Adaptive parameterized ReLU——Dynamic ReLU activation function proposed by Harbin Institute of Technology

Posted May 25, 202067 min read

Adaptive parameterized ReLU is a dynamic ReLU(Dynamic ReLU), submitted to IEEE Transactions on Industrial Electronics on May 3, 2019, accepted on January 24, 2020, February 13, 2020 Announced on IEEE's official website.

In this paper, based on Adjustment Record 16 , two residual modules are added to continue to test its effect on the Cifar10 dataset.

The basic principle of the adaptive parameterized ReLU activation function is as follows:
aprelu.png

Keras program:

#!/usr/bin/env python3
#-*-coding:utf-8-*-
"" "
Created on Tue Apr 14 04:17:45 2020
Implemented using TensorFlow 1.0.1 and Keras 2.2.1

Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht,
Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis,
IEEE Transactions on Industrial Electronics, 2020, DOI:10.1109/TIE.2020.2972458
Date of Publication:13 February 2020

@author:Minghang Zhao
"" "

from __future__ import print_function
import keras
import numpy as np
from keras.datasets import cifar10
from keras.layers import Dense, Conv2D, BatchNormalization, Activation, Minimum
from keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D, Concatenate, Reshape
from keras.regularizers import l2
from keras import backend as K
from keras.models import Model
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import LearningRateScheduler
K.set_learning_phase(1)

# The data, split between train and test sets

(x_train, y_train),(x_test, y_test) = cifar10.load_data()
x_train = x_train.astype('float32')/255.
x_test = x_test.astype('float32')/255.
x_test = x_test-np.mean(x_train)
x_train = x_train-np.mean(x_train)
print('x_train shape:', x_train.shape)
print(x_train.shape [0], 'train samples')
print(x_test.shape [0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)

# Schedule the learning rate, multiply 0.1 every 1500 epoches
def scheduler(epoch):
    if epoch%1500 == 0 and epoch! = 0:
        lr = K.get_value(model.optimizer.lr)
        K.set_value(model.optimizer.lr, lr * 0.1)
        print("lr changed to {}". format(lr * 0.1))
    return K.get_value(model.optimizer.lr)

# An adaptively parametric rectifier linear unit(APReLU)
def aprelu(inputs):
    # get the number of channels
    channels = inputs.get_shape(). as_list() [-1]
    # get a zero feature map
    zeros_input = keras.layers.subtract([inputs, inputs])
    # get a feature map with only positive features
    pos_input = Activation('relu')(inputs)
    # get a feature map with only negative features
    neg_input = Minimum()([inputs, zeros_input])
    # define a network to obtain the scaling coefficients
    scales_p = GlobalAveragePooling2D()(pos_input)
    scales_n = GlobalAveragePooling2D()(neg_input)
    scales = Concatenate()([scales_n, scales_p])
    scales = Dense(channels //16, activation = 'linear', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(scales)
    scales = BatchNormalization(momentum = 0.9, gamma_regularizer = l2(1e-4))(scales)
    scales = Activation('relu')(scales)
    scales = Dense(channels, activation = 'linear', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(scales)
    scales = BatchNormalization(momentum = 0.9, gamma_regularizer = l2(1e-4))(scales)
    scales = Activation('sigmoid')(scales)
    scales = Reshape((1,1, channels))(scales)
    # apply a paramtetric relu
    neg_part = keras.layers.multiply([scales, neg_input])
    return keras.layers.add([pos_input, neg_part])

# Residual Block
def residual_block(incoming, nb_blocks, out_channels, downsample = False,
                   downsample_strides = 2):

    residual = incoming
    in_channels = incoming.get_shape(). as_list() [-1]

    for i in range(nb_blocks):

        identity = residual

        if not downsample:
            downsample_strides = 1

        residual = BatchNormalization(momentum = 0.9, gamma_regularizer = l2(1e-4))(residual)
        residual = aprelu(residual)
        residual = Conv2D(out_channels, 3, strides =(downsample_strides, downsample_strides),
                          padding = 'same', kernel_initializer = 'he_normal',
                          kernel_regularizer = l2(1e-4))(residual)

        residual = BatchNormalization(momentum = 0.9, gamma_regularizer = l2(1e-4))(residual)
        residual = aprelu(residual)
        residual = Conv2D(out_channels, 3, padding = 'same', kernel_initializer = 'he_normal',
                          kernel_regularizer = l2(1e-4))(residual)

        # Downsampling
        if downsample_strides> 1:
            identity = AveragePooling2D(pool_size =(1,1), strides =(2,2))(identity)

        # Zero_padding to match channels
        if in_channels! = out_channels:
            zeros_identity = keras.layers.subtract([identity, identity])
            identity = keras.layers.concatenate([identity, zeros_identity])
            in_channels = out_channels

        residual = keras.layers.add([residual, identity])

    return residual


# define and train a model
inputs = Input(shape =(32, 32, 3))
net = Conv2D(16, 3, padding = 'same', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(inputs)
net = residual_block(net, 1, 32, downsample = False)
net = residual_block(net, 1, 32, downsample = True)
net = residual_block(net, 1, 32, downsample = False)
net = residual_block(net, 1, 64, downsample = True)
net = residual_block(net, 1, 64, downsample = False)
net = BatchNormalization(momentum = 0.9, gamma_regularizer = l2(1e-4))(net)
net = aprelu(net)
net = GlobalAveragePooling2D()(net)
outputs = Dense(10, activation = 'softmax', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(net)
model = Model(inputs = inputs, outputs = outputs)
sgd = optimizers.SGD(lr = 0.1, decay = 0., momentum = 0.9, nesterov = True)
model.compile(loss = 'categorical_crossentropy', optimizer = sgd, metrics = ['accuracy'])

