.3043 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4068
Neighbors Score: 0.3826, Labels Score: 0.8864   Using time in epoch 117: 29.5220s
Epoch 118/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2869 - binary_accuracy: 0.8838 - auc: 0.8370 - pr: 0.4488 - val_loss: 0.3036 - val_binary_accuracy: 0.8795 - val_auc: 0.8123 - val_pr: 0.4080
Neighbors Score: 0.3833, Labels Score: 0.8877   Using time in epoch 118: 25.8667s
Epoch 119/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2869 - binary_accuracy: 0.8838 - auc: 0.8370 - pr: 0.4490 - val_loss: 0.3038 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4076
Neighbors Score: 0.3835, Labels Score: 0.8849   Using time in epoch 119: 27.2296s
Epoch 120/1000
680/680 [==============================] - 156s 228ms/step - loss: 0.2869 - binary_accuracy: 0.8838 - auc: 0.8371 - pr: 0.4489 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4071
Neighbors Score: 0.3847, Labels Score: 0.8882   Using time in epoch 120: 25.9605s
Epoch 121/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2868 - binary_accuracy: 0.8838 - auc: 0.8371 - pr: 0.4490 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4073
Neighbors Score: 0.3878, Labels Score: 0.8884   Using time in epoch 121: 26.7785s
Epoch 122/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2868 - binary_accuracy: 0.8838 - auc: 0.8372 - pr: 0.4492 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4068
Neighbors Score: 0.3860, Labels Score: 0.8870   Using time in epoch 122: 26.3848s
Epoch 123/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2868 - binary_accuracy: 0.8838 - auc: 0.8372 - pr: 0.4491 - val_loss: 0.3045 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4065
Neighbors Score: 0.3884, Labels Score: 0.8891   Using time in epoch 123: 26.4708s
Epoch 124/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2867 - binary_accuracy: 0.8838 - auc: 0.8372 - pr: 0.4493 - val_loss: 0.3043 - val_binary_accuracy: 0.8793 - val_auc: 0.8118 - val_pr: 0.4062
Neighbors Score: 0.3888, Labels Score: 0.8882   Using time in epoch 124: 26.8536s
Epoch 125/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2867 - binary_accuracy: 0.8839 - auc: 0.8374 - pr: 0.4495 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4069
Neighbors Score: 0.3905, Labels Score: 0.8900   Using time in epoch 125: 25.8470s
Epoch 126/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2867 - binary_accuracy: 0.8839 - auc: 0.8374 - pr: 0.4493 - val_loss: 0.3036 - val_binary_accuracy: 0.8795 - val_auc: 0.8124 - val_pr: 0.4081
Neighbors Score: 0.3929, Labels Score: 0.8881   Using time in epoch 126: 27.3123s
Epoch 127/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2866 - binary_accuracy: 0.8838 - auc: 0.8374 - pr: 0.4495 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8120 - val_pr: 0.4076
Neighbors Score: 0.3883, Labels Score: 0.8901   Using time in epoch 127: 26.5573s
Epoch 128/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2866 - binary_accuracy: 0.8839 - auc: 0.8375 - pr: 0.4496 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4066
Neighbors Score: 0.3847, Labels Score: 0.8877   Using time in epoch 128: 26.2946s
Epoch 129/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2866 - binary_accuracy: 0.8839 - auc: 0.8375 - pr: 0.4497 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4066
Neighbors Score: 0.3880, Labels Score: 0.8883   Using time in epoch 129: 26.0769s
Epoch 130/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2865 - binary_accuracy: 0.8839 - auc: 0.8376 - pr: 0.4498 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4073
Neighbors Score: 0.3881, Labels Score: 0.8905   Using time in epoch 130: 26.7934s
Epoch 131/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2866 - binary_accuracy: 0.8839 - auc: 0.8374 - pr: 0.4496 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8121 - val_pr: 0.4078
Neighbors Score: 0.3901, Labels Score: 0.8903   Using time in epoch 131: 26.7222s
Epoch 132/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2865 - binary_accuracy: 0.8839 - auc: 0.8377 - pr: 0.4500 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4073
Neighbors Score: 0.3916, Labels Score: 0.8897   Using time in epoch 132: 28.6470s
Epoch 133/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2865 - binary_accuracy: 0.8839 - auc: 0.8376 - pr: 0.4498 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4070
Neighbors Score: 0.3883, Labels Score: 0.8869   Using time in epoch 133: 26.8708s
Epoch 134/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2865 - binary_accuracy: 0.8839 - auc: 0.8376 - pr: 0.4498 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8122 - val_pr: 0.4083
Neighbors Score: 0.3888, Labels Score: 0.8864   Using time in epoch 134: 26.5704s
Epoch 135/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2865 - binary_accuracy: 0.8838 - auc: 0.8376 - pr: 0.4496 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8122 - val_pr: 0.4080
Neighbors Score: 0.3926, Labels Score: 0.8889   Using time in epoch 135: 27.8381s
Epoch 136/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2865 - binary_accuracy: 0.8839 - auc: 0.8377 - pr: 0.4500 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8123 - val_pr: 0.4080
Neighbors Score: 0.3861, Labels Score: 0.8874   Using time in epoch 136: 26.4816s
Epoch 137/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2864 - binary_accuracy: 0.8839 - auc: 0.8378 - pr: 0.4501 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4074
Neighbors Score: 0.3876, Labels Score: 0.8890   Using time in epoch 137: 27.3792s
Epoch 138/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2864 - binary_accuracy: 0.8839 - auc: 0.8377 - pr: 0.4499 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4073
Neighbors Score: 0.3905, Labels Score: 0.8885   Using time in epoch 138: 26.0688s
Epoch 139/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2863 - binary_accuracy: 0.8839 - auc: 0.8379 - pr: 0.4504 - val_loss: 0.3039 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4075
Neighbors Score: 0.3873, Labels Score: 0.8876   Using time in epoch 139: 26.4731s
Epoch 140/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2863 - binary_accuracy: 0.8839 - auc: 0.8379 - pr: 0.4503 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4073
Neighbors Score: 0.3928, Labels Score: 0.8888   Using time in epoch 140: 28.9034s
Epoch 141/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2863 - binary_accuracy: 0.8839 - auc: 0.8380 - pr: 0.4504 - val_loss: 0.3045 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4065
Neighbors Score: 0.3898, Labels Score: 0.8906   Using time in epoch 141: 27.5755s
Epoch 142/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2864 - binary_accuracy: 0.8839 - auc: 0.8379 - pr: 0.4501 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4073
Neighbors Score: 0.3940, Labels Score: 0.8913   Using time in epoch 142: 27.3248s
Epoch 143/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2863 - binary_accuracy: 0.8839 - auc: 0.8380 - pr: 0.4505 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4075
Neighbors Score: 0.3884, Labels Score: 0.8891   Using time in epoch 143: 27.5334s
Epoch 144/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2864 - binary_accuracy: 0.8839 - auc: 0.8379 - pr: 0.4501 - val_loss: 0.3043 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4072
Neighbors Score: 0.3918, Labels Score: 0.8917   Using time in epoch 144: 27.9204s
Epoch 145/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2863 - binary_accuracy: 0.8839 - auc: 0.8380 - pr: 0.4503 - val_loss: 0.3043 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4072
Neighbors Score: 0.3872, Labels Score: 0.8886   Using time in epoch 145: 25.6989s
Epoch 146/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8381 - pr: 0.4505 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8122 - val_pr: 0.4079
Neighbors Score: 0.3916, Labels Score: 0.8896   Using time in epoch 146: 27.3616s
Epoch 147/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8381 - pr: 0.4506 - val_loss: 0.3044 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4072
Neighbors Score: 0.3938, Labels Score: 0.8892   Using time in epoch 147: 28.1304s
Epoch 148/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8381 - pr: 0.4506 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4072
Neighbors Score: 0.3917, Labels Score: 0.8898   Using time in epoch 148: 28.7152s
Epoch 149/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2861 - binary_accuracy: 0.8840 - auc: 0.8382 - pr: 0.4509 - val_loss: 0.3039 - val_binary_accuracy: 0.8794 - val_auc: 0.8122 - val_pr: 0.4075
Neighbors Score: 0.3918, Labels Score: 0.8894   Using time in epoch 149: 28.2257s
Epoch 150/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8382 - pr: 0.4508 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4075
Neighbors Score: 0.3953, Labels Score: 0.8912   Using time in epoch 150: 28.4136s
Epoch 151/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8382 - pr: 0.4506 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4077
Neighbors Score: 0.3931, Labels Score: 0.8880   Using time in epoch 151: 26.2629s
Epoch 152/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2862 - binary_accuracy: 0.8839 - auc: 0.8382 - pr: 0.4507 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4068
Neighbors Score: 0.3950, Labels Score: 0.8892   Using time in epoch 152: 26.1941s
Epoch 153/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8382 - pr: 0.4509 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4072
Neighbors Score: 0.3966, Labels Score: 0.8901   Using time in epoch 153: 26.7933s
Epoch 154/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8383 - pr: 0.4508 - val_loss: 0.3035 - val_binary_accuracy: 0.8796 - val_auc: 0.8122 - val_pr: 0.4081
Neighbors Score: 0.3942, Labels Score: 0.8879   Using time in epoch 154: 26.4795s
Epoch 155/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8383 - pr: 0.4509 - val_loss: 0.3035 - val_binary_accuracy: 0.8795 - val_auc: 0.8123 - val_pr: 0.4078
Neighbors Score: 0.3947, Labels Score: 0.8897   Using time in epoch 155: 28.0350s
Epoch 156/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8384 - pr: 0.4511 - val_loss: 0.3045 - val_binary_accuracy: 0.8793 - val_auc: 0.8119 - val_pr: 0.4068
Neighbors Score: 0.3965, Labels Score: 0.8917   Using time in epoch 156: 27.4691s
Epoch 157/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8384 - pr: 0.4510 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4066
Neighbors Score: 0.3955, Labels Score: 0.8907   Using time in epoch 157: 25.7028s
Epoch 158/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8384 - pr: 0.4509 - val_loss: 0.3044 - val_binary_accuracy: 0.8794 - val_auc: 0.8118 - val_pr: 0.4070
Neighbors Score: 0.3965, Labels Score: 0.8917   Using time in epoch 158: 25.8026s
Epoch 159/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2860 - binary_accuracy: 0.8839 - auc: 0.8385 - pr: 0.4511 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4077
Neighbors Score: 0.3950, Labels Score: 0.8883   Using time in epoch 159: 25.4838s
Epoch 160/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2861 - binary_accuracy: 0.8839 - auc: 0.8384 - pr: 0.4510 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4077
Neighbors Score: 0.3937, Labels Score: 0.8893   Using time in epoch 160: 25.9053s
Epoch 161/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2860 - binary_accuracy: 0.8840 - auc: 0.8384 - pr: 0.4512 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8122 - val_pr: 0.4083
Neighbors Score: 0.3964, Labels Score: 0.8910   Using time in epoch 161: 26.6878s
Epoch 162/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8386 - pr: 0.4513 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4074
Neighbors Score: 0.3957, Labels Score: 0.8909   Using time in epoch 162: 26.9841s
Epoch 163/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2860 - binary_accuracy: 0.8839 - auc: 0.8385 - pr: 0.4512 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4078
Neighbors Score: 0.3969, Labels Score: 0.8908   Using time in epoch 163: 28.6346s
Epoch 164/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8386 - pr: 0.4515 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8122 - val_pr: 0.4077
Neighbors Score: 0.3961, Labels Score: 0.8894   Using time in epoch 164: 27.0333s
Epoch 165/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8386 - pr: 0.4513 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4073
Neighbors Score: 0.3978, Labels Score: 0.8895   Using time in epoch 165: 26.8961s
Epoch 166/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4515 - val_loss: 0.3040 - val_binary_accuracy: 0.8794 - val_auc: 0.8121 - val_pr: 0.4074
Neighbors Score: 0.3971, Labels Score: 0.8923   Using time in epoch 166: 26.6179s
Epoch 167/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8386 - pr: 0.4514 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4071
Neighbors Score: 0.3967, Labels Score: 0.8925   Using time in epoch 167: 25.3180s
Epoch 168/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4514 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4079
Neighbors Score: 0.3967, Labels Score: 0.8898   Using time in epoch 168: 27.5014s
Epoch 169/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8386 - pr: 0.4514 - val_loss: 0.3033 - val_binary_accuracy: 0.8796 - val_auc: 0.8124 - val_pr: 0.4080
Neighbors Score: 0.3961, Labels Score: 0.8884   Using time in epoch 169: 26.1871s
Epoch 170/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4515 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4078
Neighbors Score: 0.3996, Labels Score: 0.8916   Using time in epoch 170: 26.0022s
Epoch 171/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2859 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4513 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4071
Neighbors Score: 0.3968, Labels Score: 0.8898   Using time in epoch 171: 25.4336s
Epoch 172/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4517 - val_loss: 0.3043 - val_binary_accuracy: 0.8794 - val_auc: 0.8120 - val_pr: 0.4072
Neighbors Score: 0.3988, Labels Score: 0.8908   Using time in epoch 172: 26.3683s
Epoch 173/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8387 - pr: 0.4515 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4075
Neighbors Score: 0.3986, Labels Score: 0.8912   Using time in epoch 173: 26.0361s
Epoch 174/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4516 - val_loss: 0.3038 - val_binary_accuracy: 0.8796 - val_auc: 0.8121 - val_pr: 0.4080
Neighbors Score: 0.3970, Labels Score: 0.8901   Using time in epoch 174: 28.1757s
Epoch 175/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4518 - val_loss: 0.3038 - val_binary_accuracy: 0.8796 - val_auc: 0.8121 - val_pr: 0.4081
Neighbors Score: 0.3987, Labels Score: 0.8912   Using time in epoch 175: 27.3912s
Epoch 176/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4515 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4072
Neighbors Score: 0.4006, Labels Score: 0.8934   Using time in epoch 176: 26.5088s
Epoch 177/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4517 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4079
Neighbors Score: 0.3971, Labels Score: 0.8905   Using time in epoch 177: 25.4201s
Epoch 178/1000
680/680 [==============================] - 162s 232ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4516 - val_loss: 0.3036 - val_binary_accuracy: 0.8795 - val_auc: 0.8122 - val_pr: 0.4079
Neighbors Score: 0.3979, Labels Score: 0.8908   Using time in epoch 178: 26.0672s
Epoch 179/1000
680/680 [==============================] - 162s 232ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4518 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4078
Neighbors Score: 0.3972, Labels Score: 0.8918   Using time in epoch 179: 25.5250s
Epoch 180/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2858 - binary_accuracy: 0.8840 - auc: 0.8388 - pr: 0.4516 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4075
Neighbors Score: 0.3997, Labels Score: 0.8934   Using time in epoch 180: 27.2278s
Epoch 181/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4521 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4076
Neighbors Score: 0.3981, Labels Score: 0.8924   Using time in epoch 181: 26.4099s
Epoch 182/1000
680/680 [==============================] - 160s 234ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4521 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4078
Neighbors Score: 0.3982, Labels Score: 0.8918   Using time in epoch 182: 26.4286s
Epoch 183/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4521 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4075
Neighbors Score: 0.3998, Labels Score: 0.8915   Using time in epoch 183: 26.0691s
Epoch 184/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4520 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4080
Neighbors Score: 0.3982, Labels Score: 0.8900   Using time in epoch 184: 27.7081s
Epoch 185/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4521 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4080
Neighbors Score: 0.4007, Labels Score: 0.8912   Using time in epoch 185: 26.4259s
Epoch 186/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8390 - pr: 0.4520 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4080
Neighbors Score: 0.3971, Labels Score: 0.8904   Using time in epoch 186: 25.6792s
Epoch 187/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2857 - binary_accuracy: 0.8840 - auc: 0.8389 - pr: 0.4520 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4077
Neighbors Score: 0.3974, Labels Score: 0.8906   Using time in epoch 187: 26.5700s
Epoch 188/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8391 - pr: 0.4521 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8119 - val_pr: 0.4073
Neighbors Score: 0.4000, Labels Score: 0.8921   Using time in epoch 188: 26.5440s
Epoch 189/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8391 - pr: 0.4521 - val_loss: 0.3036 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4080
Neighbors Score: 0.4001, Labels Score: 0.8914   Using time in epoch 189: 26.4452s
Epoch 190/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8391 - pr: 0.4522 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4077
Neighbors Score: 0.3987, Labels Score: 0.8918   Using time in epoch 190: 26.6142s
Epoch 191/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8391 - pr: 0.4522 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4074
Neighbors Score: 0.3964, Labels Score: 0.8902   Using time in epoch 191: 26.7307s
Epoch 192/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4522 - val_loss: 0.3036 - val_binary_accuracy: 0.8796 - val_auc: 0.8122 - val_pr: 0.4082
Neighbors Score: 0.4003, Labels Score: 0.8924   Using time in epoch 192: 25.7273s
Epoch 193/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8391 - pr: 0.4522 - val_loss: 0.3045 - val_binary_accuracy: 0.8794 - val_auc: 0.8117 - val_pr: 0.4070
Neighbors Score: 0.4015, Labels Score: 0.8927   Using time in epoch 193: 26.5311s
Epoch 194/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4523 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8120 - val_pr: 0.4078
Neighbors Score: 0.3996, Labels Score: 0.8907   Using time in epoch 194: 26.4875s
Epoch 195/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4522 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4077
Neighbors Score: 0.4005, Labels Score: 0.8910   Using time in epoch 195: 25.6931s
Epoch 196/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4522 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4076
Neighbors Score: 0.3988, Labels Score: 0.8905   Using time in epoch 196: 26.3459s
Epoch 197/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4524 - val_loss: 0.3035 - val_binary_accuracy: 0.8796 - val_auc: 0.8121 - val_pr: 0.4083
Neighbors Score: 0.3973, Labels Score: 0.8904   Using time in epoch 197: 26.2142s
Epoch 198/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4525 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4078
Neighbors Score: 0.3971, Labels Score: 0.8899   Using time in epoch 198: 26.1011s
Epoch 199/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4522 - val_loss: 0.3038 - val_binary_accuracy: 0.8796 - val_auc: 0.8120 - val_pr: 0.4078
Neighbors Score: 0.4002, Labels Score: 0.8918   Using time in epoch 199: 26.5209s
Epoch 200/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4524 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4079
Neighbors Score: 0.4018, Labels Score: 0.8922   Using time in epoch 200: 29.9910s
Epoch 201/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2856 - binary_accuracy: 0.8840 - auc: 0.8392 - pr: 0.4522 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4078
Neighbors Score: 0.3989, Labels Score: 0.8910   Using time in epoch 201: 25.8258s
Epoch 202/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4524 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4076
Neighbors Score: 0.3988, Labels Score: 0.8906   Using time in epoch 202: 25.6193s
Epoch 203/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4525 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4073
Neighbors Score: 0.3973, Labels Score: 0.8912   Using time in epoch 203: 26.6250s
Epoch 204/1000
680/680 [==============================] - 160s 234ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4523 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4073
Neighbors Score: 0.3973, Labels Score: 0.8931   Using time in epoch 204: 26.9688s
Epoch 205/1000
680/680 [==============================] - 163s 233ms/step - loss: 0.2855 - binary_accuracy: 0.8841 - auc: 0.8393 - pr: 0.4526 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4075
Neighbors Score: 0.3961, Labels Score: 0.8920   Using time in epoch 205: 25.9903s
Epoch 206/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4525 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4080
Neighbors Score: 0.3976, Labels Score: 0.8918   Using time in epoch 206: 26.9363s
Epoch 207/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4526 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4074
Neighbors Score: 0.3973, Labels Score: 0.8916   Using time in epoch 207: 26.4102s
Epoch 208/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8393 - pr: 0.4525 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4080
Neighbors Score: 0.4004, Labels Score: 0.8919   Using time in epoch 208: 25.4325s
Epoch 209/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8394 - pr: 0.4527 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4077
Neighbors Score: 0.4005, Labels Score: 0.8923   Using time in epoch 209: 25.2572s
Epoch 210/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8394 - pr: 0.4527 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8119 - val_pr: 0.4074
Neighbors Score: 0.3990, Labels Score: 0.8914   Using time in epoch 210: 26.1295s
Epoch 211/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8394 - pr: 0.4527 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8121 - val_pr: 0.4082
Neighbors Score: 0.3986, Labels Score: 0.8921   Using time in epoch 211: 25.6146s
Epoch 212/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2855 - binary_accuracy: 0.8840 - auc: 0.8394 - pr: 0.4526 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4079
Neighbors Score: 0.3976, Labels Score: 0.8919   Using time in epoch 212: 25.5433s
Epoch 213/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4077
Neighbors Score: 0.3979, Labels Score: 0.8911   Using time in epoch 213: 25.3355s
Epoch 214/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4529 - val_loss: 0.3037 - val_binary_accuracy: 0.8795 - val_auc: 0.8121 - val_pr: 0.4080
Neighbors Score: 0.3990, Labels Score: 0.8919   Using time in epoch 214: 26.2748s
Epoch 215/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8120 - val_pr: 0.4079
Neighbors Score: 0.4002, Labels Score: 0.8924   Using time in epoch 215: 26.0523s
Epoch 216/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8120 - val_pr: 0.4081
Neighbors Score: 0.3976, Labels Score: 0.8921   Using time in epoch 216: 26.1962s
Epoch 217/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4529 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4080
Neighbors Score: 0.3989, Labels Score: 0.8924   Using time in epoch 217: 26.4010s
Epoch 218/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2854 - binary_accuracy: 0.8840 - auc: 0.8395 - pr: 0.4527 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4073
Neighbors Score: 0.3976, Labels Score: 0.8917   Using time in epoch 218: 25.5677s
Epoch 219/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4529 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4076
Neighbors Score: 0.3986, Labels Score: 0.8939   Using time in epoch 219: 25.4083s
Epoch 220/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2854 - binary_accuracy: 0.8840 - auc: 0.8396 - pr: 0.4528 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4076
Neighbors Score: 0.3987, Labels Score: 0.8926   Using time in epoch 220: 25.4305s
Epoch 221/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4081
Neighbors Score: 0.3987, Labels Score: 0.8926   Using time in epoch 221: 26.7052s
Epoch 222/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4076
Neighbors Score: 0.4011, Labels Score: 0.8924   Using time in epoch 222: 26.6325s
Epoch 223/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4529 - val_loss: 0.3044 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4070
Neighbors Score: 0.3976, Labels Score: 0.8913   Using time in epoch 223: 26.3406s
Epoch 224/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4531 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4075
Neighbors Score: 0.3981, Labels Score: 0.8918   Using time in epoch 224: 26.3440s
Epoch 225/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4530 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4070
Neighbors Score: 0.3978, Labels Score: 0.8922   Using time in epoch 225: 26.4339s
Epoch 226/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4530 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4078
Neighbors Score: 0.3973, Labels Score: 0.8908   Using time in epoch 226: 26.1894s
Epoch 227/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4530 - val_loss: 0.3036 - val_binary_accuracy: 0.8796 - val_auc: 0.8118 - val_pr: 0.4078
Neighbors Score: 0.3977, Labels Score: 0.8917   Using time in epoch 227: 26.6399s
Epoch 228/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4531 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4075
Neighbors Score: 0.3990, Labels Score: 0.8910   Using time in epoch 228: 25.9400s
Epoch 229/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4531 - val_loss: 0.3038 - val_binary_accuracy: 0.8796 - val_auc: 0.8118 - val_pr: 0.4081
Neighbors Score: 0.3998, Labels Score: 0.8921   Using time in epoch 229: 28.7426s
Epoch 230/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4531 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4073
Neighbors Score: 0.3998, Labels Score: 0.8934   Using time in epoch 230: 26.4627s
Epoch 231/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4531 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4073
Neighbors Score: 0.3980, Labels Score: 0.8922   Using time in epoch 231: 26.3153s
Epoch 232/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2854 - binary_accuracy: 0.8841 - auc: 0.8395 - pr: 0.4528 - val_loss: 0.3038 - val_binary_accuracy: 0.8796 - val_auc: 0.8118 - val_pr: 0.4080
Neighbors Score: 0.4004, Labels Score: 0.8920   Using time in epoch 232: 26.5829s
Epoch 233/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8396 - pr: 0.4529 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4080
Neighbors Score: 0.3989, Labels Score: 0.8921   Using time in epoch 233: 26.4672s
Epoch 234/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4532 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4072
Neighbors Score: 0.3972, Labels Score: 0.8917   Using time in epoch 234: 26.1049s
Epoch 235/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4531 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8118 - val_pr: 0.4076
Neighbors Score: 0.3969, Labels Score: 0.8906   Using time in epoch 235: 25.6987s
Epoch 236/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4531 - val_loss: 0.3037 - val_binary_accuracy: 0.8796 - val_auc: 0.8119 - val_pr: 0.4076
Neighbors Score: 0.3967, Labels Score: 0.8906   Using time in epoch 236: 26.8325s
Epoch 237/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4531 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4072
Neighbors Score: 0.3988, Labels Score: 0.8921   Using time in epoch 237: 28.6292s
Epoch 238/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4532 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8118 - val_pr: 0.4073
Neighbors Score: 0.3990, Labels Score: 0.8922   Using time in epoch 238: 25.3784s
Epoch 239/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4534 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8116 - val_pr: 0.4069
Neighbors Score: 0.3979, Labels Score: 0.8932   Using time in epoch 239: 26.0145s
Epoch 240/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4533 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4074
Neighbors Score: 0.4000, Labels Score: 0.8918   Using time in epoch 240: 26.2505s
Epoch 241/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2853 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4530 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4071
Neighbors Score: 0.3992, Labels Score: 0.8917   Using time in epoch 241: 26.4473s
Epoch 242/1000
680/680 [==============================] - 158s 231ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8397 - pr: 0.4532 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4068
Neighbors Score: 0.3971, Labels Score: 0.8922   Using time in epoch 242: 25.9373s
Epoch 243/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4533 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4074
Neighbors Score: 0.3977, Labels Score: 0.8933   Using time in epoch 243: 25.8746s
Epoch 244/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4533 - val_loss: 0.3038 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4074
Neighbors Score: 0.3990, Labels Score: 0.8923   Using time in epoch 244: 26.1865s
Epoch 245/1000
680/680 [==============================] - 164s 235ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4532 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8116 - val_pr: 0.4074
Neighbors Score: 0.3983, Labels Score: 0.8911   Using time in epoch 245: 26.0588s
Epoch 246/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4534 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4071
Neighbors Score: 0.3994, Labels Score: 0.8920   Using time in epoch 246: 28.1342s
Epoch 247/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4532 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4069
Neighbors Score: 0.4008, Labels Score: 0.8940   Using time in epoch 247: 25.9360s