# data augmentation
datagen = ImageDataGenerator(
    # randomly rotate images in the range(deg 0 to 180)
    rotation_range = 30,
    # Range for random zoom
    zoom_range = 0.2,
    # shear angle in counter-clockwise direction in degrees
    shear_range = 30,
    # randomly flip images
    horizontal_flip = True,
    # randomly shift images horizontally
    width_shift_range = 0.125,
    # randomly shift images vertically
    height_shift_range = 0.125)

reduce_lr = LearningRateScheduler(scheduler)
# fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(x_train, y_train, batch_size = 100),
                    validation_data =(x_test, y_test), epochs = 5000,
                    verbose = 1, callbacks = [reduce_lr], workers = 4)

# get results
K.set_learning_phase(0)
DRSN_train_score = model.evaluate(x_train, y_train, batch_size = 100, verbose = 0)
print('Train loss:', DRSN_train_score [0])
print('Train accuracy:', DRSN_train_score [1])
DRSN_test_score = model.evaluate(x_test, y_test, batch_size = 100, verbose = 0)
print('Test loss:', DRSN_test_score [0])
print('Test accuracy:', DRSN_test_score [1])

The experimental results are as follows(for convenience of viewing, some equal signs have been deleted):

Using TensorFlow backend.
x_train shape:(50000, 32, 32, 3)
50000 train samples
10000 test samples
Epoch 1/5000
20s 41ms/step-loss:1.9490-acc:0.3869-val_loss:1.6784-val_acc:0.4900
Epoch 2/5000
14s 29ms/step-loss:1.6703-acc:0.4833-val_loss:1.4725-val_acc:0.5484
Epoch 3/5000
14s 29ms/step-loss:1.5095-acc:0.5392-val_loss:1.3049-val_acc:0.6056
Epoch 4/5000
14s 29ms/step-loss:1.3979-acc:0.5784-val_loss:1.2282-val_acc:0.6386
Epoch 5/5000
14s 29ms/step-loss:1.3169-acc:0.6028-val_loss:1.1671-val_acc:0.6576
Epoch 6/5000
14s 29ms/step-loss:1.2644-acc:0.6202-val_loss:1.1295-val_acc:0.6625
Epoch 7/5000
14s 29ms/step-loss:1.2118-acc:0.6399-val_loss:1.0974-val_acc:0.6794
Epoch 8/5000
14s 29ms/step-loss:1.1754-acc:0.6510-val_loss:1.0352-val_acc:0.7042
Epoch 9/5000
14s 29ms/step-loss:1.1392-acc:0.6640-val_loss:1.0079-val_acc:0.7117
Epoch 10/5000
14s 29ms/step-loss:1.1119-acc:0.6746-val_loss:0.9513-val_acc:0.7395
Epoch 11/5000
14s 29ms/step-loss:1.0894-acc:0.6835-val_loss:0.9600-val_acc:0.7335
Epoch 12/5000
14s 29ms/step-loss:1.0705-acc:0.6928-val_loss:0.9051-val_acc:0.7574
Epoch 13/5000
14s 29ms/step-loss:1.0536-acc:0.6997-val_loss:0.9088-val_acc:0.7560
Epoch 14/5000
14s 29ms/step-loss:1.0392-acc:0.7067-val_loss:0.8895-val_acc:0.7610
Epoch 15/5000
14s 29ms/step-loss:1.0240-acc:0.7122-val_loss:0.9020-val_acc:0.7570
Epoch 16/5000
14s 29ms/step-loss:1.0169-acc:0.7169-val_loss:0.9082-val_acc:0.7576
Epoch 17/5000
14s 29ms/step-loss:1.0000-acc:0.7205-val_loss:0.8647-val_acc:0.7762
Epoch 18/5000
14s 29ms/step-loss:0.9946-acc:0.7258-val_loss:0.8520-val_acc:0.7816
Epoch 19/5000
14s 29ms/step-loss:0.9874-acc:0.7300-val_loss:0.8447-val_acc:0.7781
Epoch 20/5000
14s 29ms/step-loss:0.9796-acc:0.7331-val_loss:0.8503-val_acc:0.7834
Epoch 21/5000
14s 29ms/step-loss:0.9739-acc:0.7345-val_loss:0.8347-val_acc:0.7905
Epoch 22/5000
14s 29ms/step-loss:0.9654-acc:0.7408-val_loss:0.8485-val_acc:0.7847
Epoch 23/5000
14s 29ms/step-loss:0.9562-acc:0.7437-val_loss:0.8187-val_acc:0.8000
Epoch 24/5000
14s 29ms/step-loss:0.9529-acc:0.7453-val_loss:0.8432-val_acc:0.7849