Epoch 248/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8398 - pr: 0.4534 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8117 - val_pr: 0.4075
Neighbors Score: 0.3988, Labels Score: 0.8921   Using time in epoch 248: 27.6657s
Epoch 249/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4535 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4072
Neighbors Score: 0.3990, Labels Score: 0.8919   Using time in epoch 249: 26.1518s
Epoch 250/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4534 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8117 - val_pr: 0.4076
Neighbors Score: 0.3959, Labels Score: 0.8914   Using time in epoch 250: 26.6414s
Epoch 251/1000
680/680 [==============================] - 168s 242ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4535 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8116 - val_pr: 0.4075
Neighbors Score: 0.3995, Labels Score: 0.8922   Using time in epoch 251: 27.6650s
Epoch 252/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4534 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4073
Neighbors Score: 0.3986, Labels Score: 0.8920   Using time in epoch 252: 26.3316s
Epoch 253/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4534 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4073
Neighbors Score: 0.3983, Labels Score: 0.8923   Using time in epoch 253: 27.1345s
Epoch 254/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4535 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8117 - val_pr: 0.4072
Neighbors Score: 0.3994, Labels Score: 0.8924   Using time in epoch 254: 26.5604s
Epoch 255/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2852 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4534 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4069
Neighbors Score: 0.3988, Labels Score: 0.8926   Using time in epoch 255: 26.3406s
Epoch 256/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4536 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4067
Neighbors Score: 0.3983, Labels Score: 0.8926   Using time in epoch 256: 26.1567s
Epoch 257/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4535 - val_loss: 0.3043 - val_binary_accuracy: 0.8793 - val_auc: 0.8112 - val_pr: 0.4060
Neighbors Score: 0.3974, Labels Score: 0.8920   Using time in epoch 257: 25.5996s
Epoch 258/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4534 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4070
Neighbors Score: 0.3993, Labels Score: 0.8928   Using time in epoch 258: 26.1340s
Epoch 259/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8399 - pr: 0.4536 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4069
Neighbors Score: 0.3991, Labels Score: 0.8925   Using time in epoch 259: 27.6440s
Epoch 260/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4536 - val_loss: 0.3044 - val_binary_accuracy: 0.8794 - val_auc: 0.8112 - val_pr: 0.4066
Neighbors Score: 0.4005, Labels Score: 0.8932   Using time in epoch 260: 25.6918s
Epoch 261/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4538 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4069
Neighbors Score: 0.3993, Labels Score: 0.8923   Using time in epoch 261: 27.0893s
Epoch 262/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4536 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4069
Neighbors Score: 0.3993, Labels Score: 0.8931   Using time in epoch 262: 25.5836s
Epoch 263/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4538 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4069
Neighbors Score: 0.3992, Labels Score: 0.8923   Using time in epoch 263: 26.2886s
Epoch 264/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4536 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4070
Neighbors Score: 0.3998, Labels Score: 0.8932   Using time in epoch 264: 26.0599s
Epoch 265/1000
680/680 [==============================] - 155s 226ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4538 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4072
Neighbors Score: 0.3988, Labels Score: 0.8923   Using time in epoch 265: 25.6511s
Epoch 266/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4537 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4070
Neighbors Score: 0.3990, Labels Score: 0.8921   Using time in epoch 266: 26.0658s
Epoch 267/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2851 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4537 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4073
Neighbors Score: 0.4001, Labels Score: 0.8930   Using time in epoch 267: 26.0226s
Epoch 268/1000
680/680 [==============================] - 162s 232ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4068
Neighbors Score: 0.3993, Labels Score: 0.8930   Using time in epoch 268: 26.1294s
Epoch 269/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4537 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4071
Neighbors Score: 0.3993, Labels Score: 0.8928   Using time in epoch 269: 26.6127s
Epoch 270/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3042 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4067
Neighbors Score: 0.3984, Labels Score: 0.8923   Using time in epoch 270: 26.3897s
Epoch 271/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4538 - val_loss: 0.3041 - val_binary_accuracy: 0.8794 - val_auc: 0.8115 - val_pr: 0.4069
Neighbors Score: 0.3991, Labels Score: 0.8930   Using time in epoch 271: 26.6222s
Epoch 272/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4072
Neighbors Score: 0.3980, Labels Score: 0.8922   Using time in epoch 272: 26.4532s
Epoch 273/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4538 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4072
Neighbors Score: 0.3983, Labels Score: 0.8928   Using time in epoch 273: 26.1069s
Epoch 274/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4070
Neighbors Score: 0.3997, Labels Score: 0.8925   Using time in epoch 274: 26.1206s
Epoch 275/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4538 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8116 - val_pr: 0.4074
Neighbors Score: 0.3983, Labels Score: 0.8921   Using time in epoch 275: 26.1607s
Epoch 276/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8400 - pr: 0.4538 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4072
Neighbors Score: 0.3994, Labels Score: 0.8928   Using time in epoch 276: 28.0108s
Epoch 277/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3043 - val_binary_accuracy: 0.8794 - val_auc: 0.8112 - val_pr: 0.4065
Neighbors Score: 0.3991, Labels Score: 0.8931   Using time in epoch 277: 26.3624s
Epoch 278/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4540 - val_loss: 0.3039 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4070
Neighbors Score: 0.3996, Labels Score: 0.8933   Using time in epoch 278: 25.5283s
Epoch 279/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4539 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4072
Neighbors Score: 0.4002, Labels Score: 0.8925   Using time in epoch 279: 25.9752s
Epoch 280/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4539 - val_loss: 0.3040 - val_binary_accuracy: 0.8795 - val_auc: 0.8115 - val_pr: 0.4070
Neighbors Score: 0.3996, Labels Score: 0.8927   Using time in epoch 280: 26.3769s
Epoch 281/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4540 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4070
Neighbors Score: 0.3988, Labels Score: 0.8927   Using time in epoch 281: 25.2263s
Epoch 282/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4538 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4070
Neighbors Score: 0.4002, Labels Score: 0.8932   Using time in epoch 282: 26.1189s
Epoch 283/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4540 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4069
Neighbors Score: 0.3999, Labels Score: 0.8932   Using time in epoch 283: 25.4343s
Epoch 284/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4541 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4073
Neighbors Score: 0.3991, Labels Score: 0.8926   Using time in epoch 284: 28.1892s
Epoch 285/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4072
Neighbors Score: 0.3999, Labels Score: 0.8924   Using time in epoch 285: 26.2722s
Epoch 286/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4539 - val_loss: 0.3039 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4072
Neighbors Score: 0.3996, Labels Score: 0.8929   Using time in epoch 286: 25.7945s
Epoch 287/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4539 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8115 - val_pr: 0.4073
Neighbors Score: 0.3987, Labels Score: 0.8927   Using time in epoch 287: 26.3021s
Epoch 288/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4073
Neighbors Score: 0.3998, Labels Score: 0.8929   Using time in epoch 288: 26.1884s
Epoch 289/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4065
Neighbors Score: 0.3995, Labels Score: 0.8929   Using time in epoch 289: 26.9336s
Epoch 290/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2850 - binary_accuracy: 0.8841 - auc: 0.8401 - pr: 0.4540 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4069
Neighbors Score: 0.4007, Labels Score: 0.8932   Using time in epoch 290: 29.3165s
Epoch 291/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4072
Neighbors Score: 0.4005, Labels Score: 0.8928   Using time in epoch 291: 25.9669s
Epoch 292/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4069
Neighbors Score: 0.3998, Labels Score: 0.8933   Using time in epoch 292: 26.4676s
Epoch 293/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4542 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4071
Neighbors Score: 0.4011, Labels Score: 0.8939   Using time in epoch 293: 26.4253s
Epoch 294/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4070
Neighbors Score: 0.4002, Labels Score: 0.8930   Using time in epoch 294: 26.5586s
Epoch 295/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4540 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4063
Neighbors Score: 0.3992, Labels Score: 0.8935   Using time in epoch 295: 26.6753s
Epoch 296/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8402 - pr: 0.4541 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8115 - val_pr: 0.4075
Neighbors Score: 0.3999, Labels Score: 0.8929   Using time in epoch 296: 26.3977s
Epoch 297/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4541 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8114 - val_pr: 0.4070
Neighbors Score: 0.4002, Labels Score: 0.8933   Using time in epoch 297: 26.4423s
Epoch 298/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8112 - val_pr: 0.4068
Neighbors Score: 0.3997, Labels Score: 0.8934   Using time in epoch 298: 25.7832s
Epoch 299/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8112 - val_pr: 0.4066
Neighbors Score: 0.3993, Labels Score: 0.8926   Using time in epoch 299: 27.1060s
Epoch 300/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8402 - pr: 0.4541 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4068
Neighbors Score: 0.4013, Labels Score: 0.8936   Using time in epoch 300: 26.3033s
Epoch 301/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3040 - val_binary_accuracy: 0.8796 - val_auc: 0.8115 - val_pr: 0.4074
Neighbors Score: 0.4000, Labels Score: 0.8927   Using time in epoch 301: 25.9557s
Epoch 302/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4069
Neighbors Score: 0.3991, Labels Score: 0.8933   Using time in epoch 302: 25.8283s
Epoch 303/1000
680/680 [==============================] - 168s 243ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8113 - val_pr: 0.4069
Neighbors Score: 0.4007, Labels Score: 0.8933   Using time in epoch 303: 26.3401s
Epoch 304/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4544 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4071
Neighbors Score: 0.4008, Labels Score: 0.8940   Using time in epoch 304: 26.5406s
Epoch 305/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4066
Neighbors Score: 0.3998, Labels Score: 0.8936   Using time in epoch 305: 25.7941s
Epoch 306/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4541 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4067
Neighbors Score: 0.3999, Labels Score: 0.8937   Using time in epoch 306: 26.4846s
Epoch 307/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4016, Labels Score: 0.8936   Using time in epoch 307: 25.3711s
Epoch 308/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4072
Neighbors Score: 0.4008, Labels Score: 0.8932   Using time in epoch 308: 26.0078s
Epoch 309/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4067
Neighbors Score: 0.4002, Labels Score: 0.8932   Using time in epoch 309: 26.1601s
Epoch 310/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4068
Neighbors Score: 0.4016, Labels Score: 0.8940   Using time in epoch 310: 27.6337s
Epoch 311/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2849 - binary_accuracy: 0.8842 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4003, Labels Score: 0.8934   Using time in epoch 311: 26.9113s
Epoch 312/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4070
Neighbors Score: 0.4004, Labels Score: 0.8934   Using time in epoch 312: 26.5262s
Epoch 313/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2848 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4543 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4007, Labels Score: 0.8936   Using time in epoch 313: 26.4944s
Epoch 314/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4066
Neighbors Score: 0.4011, Labels Score: 0.8941   Using time in epoch 314: 26.9519s
Epoch 315/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8114 - val_pr: 0.4074
Neighbors Score: 0.4012, Labels Score: 0.8938   Using time in epoch 315: 25.7663s
Epoch 316/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2849 - binary_accuracy: 0.8841 - auc: 0.8403 - pr: 0.4542 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4066
Neighbors Score: 0.4002, Labels Score: 0.8940   Using time in epoch 316: 26.0887s
Epoch 317/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4543 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4070
Neighbors Score: 0.4014, Labels Score: 0.8939   Using time in epoch 317: 25.6482s
Epoch 318/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4071
Neighbors Score: 0.4011, Labels Score: 0.8935   Using time in epoch 318: 25.9984s
Epoch 319/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4016, Labels Score: 0.8940   Using time in epoch 319: 26.7171s
Epoch 320/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4543 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4072
Neighbors Score: 0.4018, Labels Score: 0.8937   Using time in epoch 320: 26.9295s
Epoch 321/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4071
Neighbors Score: 0.4016, Labels Score: 0.8938   Using time in epoch 321: 26.8719s
Epoch 322/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4543 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4073
Neighbors Score: 0.4011, Labels Score: 0.8940   Using time in epoch 322: 26.1811s
Epoch 323/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4069
Neighbors Score: 0.4007, Labels Score: 0.8936   Using time in epoch 323: 26.2263s
Epoch 324/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4071
Neighbors Score: 0.4014, Labels Score: 0.8942   Using time in epoch 324: 26.6262s
Epoch 325/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3041 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4067
Neighbors Score: 0.4004, Labels Score: 0.8937   Using time in epoch 325: 26.1858s