Epoch 25/5000
14s 29ms/step-loss:0.9468-acc:0.7479-val_loss:0.8176-val_acc:0.7991
Epoch 26/5000
14s 29ms/step-loss:0.9374-acc:0.7529-val_loss:0.8107-val_acc:0.8008
Epoch 27/5000
14s 29ms/step-loss:0.9401-acc:0.7521-val_loss:0.8046-val_acc:0.8056
Epoch 28/5000
14s 29ms/step-loss:0.9357-acc:0.7532-val_loss:0.7972-val_acc:0.8110
Epoch 29/5000
14s 29ms/step-loss:0.9268-acc:0.7579-val_loss:0.8300-val_acc:0.7964
Epoch 30/5000
14s 29ms/step-loss:0.9260-acc:0.7603-val_loss:0.8116-val_acc:0.7988
Epoch 31/5000
14s 29ms/step-loss:0.9204-acc:0.7607-val_loss:0.7832-val_acc:0.8146
Epoch 32/5000
14s 29ms/step-loss:0.9200-acc:0.7617-val_loss:0.7900-val_acc:0.8138
Epoch 33/5000
14s 29ms/step-loss:0.9179-acc:0.7647-val_loss:0.8021-val_acc:0.8061
Epoch 34/5000
14s 28ms/step-loss:0.9111-acc:0.7656-val_loss:0.8005-val_acc:0.8052
Epoch 35/5000
14s 29ms/step-loss:0.9107-acc:0.7671-val_loss:0.7924-val_acc:0.8160
Epoch 36/5000
14s 29ms/step-loss:0.9084-acc:0.7690-val_loss:0.7984-val_acc:0.8104
Epoch 37/5000
14s 29ms/step-loss:0.9018-acc:0.7695-val_loss:0.8222-val_acc:0.8028
Epoch 38/5000
14s 29ms/step-loss:0.9068-acc:0.7711-val_loss:0.7934-val_acc:0.8156
Epoch 39/5000
14s 29ms/step-loss:0.8978-acc:0.7737-val_loss:0.7866-val_acc:0.8163
Epoch 40/5000
14s 29ms/step-loss:0.9013-acc:0.7723-val_loss:0.8102-val_acc:0.8108
Epoch 41/5000
14s 29ms/step-loss:0.8921-acc:0.7756-val_loss:0.7937-val_acc:0.8163
Epoch 42/5000
14s 29ms/step-loss:0.8922-acc:0.7764-val_loss:0.7852-val_acc:0.8196
Epoch 43/5000
14s 29ms/step-loss:0.8946-acc:0.7751-val_loss:0.8259-val_acc:0.8046
Epoch 44/5000
14s 29ms/step-loss:0.8908-acc:0.7771-val_loss:0.7840-val_acc:0.8193
Epoch 45/5000
14s 29ms/step-loss:0.8865-acc:0.7795-val_loss:0.8009-val_acc:0.8101
Epoch 46/5000
14s 29ms/step-loss:0.8877-acc:0.7812-val_loss:0.7900-val_acc:0.8169
Epoch 47/5000
14s 29ms/step-loss:0.8811-acc:0.7818-val_loss:0.7807-val_acc:0.8206
Epoch 48/5000
14s 29ms/step-loss:0.8779-acc:0.7845-val_loss:0.7634-val_acc:0.8273
Epoch 49/5000
14s 29ms/step-loss:0.8800-acc:0.7827-val_loss:0.7734-val_acc:0.8242
Epoch 50/5000
14s 29ms/step-loss:0.8772-acc:0.7835-val_loss:0.7841-val_acc:0.8193
Epoch 51/5000
14s 29ms/step-loss:0.8736-acc:0.7843-val_loss:0.7970-val_acc:0.8190
Epoch 52/5000
14s 29ms/step-loss:0.8768-acc:0.7852-val_loss:0.7855-val_acc:0.8178
Epoch 53/5000
14s 29ms/step-loss:0.8741-acc:0.7835-val_loss:0.7851-val_acc:0.8209
Epoch 54/5000
14s 29ms/step-loss:0.8722-acc:0.7858-val_loss:0.7825-val_acc:0.8184
Epoch 55/5000
14s 29ms/step-loss:0.8697-acc:0.7891-val_loss:0.7771-val_acc:0.8227
Epoch 56/5000
14s 29ms/step-loss:0.8711-acc:0.7873-val_loss:0.7677-val_acc:0.8236
Epoch 57/5000
14s 29ms/step-loss:0.8711-acc:0.7878-val_loss:0.7872-val_acc:0.8155
Epoch 58/5000
14s 29ms/step-loss:0.8678-acc:0.7886-val_loss:0.7936-val_acc:0.8193
Epoch 59/5000
14s 29ms/step-loss:0.8650-acc:0.7904-val_loss:0.7778-val_acc:0.8287
Epoch 60/5000
14s 29ms/step-loss:0.8655-acc:0.7905-val_loss:0.7670-val_acc:0.8283
Epoch 61/5000
14s 29ms/step-loss:0.8640-acc:0.7906-val_loss:0.7757-val_acc:0.8247
Epoch 62/5000
14s 29ms/step-loss:0.8645-acc:0.7894-val_loss:0.7600-val_acc:0.8312
Epoch 63/5000
14s 29ms/step-loss:0.8620-acc:0.7916-val_loss:0.7823-val_acc:0.8211
Epoch 64/5000