Epoch 326/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4544 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8113 - val_pr: 0.4072
Neighbors Score: 0.4010, Labels Score: 0.8936   Using time in epoch 326: 26.3029s
Epoch 327/1000
680/680 [==============================] - 156s 227ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4002, Labels Score: 0.8939   Using time in epoch 327: 25.8112s
Epoch 328/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4545 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8112 - val_pr: 0.4067
Neighbors Score: 0.4016, Labels Score: 0.8943   Using time in epoch 328: 26.0231s
Epoch 329/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4544 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4008, Labels Score: 0.8931   Using time in epoch 329: 26.0475s
Epoch 330/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4004, Labels Score: 0.8937   Using time in epoch 330: 26.8060s
Epoch 331/1000
680/680 [==============================] - 155s 226ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3041 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4015, Labels Score: 0.8941   Using time in epoch 331: 26.3166s
Epoch 332/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4545 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4070
Neighbors Score: 0.4011, Labels Score: 0.8938   Using time in epoch 332: 26.0371s
Epoch 333/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4024, Labels Score: 0.8944   Using time in epoch 333: 26.4487s
Epoch 334/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4545 - val_loss: 0.3042 - val_binary_accuracy: 0.8795 - val_auc: 0.8112 - val_pr: 0.4067
Neighbors Score: 0.4014, Labels Score: 0.8942   Using time in epoch 334: 26.4609s
Epoch 335/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8404 - pr: 0.4545 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4018, Labels Score: 0.8938   Using time in epoch 335: 26.3117s
Epoch 336/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4545 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4015, Labels Score: 0.8938   Using time in epoch 336: 27.1727s
Epoch 337/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4022, Labels Score: 0.8945   Using time in epoch 337: 25.8320s
Epoch 338/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4069
Neighbors Score: 0.4023, Labels Score: 0.8940   Using time in epoch 338: 26.9206s
Epoch 339/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4071
Neighbors Score: 0.4013, Labels Score: 0.8942   Using time in epoch 339: 25.7523s
Epoch 340/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4065
Neighbors Score: 0.4025, Labels Score: 0.8942   Using time in epoch 340: 27.0810s
Epoch 341/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4023, Labels Score: 0.8944   Using time in epoch 341: 26.3963s
Epoch 342/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4547 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4070
Neighbors Score: 0.4018, Labels Score: 0.8940   Using time in epoch 342: 28.3228s
Epoch 343/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4013, Labels Score: 0.8938   Using time in epoch 343: 26.7720s
Epoch 344/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4067
Neighbors Score: 0.4019, Labels Score: 0.8949   Using time in epoch 344: 25.6290s
Epoch 345/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4018, Labels Score: 0.8948   Using time in epoch 345: 26.0054s
Epoch 346/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4025, Labels Score: 0.8943   Using time in epoch 346: 26.1565s
Epoch 347/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4071
Neighbors Score: 0.4021, Labels Score: 0.8943   Using time in epoch 347: 26.2583s
Epoch 348/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4022, Labels Score: 0.8941   Using time in epoch 348: 26.4781s
Epoch 349/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4067
Neighbors Score: 0.4025, Labels Score: 0.8942   Using time in epoch 349: 26.2991s
Epoch 350/1000
680/680 [==============================] - 166s 243ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4006, Labels Score: 0.8939   Using time in epoch 350: 27.7703s
Epoch 351/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4070
Neighbors Score: 0.4031, Labels Score: 0.8945   Using time in epoch 351: 27.1451s
Epoch 352/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4072
Neighbors Score: 0.4019, Labels Score: 0.8935   Using time in epoch 352: 26.1835s
Epoch 353/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2848 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4015, Labels Score: 0.8941   Using time in epoch 353: 27.9595s
Epoch 354/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4546 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4021, Labels Score: 0.8937   Using time in epoch 354: 26.3600s
Epoch 355/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4066
Neighbors Score: 0.4026, Labels Score: 0.8943   Using time in epoch 355: 28.3205s
Epoch 356/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4018, Labels Score: 0.8947   Using time in epoch 356: 27.9057s
Epoch 357/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4065
Neighbors Score: 0.4014, Labels Score: 0.8942   Using time in epoch 357: 25.4334s
Epoch 358/1000
680/680 [==============================] - 161s 230ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4024, Labels Score: 0.8944   Using time in epoch 358: 26.4876s
Epoch 359/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4015, Labels Score: 0.8941   Using time in epoch 359: 26.2537s
Epoch 360/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4547 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4014, Labels Score: 0.8935   Using time in epoch 360: 26.2018s
Epoch 361/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8405 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4070
Neighbors Score: 0.4028, Labels Score: 0.8940   Using time in epoch 361: 25.7822s
Epoch 362/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4072
Neighbors Score: 0.4016, Labels Score: 0.8932   Using time in epoch 362: 26.3426s
Epoch 363/1000
680/680 [==============================] - 157s 227ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4022, Labels Score: 0.8939   Using time in epoch 363: 26.7600s
Epoch 364/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4546 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4071
Neighbors Score: 0.4022, Labels Score: 0.8937   Using time in epoch 364: 27.3886s
Epoch 365/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8112 - val_pr: 0.4070
Neighbors Score: 0.4026, Labels Score: 0.8947   Using time in epoch 365: 27.2448s
Epoch 366/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4070
Neighbors Score: 0.4021, Labels Score: 0.8939   Using time in epoch 366: 25.7467s
Epoch 367/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4069
Neighbors Score: 0.4021, Labels Score: 0.8939   Using time in epoch 367: 26.5232s
Epoch 368/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4023, Labels Score: 0.8945   Using time in epoch 368: 27.1910s
Epoch 369/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4071
Neighbors Score: 0.4021, Labels Score: 0.8942   Using time in epoch 369: 26.6351s
Epoch 370/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4024, Labels Score: 0.8946   Using time in epoch 370: 26.6780s
Epoch 371/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4070
Neighbors Score: 0.4020, Labels Score: 0.8947   Using time in epoch 371: 25.9955s
Epoch 372/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4070
Neighbors Score: 0.4025, Labels Score: 0.8939   Using time in epoch 372: 26.1710s
Epoch 373/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4066
Neighbors Score: 0.4022, Labels Score: 0.8938   Using time in epoch 373: 29.0019s
Epoch 374/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4027, Labels Score: 0.8945   Using time in epoch 374: 27.1538s
Epoch 375/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4024, Labels Score: 0.8940   Using time in epoch 375: 26.1450s
Epoch 376/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4549 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4031, Labels Score: 0.8950   Using time in epoch 376: 26.3168s
Epoch 377/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4549 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4020, Labels Score: 0.8938   Using time in epoch 377: 26.3400s
Epoch 378/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4024, Labels Score: 0.8941   Using time in epoch 378: 26.7839s
Epoch 379/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4026, Labels Score: 0.8940   Using time in epoch 379: 26.3153s
Epoch 380/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4071
Neighbors Score: 0.4025, Labels Score: 0.8939   Using time in epoch 380: 26.6066s
Epoch 381/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4028, Labels Score: 0.8941   Using time in epoch 381: 25.8157s
Epoch 382/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4547 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4070
Neighbors Score: 0.4031, Labels Score: 0.8940   Using time in epoch 382: 26.0942s
Epoch 383/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4030, Labels Score: 0.8949   Using time in epoch 383: 26.2433s
Epoch 384/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4032, Labels Score: 0.8944   Using time in epoch 384: 25.9181s
Epoch 385/1000
680/680 [==============================] - 156s 227ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4028, Labels Score: 0.8944   Using time in epoch 385: 25.7665s
Epoch 386/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2847 - binary_accuracy: 0.8842 - auc: 0.8406 - pr: 0.4548 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4024, Labels Score: 0.8944   Using time in epoch 386: 25.6672s
Epoch 387/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4064
Neighbors Score: 0.4031, Labels Score: 0.8943   Using time in epoch 387: 25.5049s
Epoch 388/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4026, Labels Score: 0.8948   Using time in epoch 388: 26.2275s
Epoch 389/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8111 - val_pr: 0.4070
Neighbors Score: 0.4020, Labels Score: 0.8943   Using time in epoch 389: 25.5347s
Epoch 390/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3042 - val_binary_accuracy: 0.8796 - val_auc: 0.8111 - val_pr: 0.4070
Neighbors Score: 0.4027, Labels Score: 0.8940   Using time in epoch 390: 26.1125s
Epoch 391/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4027, Labels Score: 0.8941   Using time in epoch 391: 25.7795s
Epoch 392/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4031, Labels Score: 0.8944   Using time in epoch 392: 26.2190s
Epoch 393/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4028, Labels Score: 0.8938   Using time in epoch 393: 28.3245s
Epoch 394/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4027, Labels Score: 0.8938   Using time in epoch 394: 25.5769s
Epoch 395/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8947   Using time in epoch 395: 26.6785s
Epoch 396/1000
680/680 [==============================] - 167s 242ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4548 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4029, Labels Score: 0.8944   Using time in epoch 396: 27.0949s
Epoch 397/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4030, Labels Score: 0.8941   Using time in epoch 397: 26.8967s
Epoch 398/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 398: 26.3756s
Epoch 399/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4032, Labels Score: 0.8939   Using time in epoch 399: 26.2394s
Epoch 400/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4064
Neighbors Score: 0.4031, Labels Score: 0.8943   Using time in epoch 400: 27.3135s
Epoch 401/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4029, Labels Score: 0.8940   Using time in epoch 401: 26.6033s
Epoch 402/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4030, Labels Score: 0.8944   Using time in epoch 402: 27.2872s
Epoch 403/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4030, Labels Score: 0.8941   Using time in epoch 403: 26.3789s
Epoch 404/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4021, Labels Score: 0.8938   Using time in epoch 404: 26.7400s
Epoch 405/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4026, Labels Score: 0.8940   Using time in epoch 405: 26.5276s
Epoch 406/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4032, Labels Score: 0.8940   Using time in epoch 406: 25.2860s
Epoch 407/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4032, Labels Score: 0.8941   Using time in epoch 407: 26.0997s
Epoch 408/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4026, Labels Score: 0.8939   Using time in epoch 408: 26.5976s
Epoch 409/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4024, Labels Score: 0.8939   Using time in epoch 409: 25.6186s
Epoch 410/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4067
Neighbors Score: 0.4026, Labels Score: 0.8939   Using time in epoch 410: 25.7084s
Epoch 411/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4028, Labels Score: 0.8943   Using time in epoch 411: 26.1009s
Epoch 412/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4026, Labels Score: 0.8943   Using time in epoch 412: 26.2242s
Epoch 413/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4030, Labels Score: 0.8945   Using time in epoch 413: 25.2165s
Epoch 414/1000
680/680 [==============================] - 167s 242ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4029, Labels Score: 0.8940   Using time in epoch 414: 26.7376s
Epoch 415/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4032, Labels Score: 0.8941   Using time in epoch 415: 26.7829s
Epoch 416/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4068
Neighbors Score: 0.4037, Labels Score: 0.8944   Using time in epoch 416: 26.6685s
Epoch 417/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4039, Labels Score: 0.8945   Using time in epoch 417: 25.8558s
Epoch 418/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4028, Labels Score: 0.8942   Using time in epoch 418: 28.0287s
Epoch 419/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4063
Neighbors Score: 0.4025, Labels Score: 0.8942   Using time in epoch 419: 26.6578s
Epoch 420/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8407 - pr: 0.4549 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4029, Labels Score: 0.8941   Using time in epoch 420: 26.3780s
Epoch 421/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4033, Labels Score: 0.8941   Using time in epoch 421: 26.4655s
Epoch 422/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4027, Labels Score: 0.8940   Using time in epoch 422: 25.4604s
Epoch 423/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4030, Labels Score: 0.8938   Using time in epoch 423: 26.2722s
Epoch 424/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4550 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 424: 26.5808s
Epoch 425/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4027, Labels Score: 0.8942   Using time in epoch 425: 25.7038s
Epoch 426/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4030, Labels Score: 0.8939   Using time in epoch 426: 26.5646s
Epoch 427/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4033, Labels Score: 0.8939   Using time in epoch 427: 26.5342s
Epoch 428/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8110 - val_pr: 0.4071