14s 29ms/step-loss:0.8584-acc:0.7914-val_loss:0.7873-val_acc:0.8187
Epoch 65/5000
14s 29ms/step-loss:0.8567-acc:0.7930-val_loss:0.7810-val_acc:0.8231
Epoch 66/5000
14s 29ms/step-loss:0.8639-acc:0.7912-val_loss:0.7653-val_acc:0.8298
Epoch 67/5000
14s 29ms/step-loss:0.8594-acc:0.7939-val_loss:0.7763-val_acc:0.8265
Epoch 68/5000
14s 29ms/step-loss:0.8585-acc:0.7921-val_loss:0.7711-val_acc:0.8277
Epoch 69/5000
14s 29ms/step-loss:0.8571-acc:0.7937-val_loss:0.7650-val_acc:0.8278
Epoch 70/5000
14s 29ms/step-loss:0.8590-acc:0.7942-val_loss:0.7646-val_acc:0.8290
Epoch 71/5000
14s 29ms/step-loss:0.8548-acc:0.7960-val_loss:0.7720-val_acc:0.8247
Epoch 72/5000
14s 29ms/step-loss:0.8521-acc:0.7967-val_loss:0.7601-val_acc:0.8321
Epoch 73/5000
14s 29ms/step-loss:0.8558-acc:0.7944-val_loss:0.7635-val_acc:0.8326
Epoch 74/5000
14s 29ms/step-loss:0.8483-acc:0.7973-val_loss:0.7519-val_acc:0.8357
Epoch 75/5000
14s 29ms/step-loss:0.8506-acc:0.7966-val_loss:0.7509-val_acc:0.8339
Epoch 76/5000
14s 29ms/step-loss:0.8447-acc:0.7989-val_loss:0.7960-val_acc:0.8171
Epoch 77/5000
14s 29ms/step-loss:0.8497-acc:0.7991-val_loss:0.7699-val_acc:0.8282
Epoch 78/5000
14s 29ms/step-loss:0.8464-acc:0.7996-val_loss:0.7747-val_acc:0.8269
Epoch 79/5000
14s 29ms/step-loss:0.8509-acc:0.7971-val_loss:0.7450-val_acc:0.8379
Epoch 80/5000
14s 29ms/step-loss:0.8449-acc:0.7981-val_loss:0.7784-val_acc:0.8251
Epoch 81/5000
14s 29ms/step-loss:0.8446-acc:0.7985-val_loss:0.7689-val_acc:0.8312
Epoch 82/5000
14s 29ms/step-loss:0.8481-acc:0.7992-val_loss:0.7573-val_acc:0.8306
Epoch 83/5000
14s 29ms/step-loss:0.8417-acc:0.7996-val_loss:0.7677-val_acc:0.8297
Epoch 84/5000
14s 29ms/step-loss:0.8475-acc:0.7991-val_loss:0.7583-val_acc:0.8287
Epoch 85/5000
14s 29ms/step-loss:0.8464-acc:0.7983-val_loss:0.7552-val_acc:0.8322
Epoch 86/5000
14s 29ms/step-loss:0.8413-acc:0.8003-val_loss:0.7631-val_acc:0.8272
Epoch 87/5000
14s 29ms/step-loss:0.8400-acc:0.8001-val_loss:0.7308-val_acc:0.8473
Epoch 88/5000
14s 29ms/step-loss:0.8438-acc:0.8011-val_loss:0.7709-val_acc:0.8336
Epoch 89/5000
14s 28ms/step-loss:0.8425-acc:0.8016-val_loss:0.7587-val_acc:0.8323
Epoch 90/5000
14s 29ms/step-loss:0.8343-acc:0.8021-val_loss:0.7741-val_acc:0.8234
Epoch 91/5000
14s 29ms/step-loss:0.8438-acc:0.7996-val_loss:0.7556-val_acc:0.8351
Epoch 92/5000
14s 29ms/step-loss:0.8312-acc:0.8047-val_loss:0.7597-val_acc:0.8329
Epoch 93/5000
14s 29ms/step-loss:0.8412-acc:0.8006-val_loss:0.7615-val_acc:0.8289
Epoch 94/5000
14s 29ms/step-loss:0.8381-acc:0.8022-val_loss:0.7550-val_acc:0.8356
Epoch 95/5000
14s 29ms/step-loss:0.8362-acc:0.8025-val_loss:0.7662-val_acc:0.8306
Epoch 96/5000
14s 29ms/step-loss:0.8378-acc:0.8015-val_loss:0.7676-val_acc:0.8299
Epoch 97/5000
14s 29ms/step-loss:0.8378-acc:0.8032-val_loss:0.7482-val_acc:0.8382
Epoch 98/5000
14s 28ms/step-loss:0.8357-acc:0.8020-val_loss:0.7348-val_acc:0.8398
Epoch 99/5000
14s 29ms/step-loss:0.8369-acc:0.8018-val_loss:0.7620-val_acc:0.8332
Epoch 100/5000
14s 29ms/step-loss:0.8390-acc:0.8032-val_loss:0.7553-val_acc:0.8336
Epoch 101/5000
14s 29ms/step-loss:0.8316-acc:0.8059-val_loss:0.7575-val_acc:0.8314
Epoch 102/5000
14s 29ms/step-loss:0.8347-acc:0.8044-val_loss:0.7530-val_acc:0.8338
Epoch 103/5000
14s 29ms/step-loss:0.8327-acc:0.8043-val_loss:0.7527-val_acc:0.8376