Neighbors Score: 0.4032, Labels Score: 0.8942   Using time in epoch 428: 26.1330s
Epoch 429/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4026, Labels Score: 0.8939   Using time in epoch 429: 26.4052s
Epoch 430/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4034, Labels Score: 0.8941   Using time in epoch 430: 26.6625s
Epoch 431/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4027, Labels Score: 0.8945   Using time in epoch 431: 26.6522s
Epoch 432/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8945   Using time in epoch 432: 26.4615s
Epoch 433/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 433: 28.1209s
Epoch 434/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4029, Labels Score: 0.8939   Using time in epoch 434: 26.4649s
Epoch 435/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4033, Labels Score: 0.8941   Using time in epoch 435: 25.4627s
Epoch 436/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8110 - val_pr: 0.4069
Neighbors Score: 0.4032, Labels Score: 0.8941   Using time in epoch 436: 28.0365s
Epoch 437/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4028, Labels Score: 0.8938   Using time in epoch 437: 26.1593s
Epoch 438/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3043 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4030, Labels Score: 0.8942   Using time in epoch 438: 27.8824s
Epoch 439/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4030, Labels Score: 0.8943   Using time in epoch 439: 26.5968s
Epoch 440/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 440: 25.7309s
Epoch 441/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4038, Labels Score: 0.8939   Using time in epoch 441: 26.8016s
Epoch 442/1000
680/680 [==============================] - 169s 244ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 442: 26.9079s
Epoch 443/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4031, Labels Score: 0.8943   Using time in epoch 443: 27.2990s
Epoch 444/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4033, Labels Score: 0.8945   Using time in epoch 444: 29.7383s
Epoch 445/1000
680/680 [==============================] - 168s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4028, Labels Score: 0.8940   Using time in epoch 445: 28.7030s
Epoch 446/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 446: 25.9940s
Epoch 447/1000
680/680 [==============================] - 171s 247ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4034, Labels Score: 0.8948   Using time in epoch 447: 27.4216s
Epoch 448/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4032, Labels Score: 0.8944   Using time in epoch 448: 27.2266s
Epoch 449/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4034, Labels Score: 0.8938   Using time in epoch 449: 27.6862s
Epoch 450/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4028, Labels Score: 0.8940   Using time in epoch 450: 27.3277s
Epoch 451/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2846 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4551 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4030, Labels Score: 0.8943   Using time in epoch 451: 27.2799s
Epoch 452/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8945   Using time in epoch 452: 26.2154s
Epoch 453/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4029, Labels Score: 0.8942   Using time in epoch 453: 26.0842s
Epoch 454/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4069
Neighbors Score: 0.4032, Labels Score: 0.8942   Using time in epoch 454: 26.1970s
Epoch 455/1000
680/680 [==============================] - 167s 244ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4031, Labels Score: 0.8941   Using time in epoch 455: 27.4023s
Epoch 456/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 456: 26.6443s
Epoch 457/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4034, Labels Score: 0.8944   Using time in epoch 457: 28.9587s
Epoch 458/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4034, Labels Score: 0.8943   Using time in epoch 458: 26.2281s
Epoch 459/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 459: 26.6087s
Epoch 460/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 460: 26.9272s
Epoch 461/1000
680/680 [==============================] - 168s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 461: 26.6022s
Epoch 462/1000
680/680 [==============================] - 169s 245ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4063
Neighbors Score: 0.4034, Labels Score: 0.8943   Using time in epoch 462: 28.2549s
Epoch 463/1000
680/680 [==============================] - 156s 227ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4035, Labels Score: 0.8944   Using time in epoch 463: 25.9796s
Epoch 464/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3043 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4030, Labels Score: 0.8942   Using time in epoch 464: 28.5159s
Epoch 465/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4033, Labels Score: 0.8943   Using time in epoch 465: 26.7988s
Epoch 466/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8945   Using time in epoch 466: 25.9974s
Epoch 467/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8408 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4032, Labels Score: 0.8942   Using time in epoch 467: 25.6901s
Epoch 468/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4028, Labels Score: 0.8946   Using time in epoch 468: 26.1917s
Epoch 469/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8946   Using time in epoch 469: 26.3190s
Epoch 470/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4064
Neighbors Score: 0.4031, Labels Score: 0.8941   Using time in epoch 470: 26.0626s
Epoch 471/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4028, Labels Score: 0.8943   Using time in epoch 471: 26.7134s
Epoch 472/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4027, Labels Score: 0.8941   Using time in epoch 472: 27.3463s
Epoch 473/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4029, Labels Score: 0.8940   Using time in epoch 473: 26.0008s
Epoch 474/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4031, Labels Score: 0.8943   Using time in epoch 474: 27.5634s
Epoch 475/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4068
Neighbors Score: 0.4032, Labels Score: 0.8940   Using time in epoch 475: 26.1508s
Epoch 476/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 476: 26.5051s
Epoch 477/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8942   Using time in epoch 477: 26.1069s
Epoch 478/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4035, Labels Score: 0.8943   Using time in epoch 478: 25.8547s
Epoch 479/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4030, Labels Score: 0.8944   Using time in epoch 479: 28.2326s
Epoch 480/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4033, Labels Score: 0.8941   Using time in epoch 480: 26.3475s
Epoch 481/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4033, Labels Score: 0.8944   Using time in epoch 481: 25.5991s
Epoch 482/1000
680/680 [==============================] - 160s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4068
Neighbors Score: 0.4033, Labels Score: 0.8945   Using time in epoch 482: 28.9547s
Epoch 483/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4034, Labels Score: 0.8943   Using time in epoch 483: 26.4688s
Epoch 484/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4031, Labels Score: 0.8941   Using time in epoch 484: 26.1514s
Epoch 485/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4030, Labels Score: 0.8944   Using time in epoch 485: 26.2000s
Epoch 486/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4033, Labels Score: 0.8945   Using time in epoch 486: 27.2865s
Epoch 487/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4034, Labels Score: 0.8946   Using time in epoch 487: 26.6579s
Epoch 488/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4034, Labels Score: 0.8944   Using time in epoch 488: 26.2124s
Epoch 489/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3046 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4037, Labels Score: 0.8945   Using time in epoch 489: 26.3402s
Epoch 490/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4032, Labels Score: 0.8944   Using time in epoch 490: 26.2997s
Epoch 491/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4033, Labels Score: 0.8944   Using time in epoch 491: 27.1043s
Epoch 492/1000
680/680 [==============================] - 167s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3044 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4035, Labels Score: 0.8945   Using time in epoch 492: 26.5355s
Epoch 493/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4033, Labels Score: 0.8945   Using time in epoch 493: 27.0946s
Epoch 494/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4032, Labels Score: 0.8944   Using time in epoch 494: 26.1262s
Epoch 495/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4068
Neighbors Score: 0.4035, Labels Score: 0.8942   Using time in epoch 495: 25.7980s
Epoch 496/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8109 - val_pr: 0.4067
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 496: 26.6710s
Epoch 497/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 497: 25.9491s
Epoch 498/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8944   Using time in epoch 498: 26.5785s
Epoch 499/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4037, Labels Score: 0.8944   Using time in epoch 499: 28.3711s
Epoch 500/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4037, Labels Score: 0.8947   Using time in epoch 500: 27.2558s
Epoch 501/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8945   Using time in epoch 501: 27.5375s
Epoch 502/1000
680/680 [==============================] - 170s 245ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 502: 26.8621s
Epoch 503/1000
680/680 [==============================] - 168s 244ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 503: 26.7400s
Epoch 504/1000
680/680 [==============================] - 169s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8946   Using time in epoch 504: 26.9084s
Epoch 505/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4037, Labels Score: 0.8942   Using time in epoch 505: 27.5773s
Epoch 506/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8945   Using time in epoch 506: 26.4318s
Epoch 507/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4033, Labels Score: 0.8943   Using time in epoch 507: 27.3273s
Epoch 508/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4041, Labels Score: 0.8942   Using time in epoch 508: 26.8104s
Epoch 509/1000
680/680 [==============================] - 169s 244ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4034, Labels Score: 0.8945   Using time in epoch 509: 26.7727s
Epoch 510/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8944   Using time in epoch 510: 27.3177s
Epoch 511/1000
680/680 [==============================] - 164s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4035, Labels Score: 0.8945   Using time in epoch 511: 26.7822s
Epoch 512/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4038, Labels Score: 0.8945   Using time in epoch 512: 27.7790s
Epoch 513/1000
680/680 [==============================] - 168s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 513: 26.0559s
Epoch 514/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 514: 25.8331s
Epoch 515/1000
680/680 [==============================] - 167s 240ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4038, Labels Score: 0.8945   Using time in epoch 515: 26.9898s
Epoch 516/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4039, Labels Score: 0.8945   Using time in epoch 516: 26.2207s
Epoch 517/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8946   Using time in epoch 517: 25.6909s
Epoch 518/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4031, Labels Score: 0.8943   Using time in epoch 518: 26.6467s
Epoch 519/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3048 - val_binary_accuracy: 0.8796 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4035, Labels Score: 0.8943   Using time in epoch 519: 27.1685s
Epoch 520/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8945   Using time in epoch 520: 25.8468s
Epoch 521/1000
680/680 [==============================] - 157s 228ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4038, Labels Score: 0.8947   Using time in epoch 521: 26.4076s
Epoch 522/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4552 - val_loss: 0.3044 - val_binary_accuracy: 0.8795 - val_auc: 0.8109 - val_pr: 0.4068
Neighbors Score: 0.4032, Labels Score: 0.8943   Using time in epoch 522: 26.0874s
Epoch 523/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4038, Labels Score: 0.8944   Using time in epoch 523: 28.9510s
Epoch 524/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 524: 28.0659s
Epoch 525/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8942   Using time in epoch 525: 26.3612s
Epoch 526/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4035, Labels Score: 0.8942   Using time in epoch 526: 26.6961s
Epoch 527/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4034, Labels Score: 0.8944   Using time in epoch 527: 26.3650s
Epoch 528/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4038, Labels Score: 0.8944   Using time in epoch 528: 25.2531s
Epoch 529/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8944   Using time in epoch 529: 27.0097s
Epoch 530/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4035, Labels Score: 0.8943   Using time in epoch 530: 26.0932s
Epoch 531/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4033, Labels Score: 0.8943   Using time in epoch 531: 26.2342s
Epoch 532/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4031, Labels Score: 0.8942   Using time in epoch 532: 26.2764s
Epoch 533/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 533: 26.4139s
Epoch 534/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 534: 27.9451s
Epoch 535/1000
680/680 [==============================] - 168s 242ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4038, Labels Score: 0.8943   Using time in epoch 535: 26.4775s
Epoch 536/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4039, Labels Score: 0.8946   Using time in epoch 536: 27.0117s
Epoch 537/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4035, Labels Score: 0.8942   Using time in epoch 537: 26.5226s
Epoch 538/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4036, Labels Score: 0.8941   Using time in epoch 538: 26.7800s
Epoch 539/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8945   Using time in epoch 539: 25.6775s
Epoch 540/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4036, Labels Score: 0.8946   Using time in epoch 540: 26.4259s
Epoch 541/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8943   Using time in epoch 541: 26.9488s
Epoch 542/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 542: 26.6148s
Epoch 543/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4038, Labels Score: 0.8942   Using time in epoch 543: 26.5515s
Epoch 544/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4039, Labels Score: 0.8945   Using time in epoch 544: 25.8333s
Epoch 545/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4037, Labels Score: 0.8944   Using time in epoch 545: 25.9740s
Epoch 546/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4037, Labels Score: 0.8941   Using time in epoch 546: 26.8651s