Epoch 104/5000
14s 29ms/step-loss:0.8349-acc:0.8051-val_loss:0.7427-val_acc:0.8376
Epoch 105/5000
14s 29ms/step-loss:0.8320-acc:0.8050-val_loss:0.7632-val_acc:0.8333
Epoch 106/5000
14s 29ms/step-loss:0.8307-acc:0.8051-val_loss:0.7351-val_acc:0.8399
Epoch 107/5000
14s 29ms/step-loss:0.8311-acc:0.8061-val_loss:0.7481-val_acc:0.8351
Epoch 108/5000
14s 29ms/step-loss:0.8304-acc:0.8057-val_loss:0.7464-val_acc:0.8383
Epoch 109/5000
14s 29ms/step-loss:0.8292-acc:0.8068-val_loss:0.7460-val_acc:0.8399
Epoch 110/5000
14s 29ms/step-loss:0.8288-acc:0.8068-val_loss:0.7730-val_acc:0.8277
Epoch 111/5000
14s 29ms/step-loss:0.8307-acc:0.8046-val_loss:0.7451-val_acc:0.8381
Epoch 112/5000
14s 29ms/step-loss:0.8258-acc:0.8079-val_loss:0.7317-val_acc:0.8452
Epoch 113/5000
14s 29ms/step-loss:0.8304-acc:0.8067-val_loss:0.7715-val_acc:0.8274
Epoch 114/5000
14s 29ms/step-loss:0.8317-acc:0.8041-val_loss:0.7588-val_acc:0.8337
Epoch 115/5000
14s 29ms/step-loss:0.8293-acc:0.8044-val_loss:0.7498-val_acc:0.8366
Epoch 116/5000
14s 29ms/step-loss:0.8330-acc:0.8057-val_loss:0.7491-val_acc:0.8317
Epoch 117/5000
14s 29ms/step-loss:0.8215-acc:0.8074-val_loss:0.7496-val_acc:0.8365
Epoch 118/5000
14s 29ms/step-loss:0.8276-acc:0.8073-val_loss:0.7538-val_acc:0.8362
Epoch 119/5000
14s 29ms/step-loss:0.8291-acc:0.8069-val_loss:0.7536-val_acc:0.8353
Epoch 120/5000
14s 29ms/step-loss:0.8283-acc:0.8057-val_loss:0.7564-val_acc:0.8338
Epoch 121/5000
14s 29ms/step-loss:0.8248-acc:0.8079-val_loss:0.7387-val_acc:0.8420
Epoch 122/5000
14s 29ms/step-loss:0.8241-acc:0.8077-val_loss:0.7784-val_acc:0.8272
Epoch 123/5000
14s 29ms/step-loss:0.8257-acc:0.8077-val_loss:0.7649-val_acc:0.8289
Epoch 124/5000
14s 29ms/step-loss:0.8194-acc:0.8097-val_loss:0.7383-val_acc:0.8386
Epoch 125/5000
14s 29ms/step-loss:0.8246-acc:0.8063-val_loss:0.7556-val_acc:0.8373
Epoch 126/5000
14s 29ms/step-loss:0.8253-acc:0.8072-val_loss:0.7366-val_acc:0.8380
Epoch 127/5000
14s 29ms/step-loss:0.8204-acc:0.8103-val_loss:0.7359-val_acc:0.8400
Epoch 128/5000
14s 29ms/step-loss:0.8223-acc:0.8089-val_loss:0.7587-val_acc:0.8358
Epoch 129/5000
14s 29ms/step-loss:0.8210-acc:0.8077-val_loss:0.7663-val_acc:0.8323
Epoch 130/5000
14s 28ms/step-loss:0.8232-acc:0.8083-val_loss:0.7408-val_acc:0.8400
Epoch 131/5000
14s 29ms/step-loss:0.8270-acc:0.8074-val_loss:0.7589-val_acc:0.8339
Epoch 132/5000
14s 29ms/step-loss:0.8245-acc:0.8106-val_loss:0.7649-val_acc:0.8324
Epoch 133/5000
14s 29ms/step-loss:0.8216-acc:0.8092-val_loss:0.7717-val_acc:0.8322
Epoch 134/5000
14s 29ms/step-loss:0.8218-acc:0.8099-val_loss:0.7480-val_acc:0.8341
Epoch 135/5000
14s 29ms/step-loss:0.8220-acc:0.8093-val_loss:0.7613-val_acc:0.8310
Epoch 136/5000
14s 29ms/step-loss:0.8208-acc:0.8096-val_loss:0.7516-val_acc:0.8367
Epoch 137/5000
14s 29ms/step-loss:0.8132-acc:0.8130-val_loss:0.7599-val_acc:0.8323
Epoch 138/5000
14s 29ms/step-loss:0.8183-acc:0.8109-val_loss:0.7543-val_acc:0.8345
Epoch 139/5000
14s 29ms/step-loss:0.8213-acc:0.8090-val_loss:0.7256-val_acc:0.8475
Epoch 140/5000
14s 29ms/step-loss:0.8207-acc:0.8094-val_loss:0.7671-val_acc:0.8319
Epoch 141/5000
14s 29ms/step-loss:0.8181-acc:0.8129-val_loss:0.7379-val_acc:0.8425
Epoch 142/5000
14s 29ms/step-loss:0.8168-acc:0.8102-val_loss:0.7349-val_acc:0.8420
Epoch 143/5000