Epoch 547/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4037, Labels Score: 0.8945   Using time in epoch 547: 26.3738s
Epoch 548/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 548: 26.1662s
Epoch 549/1000
680/680 [==============================] - 168s 245ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4034, Labels Score: 0.8942   Using time in epoch 549: 26.7643s
Epoch 550/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 550: 26.1975s
Epoch 551/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4034, Labels Score: 0.8945   Using time in epoch 551: 26.2603s
Epoch 552/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4035, Labels Score: 0.8942   Using time in epoch 552: 26.4170s
Epoch 553/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4033, Labels Score: 0.8943   Using time in epoch 553: 26.0806s
Epoch 554/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 554: 26.9141s
Epoch 555/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4036, Labels Score: 0.8942   Using time in epoch 555: 25.7895s
Epoch 556/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4034, Labels Score: 0.8943   Using time in epoch 556: 26.8671s
Epoch 557/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4039, Labels Score: 0.8942   Using time in epoch 557: 27.4356s
Epoch 558/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8796 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4039, Labels Score: 0.8940   Using time in epoch 558: 26.8245s
Epoch 559/1000
680/680 [==============================] - 158s 228ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8943   Using time in epoch 559: 25.8415s
Epoch 560/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4045, Labels Score: 0.8943   Using time in epoch 560: 26.3968s
Epoch 561/1000
680/680 [==============================] - 157s 227ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4043, Labels Score: 0.8941   Using time in epoch 561: 25.8946s
Epoch 562/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4066
Neighbors Score: 0.4046, Labels Score: 0.8943   Using time in epoch 562: 25.8206s
Epoch 563/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8941   Using time in epoch 563: 25.9643s
Epoch 564/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8796 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4045, Labels Score: 0.8940   Using time in epoch 564: 27.2743s
Epoch 565/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8941   Using time in epoch 565: 25.2865s
Epoch 566/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4047, Labels Score: 0.8944   Using time in epoch 566: 25.6251s
Epoch 567/1000
680/680 [==============================] - 169s 243ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4045, Labels Score: 0.8941   Using time in epoch 567: 26.1671s
Epoch 568/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4047, Labels Score: 0.8943   Using time in epoch 568: 26.5614s
Epoch 569/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4066
Neighbors Score: 0.4044, Labels Score: 0.8942   Using time in epoch 569: 26.9641s
Epoch 570/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4046, Labels Score: 0.8941   Using time in epoch 570: 26.0525s
Epoch 571/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4047, Labels Score: 0.8942   Using time in epoch 571: 26.4535s
Epoch 572/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4047, Labels Score: 0.8942   Using time in epoch 572: 26.9593s
Epoch 573/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4048, Labels Score: 0.8943   Using time in epoch 573: 26.4717s
Epoch 574/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8943   Using time in epoch 574: 25.7396s
Epoch 575/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4050, Labels Score: 0.8944   Using time in epoch 575: 27.2546s
Epoch 576/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4045, Labels Score: 0.8943   Using time in epoch 576: 25.4038s
Epoch 577/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4049, Labels Score: 0.8941   Using time in epoch 577: 26.6842s
Epoch 578/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8409 - pr: 0.4553 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4045, Labels Score: 0.8942   Using time in epoch 578: 25.6121s
Epoch 579/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2845 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4047, Labels Score: 0.8941   Using time in epoch 579: 26.8963s
Epoch 580/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4047, Labels Score: 0.8943   Using time in epoch 580: 26.4413s
Epoch 581/1000
680/680 [==============================] - 169s 244ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4047, Labels Score: 0.8943   Using time in epoch 581: 27.6905s
Epoch 582/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4047, Labels Score: 0.8942   Using time in epoch 582: 26.7142s
Epoch 583/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8944   Using time in epoch 583: 26.4858s
Epoch 584/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8942   Using time in epoch 584: 26.9917s
Epoch 585/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4046, Labels Score: 0.8941   Using time in epoch 585: 26.3702s
Epoch 586/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4043, Labels Score: 0.8941   Using time in epoch 586: 25.6340s
Epoch 587/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4046, Labels Score: 0.8942   Using time in epoch 587: 26.0560s
Epoch 588/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4048, Labels Score: 0.8942   Using time in epoch 588: 25.9205s
Epoch 589/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4045, Labels Score: 0.8942   Using time in epoch 589: 26.0714s
Epoch 590/1000
680/680 [==============================] - 159s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4045, Labels Score: 0.8944   Using time in epoch 590: 27.0912s
Epoch 591/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4048, Labels Score: 0.8944   Using time in epoch 591: 25.6912s
Epoch 592/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8944   Using time in epoch 592: 25.7180s
Epoch 593/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8945   Using time in epoch 593: 26.4358s
Epoch 594/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4049, Labels Score: 0.8943   Using time in epoch 594: 28.5816s
Epoch 595/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8943   Using time in epoch 595: 26.9840s
Epoch 596/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4047, Labels Score: 0.8943   Using time in epoch 596: 26.2111s
Epoch 597/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4046, Labels Score: 0.8942   Using time in epoch 597: 26.4327s
Epoch 598/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4046, Labels Score: 0.8941   Using time in epoch 598: 26.6405s
Epoch 599/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8941   Using time in epoch 599: 25.8165s
Epoch 600/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4044, Labels Score: 0.8943   Using time in epoch 600: 26.9153s
Epoch 601/1000
680/680 [==============================] - 164s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4048, Labels Score: 0.8943   Using time in epoch 601: 26.8945s
Epoch 602/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4048, Labels Score: 0.8945   Using time in epoch 602: 26.0138s
Epoch 603/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4048, Labels Score: 0.8945   Using time in epoch 603: 25.7147s
Epoch 604/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 604: 27.1178s
Epoch 605/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 605: 27.4167s
Epoch 606/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4046, Labels Score: 0.8945   Using time in epoch 606: 26.7280s
Epoch 607/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8943   Using time in epoch 607: 26.7105s
Epoch 608/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8943   Using time in epoch 608: 27.0266s
Epoch 609/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4047, Labels Score: 0.8943   Using time in epoch 609: 25.7279s
Epoch 610/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8943   Using time in epoch 610: 26.2634s
Epoch 611/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8942   Using time in epoch 611: 26.7480s
Epoch 612/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4045, Labels Score: 0.8944   Using time in epoch 612: 25.5611s
Epoch 613/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 613: 26.5327s
Epoch 614/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4044, Labels Score: 0.8943   Using time in epoch 614: 26.8506s
Epoch 615/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4044, Labels Score: 0.8946   Using time in epoch 615: 26.0953s
Epoch 616/1000
680/680 [==============================] - 167s 242ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4046, Labels Score: 0.8944   Using time in epoch 616: 27.9056s
Epoch 617/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8794 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4046, Labels Score: 0.8943   Using time in epoch 617: 26.4294s
Epoch 618/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 618: 26.3818s
Epoch 619/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 619: 26.4011s
Epoch 620/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4061
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 620: 26.5704s
Epoch 621/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8943   Using time in epoch 621: 25.6792s
Epoch 622/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 622: 25.2321s
Epoch 623/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 623: 26.6760s
Epoch 624/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2845 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4048, Labels Score: 0.8945   Using time in epoch 624: 25.3311s
Epoch 625/1000
680/680 [==============================] - 157s 226ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8943   Using time in epoch 625: 26.5838s
Epoch 626/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 626: 27.1080s
Epoch 627/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 627: 26.2460s
Epoch 628/1000
680/680 [==============================] - 162s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4067
Neighbors Score: 0.4039, Labels Score: 0.8942   Using time in epoch 628: 26.0676s
Epoch 629/1000
680/680 [==============================] - 160s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 629: 26.1244s
Epoch 630/1000
680/680 [==============================] - 164s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 630: 27.1519s
Epoch 631/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 631: 27.3224s
Epoch 632/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 632: 26.3197s
Epoch 633/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 633: 26.6563s
Epoch 634/1000
680/680 [==============================] - 156s 227ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 634: 26.6180s
Epoch 635/1000
680/680 [==============================] - 155s 223ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 635: 26.5962s
Epoch 636/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 636: 25.8121s
Epoch 637/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 637: 26.3353s
Epoch 638/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 638: 26.1734s
Epoch 639/1000
680/680 [==============================] - 165s 241ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 639: 26.1706s
Epoch 640/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8943   Using time in epoch 640: 27.2800s
Epoch 641/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4046, Labels Score: 0.8946   Using time in epoch 641: 26.0623s
Epoch 642/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8943   Using time in epoch 642: 26.2574s
Epoch 643/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 643: 25.8883s
Epoch 644/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 644: 26.3368s
Epoch 645/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 645: 26.4456s
Epoch 646/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8943   Using time in epoch 646: 27.3798s
Epoch 647/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4046, Labels Score: 0.8944   Using time in epoch 647: 26.2791s
Epoch 648/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8108 - val_pr: 0.4065
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 648: 30.7334s
Epoch 649/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 649: 25.5560s
Epoch 650/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 650: 26.6001s
Epoch 651/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 651: 26.2162s
Epoch 652/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4044, Labels Score: 0.8944   Using time in epoch 652: 26.2840s
Epoch 653/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 653: 26.5172s
Epoch 654/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 654: 25.9808s
Epoch 655/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 655: 25.8025s
Epoch 656/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 656: 26.7239s
Epoch 657/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 657: 25.4024s
Epoch 658/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 658: 25.9539s
Epoch 659/1000
680/680 [==============================] - 157s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 659: 25.9262s
Epoch 660/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8794 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 660: 26.5214s
Epoch 661/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8946   Using time in epoch 661: 26.2990s
Epoch 662/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 662: 27.1350s
Epoch 663/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8943   Using time in epoch 663: 25.8870s
Epoch 664/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8104 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 664: 26.4353s
Epoch 665/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4045, Labels Score: 0.8944   Using time in epoch 665: 26.7292s
Epoch 666/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 666: 26.6350s
Epoch 667/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 667: 26.3662s
Epoch 668/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4045, Labels Score: 0.8946   Using time in epoch 668: 26.7622s
Epoch 669/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 669: 26.1632s
Epoch 670/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 670: 26.6049s
Epoch 671/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 671: 25.8494s
Epoch 672/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 672: 26.3856s
Epoch 673/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 673: 26.2552s
Epoch 674/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 674: 26.4420s
Epoch 675/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 675: 25.3186s
Epoch 676/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 676: 25.8004s
Epoch 677/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 677: 26.4425s
Epoch 678/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 678: 28.9157s
Epoch 679/1000
680/680 [==============================] - 158s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 679: 27.4351s
Epoch 680/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8794 - val_auc: 0.8107 - val_pr: 0.4067
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 680: 26.6241s
Epoch 681/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8943   Using time in epoch 681: 28.7903s
Epoch 682/1000
680/680 [==============================] - 172s 251ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 682: 28.1748s
Epoch 683/1000
680/680 [==============================] - 169s 246ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 683: 27.8467s
Epoch 684/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8943   Using time in epoch 684: 26.1840s
Epoch 685/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 685: 25.9770s
Epoch 686/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 686: 27.1455s
Epoch 687/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 687: 25.3691s
Epoch 688/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4039, Labels Score: 0.8945   Using time in epoch 688: 26.6876s
Epoch 689/1000
680/680 [==============================] - 158s 227ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 689: 29.3897s
Epoch 690/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 690: 25.7582s
Epoch 691/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 691: 26.9017s
Epoch 692/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 692: 25.3755s
Epoch 693/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 693: 26.5362s
Epoch 694/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 694: 26.3595s
Epoch 695/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 695: 25.6506s
Epoch 696/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4555 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 696: 25.9611s
Epoch 697/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4064
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 697: 26.6862s
Epoch 698/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 698: 26.7241s
Epoch 699/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 699: 25.5120s
Epoch 700/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 700: 26.4685s
Epoch 701/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 701: 26.4609s
Epoch 702/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 702: 26.3969s
Epoch 703/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4061
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 703: 24.9918s
Epoch 704/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 704: 25.9144s
Epoch 705/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8410 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8943   Using time in epoch 705: 25.2874s
Epoch 706/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8946   Using time in epoch 706: 25.9577s
Epoch 707/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 707: 27.7957s
Epoch 708/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 708: 26.0305s
Epoch 709/1000
680/680 [==============================] - 163s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 709: 25.8008s
Epoch 710/1000
680/680 [==============================] - 161s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 710: 26.5283s
Epoch 711/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4061
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 711: 26.2247s
Epoch 712/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 712: 26.2635s
Epoch 713/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 713: 25.6986s
Epoch 714/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 714: 25.5556s
Epoch 715/1000
680/680 [==============================] - 165s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 715: 29.3275s
Epoch 716/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 716: 26.4826s
Epoch 717/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 717: 26.0123s
Epoch 718/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 718: 26.0632s
Epoch 719/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 719: 25.9942s
Epoch 720/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 720: 27.7034s
Epoch 721/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 721: 26.4635s
Epoch 722/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 722: 25.7165s
Epoch 723/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 723: 25.6817s
Epoch 724/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8946   Using time in epoch 724: 26.6409s
Epoch 725/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 725: 26.3338s
Epoch 726/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4063
Neighbors Score: 0.4044, Labels Score: 0.8945   Using time in epoch 726: 26.6551s
Epoch 727/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 727: 26.7102s
Epoch 728/1000
680/680 [==============================] - 160s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 728: 26.5161s
Epoch 729/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 729: 26.4245s
Epoch 730/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 730: 25.9027s
Epoch 731/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 731: 26.6797s
Epoch 732/1000
680/680 [==============================] - 166s 242ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 732: 26.7222s
Epoch 733/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 733: 25.7440s
Epoch 734/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 734: 27.1168s
Epoch 735/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 735: 26.3092s
Epoch 736/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 736: 25.9396s
Epoch 737/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3045 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4066
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 737: 25.4787s
Epoch 738/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 738: 25.9447s
Epoch 739/1000
680/680 [==============================] - 165s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 739: 25.9817s
Epoch 740/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 740: 28.3003s
Epoch 741/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 741: 26.8035s
Epoch 742/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 742: 26.0236s
Epoch 743/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 743: 27.0472s
Epoch 744/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 744: 26.0117s
Epoch 745/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8410 - pr: 0.4554 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 745: 25.8830s
Epoch 746/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 746: 26.5531s
Epoch 747/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 747: 25.8887s
Epoch 748/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 748: 26.5491s
Epoch 749/1000
680/680 [==============================] - 163s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 749: 26.7386s
Epoch 750/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 750: 25.9141s
Epoch 751/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 751: 25.8881s
Epoch 752/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 752: 26.6084s
Epoch 753/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 753: 26.3025s
Epoch 754/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 754: 25.9009s
Epoch 755/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 755: 26.0222s
Epoch 756/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 756: 25.6020s
Epoch 757/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 757: 25.3653s
Epoch 758/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 758: 28.1364s
Epoch 759/1000
680/680 [==============================] - 160s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 759: 25.9294s
Epoch 760/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 760: 26.2088s
Epoch 761/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3050 - val_binary_accuracy: 0.8794 - val_auc: 0.8105 - val_pr: 0.4061
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 761: 26.3555s
Epoch 762/1000
680/680 [==============================] - 159s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3046 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4039, Labels Score: 0.8944   Using time in epoch 762: 26.6099s
Epoch 763/1000
680/680 [==============================] - 159s 230ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 763: 26.1762s
Epoch 764/1000
680/680 [==============================] - 155s 226ms/step - loss: 0.2843 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 764: 27.5179s
Epoch 765/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 765: 26.6615s
Epoch 766/1000
680/680 [==============================] - 162s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4065
Neighbors Score: 0.4040, Labels Score: 0.8943   Using time in epoch 766: 25.6849s
Epoch 767/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 767: 25.7013s
Epoch 768/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 768: 25.3271s
Epoch 769/1000
680/680 [==============================] - 161s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 769: 25.1153s
Epoch 770/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4065
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 770: 27.8052s
Epoch 771/1000
680/680 [==============================] - 167s 243ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 771: 25.6624s
Epoch 772/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 772: 26.7946s
Epoch 773/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 773: 26.8704s
Epoch 774/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 774: 26.6447s
Epoch 775/1000
680/680 [==============================] - 164s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8945   Using time in epoch 775: 25.6960s
Epoch 776/1000
680/680 [==============================] - 166s 241ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 776: 30.0840s
Epoch 777/1000
680/680 [==============================] - 168s 245ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 777: 26.1256s
Epoch 778/1000
680/680 [==============================] - 172s 249ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 778: 27.7628s
Epoch 779/1000
680/680 [==============================] - 162s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 779: 25.6946s
Epoch 780/1000
680/680 [==============================] - 165s 238ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 780: 25.6997s
Epoch 781/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 781: 26.9482s
Epoch 782/1000
680/680 [==============================] - 164s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 782: 28.1996s
Epoch 783/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 783: 25.8336s
Epoch 784/1000
680/680 [==============================] - 158s 229ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 784: 26.3321s
Epoch 785/1000
680/680 [==============================] - 159s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 785: 25.5135s
Epoch 786/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 786: 26.8543s
Epoch 787/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 787: 25.6389s
Epoch 788/1000
680/680 [==============================] - 164s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 788: 26.5119s
Epoch 789/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8944   Using time in epoch 789: 26.2064s
Epoch 790/1000
680/680 [==============================] - 161s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 790: 27.2500s
Epoch 791/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 791: 25.6078s
Epoch 792/1000
680/680 [==============================] - 163s 234ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 792: 26.1731s
Epoch 793/1000
680/680 [==============================] - 159s 228ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 793: 27.9380s
Epoch 794/1000
680/680 [==============================] - 163s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4040, Labels Score: 0.8945   Using time in epoch 794: 26.0274s
Epoch 795/1000
680/680 [==============================] - 170s 247ms/step - loss: 0.2844 - binary_accuracy: 0.8842 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 795: 27.5840s
Epoch 796/1000
680/680 [==============================] - 160s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 796: 25.9114s
Epoch 797/1000
680/680 [==============================] - 166s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4040, Labels Score: 0.8944   Using time in epoch 797: 25.3906s
Epoch 798/1000
680/680 [==============================] - 167s 241ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 798: 26.0545s
Epoch 799/1000
680/680 [==============================] - 167s 242ms/step - loss: 0.2843 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8944   Using time in epoch 799: 25.6660s
Epoch 800/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 800: 27.6218s
Epoch 801/1000
680/680 [==============================] - 162s 233ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8946   Using time in epoch 801: 25.8527s
Epoch 802/1000
680/680 [==============================] - 162s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8946   Using time in epoch 802: 26.1854s
Epoch 803/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4041, Labels Score: 0.8946   Using time in epoch 803: 26.3495s
Epoch 804/1000
680/680 [==============================] - 160s 231ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4062
Neighbors Score: 0.4043, Labels Score: 0.8946   Using time in epoch 804: 26.0265s
Epoch 805/1000
680/680 [==============================] - 161s 232ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4062
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 805: 26.7937s
Epoch 806/1000
680/680 [==============================] - 169s 245ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4556 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 806: 26.5007s
Epoch 807/1000
680/680 [==============================] - 166s 240ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 807: 27.1087s
Epoch 808/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 808: 28.5146s
Epoch 809/1000
680/680 [==============================] - 163s 236ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3048 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 809: 27.9205s
Epoch 810/1000
680/680 [==============================] - 170s 245ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3049 - val_binary_accuracy: 0.8795 - val_auc: 0.8105 - val_pr: 0.4063
Neighbors Score: 0.4042, Labels Score: 0.8944   Using time in epoch 810: 27.6159s
Epoch 811/1000
680/680 [==============================] - 161s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4041, Labels Score: 0.8945   Using time in epoch 811: 27.0448s
Epoch 812/1000
680/680 [==============================] - 165s 237ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4558 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8107 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8945   Using time in epoch 812: 27.9927s
Epoch 813/1000
680/680 [==============================] - 164s 239ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8795 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4043, Labels Score: 0.8946   Using time in epoch 813: 29.4603s
Epoch 814/1000
680/680 [==============================] - 162s 235ms/step - loss: 0.2844 - binary_accuracy: 0.8843 - auc: 0.8411 - pr: 0.4557 - val_loss: 0.3047 - val_binary_accuracy: 0.8794 - val_auc: 0.8106 - val_pr: 0.4064
Neighbors Score: 0.4042, Labels Score: 0.8946   Using time in epoch 814: 26.4777s
Epoch 00814: early stopping
8. Save training results...
=== Training completed! ===
Best model: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/train_out/E1000best_model.h5
Training history: /picb/bigdata/project/miaoyuanyuan/train/XChrom_test/XChrom/source/Tutorials/data/3_cross_species/train_out/history.pickle