14s 29ms/step-loss:0.8204-acc:0.8106-val_loss:0.7240-val_acc:0.8473
Epoch 144/5000
14s 29ms/step-loss:0.8152-acc:0.8119-val_loss:0.7530-val_acc:0.8353
Epoch 145/5000
14s 29ms/step-loss:0.8173-acc:0.8134-val_loss:0.7306-val_acc:0.8451
Epoch 146/5000
14s 29ms/step-loss:0.8162-acc:0.8130-val_loss:0.7702-val_acc:0.8250
Epoch 147/5000
14s 29ms/step-loss:0.8133-acc:0.8126-val_loss:0.7580-val_acc:0.8365
Epoch 148/5000
14s 29ms/step-loss:0.8170-acc:0.8108-val_loss:0.7546-val_acc:0.8344
Epoch 149/5000
14s 29ms/step-loss:0.8143-acc:0.8109-val_loss:0.7413-val_acc:0.8371
Epoch 150/5000
14s 29ms/step-loss:0.8168-acc:0.8106-val_loss:0.7591-val_acc:0.8348
Epoch 151/5000
14s 29ms/step-loss:0.8184-acc:0.8087-val_loss:0.7205-val_acc:0.8462
Epoch 152/5000
14s 29ms/step-loss:0.8173-acc:0.8111-val_loss:0.7353-val_acc:0.8407
Epoch 153/5000
14s 29ms/step-loss:0.8132-acc:0.8144-val_loss:0.7446-val_acc:0.8339
Epoch 154/5000
14s 29ms/step-loss:0.8166-acc:0.8106-val_loss:0.7216-val_acc:0.8496
Epoch 155/5000
14s 29ms/step-loss:0.8203-acc:0.8103-val_loss:0.7505-val_acc:0.8340
Epoch 156/5000
14s 29ms/step-loss:0.8138-acc:0.8115-val_loss:0.7481-val_acc:0.8363
Epoch 157/5000
14s 29ms/step-loss:0.8158-acc:0.8109-val_loss:0.7553-val_acc:0.8353
Epoch 158/5000
14s 29ms/step-loss:0.8133-acc:0.8131-val_loss:0.7236-val_acc:0.8460
Epoch 159/5000
14s 29ms/step-loss:0.8155-acc:0.8104-val_loss:0.7323-val_acc:0.8432
Epoch 160/5000
14s 28ms/step-loss:0.8107-acc:0.8135-val_loss:0.7567-val_acc:0.8351
Epoch 161/5000
14s 29ms/step-loss:0.8114-acc:0.8138-val_loss:0.7379-val_acc:0.8399
Epoch 162/5000
14s 29ms/step-loss:0.8095-acc:0.8148-val_loss:0.7653-val_acc:0.8350
Epoch 163/5000
14s 29ms/step-loss:0.8136-acc:0.8132-val_loss:0.7310-val_acc:0.8416
Epoch 164/5000
14s 29ms/step-loss:0.8074-acc:0.8149-val_loss:0.7142-val_acc:0.8510
Epoch 165/5000
14s 29ms/step-loss:0.8148-acc:0.8118-val_loss:0.7520-val_acc:0.8398
Epoch 166/5000
14s 29ms/step-loss:0.8153-acc:0.8122-val_loss:0.7357-val_acc:0.8398
Epoch 167/5000
14s 29ms/step-loss:0.8086-acc:0.8139-val_loss:0.7406-val_acc:0.8405
Epoch 168/5000
14s 29ms/step-loss:0.8110-acc:0.8135-val_loss:0.7361-val_acc:0.8427
Epoch 169/5000
14s 29ms/step-loss:0.8107-acc:0.8130-val_loss:0.7491-val_acc:0.8362
Epoch 170/5000
14s 29ms/step-loss:0.8105-acc:0.8130-val_loss:0.7632-val_acc:0.8316
Epoch 171/5000
14s 29ms/step-loss:0.8125-acc:0.8145-val_loss:0.7676-val_acc:0.8293
Epoch 172/5000
14s 29ms/step-loss:0.8102-acc:0.8146-val_loss:0.7597-val_acc:0.8353
Epoch 173/5000
14s 29ms/step-loss:0.8098-acc:0.8125-val_loss:0.7485-val_acc:0.8389
Epoch 174/5000
14s 29ms/step-loss:0.8108-acc:0.8131-val_loss:0.7655-val_acc:0.8329
Epoch 175/5000
14s 29ms/step-loss:0.8066-acc:0.8166-val_loss:0.7373-val_acc:0.8422
Epoch 176/5000
14s 29ms/step-loss:0.8074-acc:0.8133-val_loss:0.7478-val_acc:0.8356
Epoch 177/5000
14s 29ms/step-loss:0.8065-acc:0.8154-val_loss:0.7594-val_acc:0.8379
Epoch 178/5000
14s 29ms/step-loss:0.8104-acc:0.8150-val_loss:0.7273-val_acc:0.8477
Epoch 179/5000
14s 29ms/step-loss:0.8053-acc:0.8162-val_loss:0.7233-val_acc:0.8457
Epoch 180/5000
14s 29ms/step-loss:0.8067-acc:0.8153-val_loss:0.7389-val_acc:0.8433
Epoch 181/5000
14s 29ms/step-loss:0.8089-acc:0.8153-val_loss:0.7563-val_acc:0.8371
Epoch 182/5000
14s 29ms/step-loss:0.8097-acc:0.8143-val_loss:0.7127-val_acc:0.8539
Epoch 183/5000
14s 29ms/step-loss:0.8092-acc:0.8155-val_loss:0.7457-val_acc:0.8378
Epoch 184/5000
14s 29ms/step-loss:0.8085-acc:0.8138-val_loss:0.7481-val_acc:0.8390
Epoch 185/5000
14s 29ms/step-loss:0.8130-acc:0.8125-val_loss:0.7404-val_acc:0.8399
Epoch 186/5000
14s 29ms/step-loss:0.8106-acc:0.8137-val_loss:0.7346-val_acc:0.8386
Epoch 187/5000
14s 29ms/step-loss:0.8029-acc:0.8188-val_loss:0.7304-val_acc:0.8427
Epoch 188/5000
14s 29ms/step-loss:0.8038-acc:0.8168-val_loss:0.7381-val_acc:0.8420
Epoch 189/5000
14s 29ms/step-loss:0.8064-acc:0.8163-val_loss:0.7607-val_acc:0.8323
Epoch 190/5000
14s 29ms/step-loss:0.8120-acc:0.8136-val_loss:0.7491-val_acc:0.8408
Epoch 191/5000
14s 29ms/step-loss:0.8080-acc:0.8159-val_loss:0.7317-val_acc:0.8477
Epoch 192/5000
14s 29ms/step-loss:0.8058-acc:0.8151-val_loss:0.7431-val_acc:0.8367
Epoch 193/5000
14s 29ms/step-loss:0.8114-acc:0.8142-val_loss:0.7348-val_acc:0.8399
Epoch 194/5000
14s 29ms/step-loss:0.7997-acc:0.8172-val_loss:0.7295-val_acc:0.8434
Epoch 195/5000
14s 29ms/step-loss:0.8110-acc:0.8143-val_loss:0.7138-val_acc:0.8516
Epoch 196/5000
14s 29ms/step-loss:0.8069-acc:0.8127-val_loss:0.7544-val_acc:0.8377
Epoch 197/5000
14s 29ms/step-loss:0.8031-acc:0.8177-val_loss:0.7436-val_acc:0.8442
Epoch 198/5000
14s 29ms/step-loss:0.8027-acc:0.8170-val_loss:0.7417-val_acc:0.8372
Epoch 199/5000
14s 29ms/step-loss:0.8024-acc:0.8155-val_loss:0.7525-val_acc:0.8345
Epoch 200/5000
14s 29ms/step-loss:0.8033-acc:0.8170-val_loss:0.7385-val_acc:0.8423
Epoch 201/5000
14s 29ms/step-loss:0.8066-acc:0.8155-val_loss:0.7318-val_acc:0.8452
Epoch 202/5000
14s 29ms/step-loss:0.8076-acc:0.8165-val_loss:0.7371-val_acc:0.8439
Epoch 203/5000
14s 29ms/step-loss:0.8030-acc:0.8166-val_loss:0.7295-val_acc:0.8447
Epoch 204/5000
14s 29ms/step-loss:0.8019-acc:0.8164-val_loss:0.7153-val_acc:0.8485
Epoch 205/5000
14s 29ms/step-loss:0.8073-acc:0.8142-val_loss:0.7385-val_acc:0.8428
Epoch 206/5000
14s 29ms/step-loss:0.8034-acc:0.8164-val_loss:0.7435-val_acc:0.8428
Epoch 207/5000
14s 29ms/step-loss:0.8040-acc:0.8167-val_loss:0.7462-val_acc:0.8398
Epoch 208/5000
14s 28ms/step-loss:0.8017-acc:0.8141-val_loss:0.7423-val_acc:0.8387
Epoch 209/5000
14s 29ms/step-loss:0.8069-acc:0.8141-val_loss:0.7276-val_acc:0.8446
Epoch 210/5000
14s 28ms/step-loss:0.7999-acc:0.8182-val_loss:0.7280-val_acc:0.8451
Epoch 211/5000
14s 29ms/step-loss:0.8038-acc:0.8173-val_loss:0.7510-val_acc:0.8375
Epoch 212/5000
14s 29ms/step-loss:0.8054-acc:0.8154-val_loss:0.7397-val_acc:0.8402
Epoch 213/5000
14s 29ms/step-loss:0.8063-acc:0.8174-val_loss:0.7352-val_acc:0.8399
Epoch 214/5000
14s 29ms/step-loss:0.8059-acc:0.8167-val_loss:0.7599-val_acc:0.8330
Epoch 215/5000
14s 29ms/step-loss:0.8095-acc:0.8139-val_loss:0.7212-val_acc:0.8494
Epoch 216/5000
14s 29ms/step-loss:0.8039-acc:0.8165-val_loss:0.7612-val_acc:0.8321
Epoch 217/5000
14s 29ms/step-loss:0.8084-acc:0.8142-val_loss:0.7265-val_acc:0.8488
Epoch 218/5000
14s 29ms/step-loss:0.8024-acc:0.8164-val_loss:0.7552-val_acc:0.8385
Epoch 219/5000
14s 29ms/step-loss:0.8067-acc:0.8140-val_loss:0.7338-val_acc:0.8453
Epoch 220/5000
14s 29ms/step-loss:0.8021-acc:0.8185-val_loss:0.7373-val_acc:0.8473
Epoch 221/5000