Plotting training metrics to monitor overfitting and evaluate the final model performance. Ideally, after a certain number of epochs, the validation curves plateau (i.e., remain stable).

The metrics computed during training are saved in ./data/3_cross_species/train_out/history.pickle. Load them with:

import pickle
with open('./data/3_cross_species/train_out/history.pickle', 'rb') as f:
    history = pickle.load(f)

You can then use this history object to plot training/validation metrics (e.g., loss, auROC/auPRC, NS/LS) over epochs.

The function plot_train_history() will automatically detect whether NS and LS values have been computed during training. If these metrics are available in the history data, they will be automatically included in the training metric plots along with other evaluation metrics such as loss, auROC, and auPRC.

[8]:

xc.pl.plot_train_history(
    history = history['history'],
    savefig = True,
    out_file = './data/3_cross_species/train_out/train_history_plot.pdf'
    )

../_images/Tutorials_3_Cross-species_calc_ISM_16_0.png

5. Evaluate model performance in cross-species scenario

The following metrics will be evaluated on the human(m1d1) test set data:

Binary classification metrics:
- (overall, per cell, per peak) auROC
- (overall, per cell, per peak) auPRC
Cell state fidelity:
- Neighbor Score (NS) (k=10, 50, 100)
- Label Score (LS) (k=10, 50, 100)

This combination of binary classification metrics and cell state fidelity provides a comprehensive evaluation of the model’s predictive performance on data from different species.

[9]:

#### 1- calculate cross-species auROC & auPRC
metrics1 = xc.tl.crosssamples_aucprc(
    cell_embedding_ad='./data/3_cross_species/m1d1_rna_harmony.h5ad',
    input_folder='./data/3_cross_species/test_data',
    model_path='./data/3_cross_species/train_out/E1000best_model.h5',
    output_path='./data/3_cross_species/eval_out',
    cellembed_raw='X_pca_harmony',
    save_pred=True,
    scatter_plot=True
    )

2025-08-20 14:08:32.946716: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-08-20 14:08:34.542231: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 19982 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:31:00.0, compute capability: 8.6
2025-08-20 14:08:34.542839: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 21971 MB memory:  -> device: 1, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:4b:00.0, compute capability: 8.6
2025-08-20 14:08:34.543350: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:2 with 21971 MB memory:  -> device: 2, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:98:00.0, compute capability: 8.6
2025-08-20 14:08:34.543748: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:3 with 572 MB memory:  -> device: 3, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:b1:00.0, compute capability: 8.6
2025-08-20 14:08:35.615747: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
2025-08-20 14:08:37.202628: I tensorflow/stream_executor/cuda/cuda_dnn.cc:369] Loaded cuDNN version 8800
2025-08-20 14:08:38.020093: I tensorflow/stream_executor/cuda/cuda_blas.cc:1760] TensorFloat-32 will be used for the matrix multiplication. This will only be logged once.

Predict done! prediction shape is: (37363, 4489)
Overall auROC: 0.7519, auPRC: 0.3469
Per-cell auROC: 0.6918, auPRC: 0.2696
Valid cells: 4489
Per-peak auROC: 0.6965, auPRC: 0.2516
Valid peaks: 37363

../_images/Tutorials_3_Cross-species_calc_ISM_19_2.png

../_images/Tutorials_3_Cross-species_calc_ISM_19_3.png

[10]:

#### 2- calculate cross-species ns & ls
metrics2 = xc.tl.crosssamples_nsls(
    cell_embedding_ad='./data/3_cross_species/m1d1_rna_harmony.h5ad',
    input_folder='./data/3_cross_species/test_data',
    model_path='./data/3_cross_species/train_out/E1000best_model.h5',
    output_path='./data/3_cross_species/eval_out',
    cellembed_raw='X_pca_harmony',
    celltype = 'cell_type',
    save_pred=True,
    plot_umap=True
    )

Predict done! prediction shape is: (37363, 4489)

/home/miaoyuanyuan/miniconda3/envs/py3.8_tf2.6.0/lib/python3.8/site-packages/scanpy/preprocessing/_simple.py:842: UserWarning: Received a view of an AnnData. Making a copy.
  view_to_actual(adata)

neighbor score(100)=0.2347,label score(100)=0.8496
neighbor score(50)=0.1708,label score(50)=0.8776
neighbor score(10)=0.0772,label score(10)=0.9098

../_images/Tutorials_3_Cross-species_calc_ISM_20_3.png

6. Calculate ISM

We computed ISM on a human ATAC-seq peak. The corresponding BED file is provided in our Zenodo repository (DOI: 10.5281/zenodo.16959682) under 3_cross_species/m1d1_peaks.bed (chr14 73168099 73168956).

[11]:

m1d1_rna = sc.read_h5ad('./data/3_cross_species/m1d1_rna_harmony.h5ad')
model = xc.tr.XChrom_model(n_cells=m1d1_rna.shape[0],show_summary=False)
model.load_weights('./data/3_cross_species/train_out/E1000best_model.h5')

ism_results = xc.tl.calc_ism_from_bed(
    cell_embedding_ad = m1d1_rna,
    cellembed_raw = 'X_pca_harmony',
    peak_bed='./data/3_cross_species/m1d1_peaks.bed',
    fasta_file='/picb/bigdata/project/miaoyuanyuan/hg38.fa',
    XChrom_model = model,
    output_path='./data/3_cross_species/ISM_results/'
)
print(f"ISM matrix shape: {ism_results[0].shape}")

Extracting sequences from BED file...
Converting to one-hot encoding...
Calculating ISM for 1 peaks...
Processing peak 1/1
All ISM matrices shape (n_peaks, n_cells, seq_len, 4): (1, 4489, 1344, 4)
ISM calculation completed. Results saved to ./data/3_cross_species/ISM_results/
ISM matrix shape: (4489, 1344, 4)

We normalized the ISM scores for the four nucleotides at each position such that they summed to zero. We then took the normalized ISM score at the reference nucleotide as the importance score for that position to plot.

[12]:

peak0_ism = np.load('./data/3_cross_species/ISM_results/peak0_ism.npy')
tmp,seqs_coords = xc.tl.ism_norm(
    peak_ism = peak0_ism,
    peak_bed = './data/3_cross_species/m1d1_peaks.bed',
    fasta_file='/picb/bigdata/project/miaoyuanyuan/hg38.fa',
    seq_len=1344)

[13]:

ad = sc.read_h5ad('./data/3_cross_species/m1d1_atac.h5ad')
cts = ['L2/3 IT','LAMP5','MGC']
f, axs = plt.subplots(nrows=3, figsize=(10, 6))
a = 510
b = 610
for i in range(3):
    # aggregate cells
    cells = np.where((ad.obs['cell_type']==cts[i]))[0]
    # normalize
    toplot = pd.DataFrame(tmp[cells,:].mean(axis=0), columns = ['A', 'C', 'G', 'T'])
    toplot = toplot.iloc[a:b,:]
    toplot.index = np.arange(toplot.shape[0])
    xc.pl.plot_logo(toplot, -0.3,0.35, axs[i], '%s:%d-%d (%s)'%(seqs_coords[0][0],seqs_coords[0][1]+a, seqs_coords[0][1]+b, cts[i]))
f.tight_layout()
# f.savefig('./ism_peak0_100bp_celltype3.pdf', bbox_inches='tight', dpi=300,format="pdf")

../_images/Tutorials_3_Cross-species_calc_ISM_25_0.png

7. Calculate PWM-ISM dot product

After obtaining the base-level importance scores for each input sequence, we sought to determine whether specific motifs play key roles in model training and prediction for particular cell types. We scanned these sequences (using the FIMO tool) to identify candidate motifs and then calculated whether the PWM scores of these candidate motifs correlated with the ISM values computed for the region. A correlation value was obtained for each cell, and the final result was derived by averaging these values across cells of the same cell type. The specific analysis code can be found via https://github.com/Miaoyuanyuan777/XChrom_analysis.

Here, we only show correlation values between the PWM score and the ISM values computed for the candidate MEF2C region (chr14:73168422-73168436) identified at a human sequence (chr14:73168099-73168956) (in m1d1_peaks.bed) for three cell types: ‘L2/3 IT’, ‘LAMP5’, and ‘MGC’.

[14]:

ism = np.load('./data/3_cross_species/ISM_results/peak0_ism.npy')
ism_norm = ism - np.repeat(ism.mean(axis=2)[:,:,np.newaxis],4,axis=2)
motif = 'MEF2C'
pwm = pd.read_csv(f'./data/3_cross_species/{motif}.csv',index_col = 0)
start_site = 566
ism_matrix = ism_norm[:,start_site:(start_site+pwm.shape[1]),:]
m1d1_rna.obs[motif] = [np.dot(pwm.transpose().values.flatten(),i.flatten()) for i in ism_matrix]

[15]:

cts = ['L2/3 IT','LAMP5','MGC']
f, axs = plt.subplots(ncols=1, figsize=(4,3))
sns.violinplot(x='cell_type', y = motif, data=m1d1_rna.obs, order=cts)
sns.stripplot(x='cell_type', y=motif, data=m1d1_rna.obs, order=cts, alpha=0.6, color='0.3', size=2)
axs.set_ylim(-1,2.5)
axs.axhline(y=0, linestyle='dashed', color='0.3')
# f.savefig(f'./corr_{motif}.pdf', bbox_inches='tight', dpi=300)

[15]:

<matplotlib.lines.Line2D at 0x7fb74a977d90>

../_images/Tutorials_3_Cross-species_calc_ISM_29_1.png

The vertical axis represents the computed MEF2C PWM-ISM correlation (dot product) described above. A higher correlation suggests MEF2C binding motif has stronger predictive importance for chromatin accessibility in that specific cell type.

The results indicate that MEF2C binding sites has the strongest regulatory importance in LAMP5 (inhibitory neurons), a weaker regulatory importance in L2/3 IT (excitatory neurons), and the weakest regulatory importance in MGC (non-neuronal).