14s 29ms/step-loss:0.8006-acc:0.8187-val_loss:0.7413-val_acc:0.8401
Epoch 222/5000
14s 29ms/step-loss:0.7987-acc:0.8192-val_loss:0.7323-val_acc:0.8426
Epoch 223/5000
14s 29ms/step-loss:0.8001-acc:0.8177-val_loss:0.7311-val_acc:0.8450
Epoch 224/5000
14s 29ms/step-loss:0.8025-acc:0.8179-val_loss:0.7417-val_acc:0.8415
Epoch 225/5000
14s 29ms/step-loss:0.8026-acc:0.8182-val_loss:0.7238-val_acc:0.8520
Epoch 226/5000
14s 29ms/step-loss:0.8008-acc:0.8174-val_loss:0.7348-val_acc:0.8471
Epoch 227/5000
14s 29ms/step-loss:0.8020-acc:0.8173-val_loss:0.7414-val_acc:0.8392
Epoch 228/5000
14s 29ms/step-loss:0.8049-acc:0.8159-val_loss:0.7642-val_acc:0.8351
Epoch 229/5000
14s 29ms/step-loss:0.8000-acc:0.8202-val_loss:0.7448-val_acc:0.8428
Epoch 230/5000
14s 29ms/step-loss:0.8026-acc:0.8165-val_loss:0.7576-val_acc:0.8365
Epoch 231/5000
14s 29ms/step-loss:0.8023-acc:0.8173-val_loss:0.7490-val_acc:0.8394
Epoch 232/5000
14s 29ms/step-loss:0.8002-acc:0.8186-val_loss:0.7445-val_acc:0.8411
Epoch 233/5000
14s 29ms/step-loss:0.8010-acc:0.8179-val_loss:0.7350-val_acc:0.8431
Epoch 234/5000
14s 29ms/step-loss:0.8057-acc:0.8156-val_loss:0.7372-val_acc:0.8453
Epoch 235/5000
14s 29ms/step-loss:0.7973-acc:0.8185-val_loss:0.7230-val_acc:0.8490
Epoch 236/5000
14s 29ms/step-loss:0.8048-acc:0.8169-val_loss:0.7283-val_acc:0.8421
Epoch 237/5000
14s 29ms/step-loss:0.8001-acc:0.8179-val_loss:0.7345-val_acc:0.8444
Epoch 238/5000
14s 29ms/step-loss:0.7995-acc:0.8173-val_loss:0.7595-val_acc:0.8340
Epoch 239/5000
14s 29ms/step-loss:0.8022-acc:0.8173-val_loss:0.7389-val_acc:0.8398
Epoch 240/5000
14s 28ms/step-loss:0.8003-acc:0.8181-val_loss:0.7388-val_acc:0.8429
Epoch 241/5000
14s 29ms/step-loss:0.8006-acc:0.8187-val_loss:0.7415-val_acc:0.8413
Epoch 242/5000
14s 29ms/step-loss:0.8020-acc:0.8167-val_loss:0.7296-val_acc:0.8506
Epoch 243/5000
14s 29ms/step-loss:0.7966-acc:0.8192-val_loss:0.7433-val_acc:0.8383
Epoch 244/5000
14s 29ms/step-loss:0.8014-acc:0.8186-val_loss:0.7347-val_acc:0.8423
Epoch 245/5000
14s 29ms/step-loss:0.8037-acc:0.8164-val_loss:0.7479-val_acc:0.8413
Epoch 246/5000
14s 29ms/step-loss:0.7996-acc:0.8185-val_loss:0.7393-val_acc:0.8413
Epoch 247/5000
14s 29ms/step-loss:0.7986-acc:0.8198-val_loss:0.7266-val_acc:0.8473
Epoch 248/5000
14s 29ms/step-loss:0.7990-acc:0.8187-val_loss:0.7422-val_acc:0.8415
Epoch 249/5000
14s 28ms/step-loss:0.7970-acc:0.8193-val_loss:0.7325-val_acc:0.8450
Epoch 250/5000
14s 29ms/step-loss:0.8014-acc:0.8166-val_loss:0.7342-val_acc:0.8443
Epoch 251/5000
14s 29ms/step-loss:0.8032-acc:0.8176-val_loss:0.7330-val_acc:0.8453
Epoch 252/5000
14s 29ms/step-loss:0.8051-acc:0.8161-val_loss:0.7535-val_acc:0.8367
Epoch 253/5000
14s 29ms/step-loss:0.7980-acc:0.8211-val_loss:0.7217-val_acc:0.8507
Epoch 254/5000
14s 29ms/step-loss:0.8033-acc:0.8163-val_loss:0.7390-val_acc:0.8423
Epoch 255/5000
14s 29ms/step-loss:0.7991-acc:0.8179-val_loss:0.7291-val_acc:0.8468
Epoch 256/5000
14s 29ms/step-loss:0.7978-acc:0.8189-val_loss:0.7384-val_acc:0.8454
Epoch 257/5000
14s 29ms/step-loss:0.7993-acc:0.8190-val_loss:0.7049-val_acc:0.8536
Epoch 258/5000
14s 29ms/step-loss:0.8019-acc:0.8183-val_loss:0.7616-val_acc:0.8394
Epoch 259/5000
14s 29ms/step-loss:0.7873-acc:0.8211-val_loss:0.7415-val_acc:0.8396
Epoch 260/5000
14s 29ms/step-loss:0.8046-acc:0.8170-val_loss:0.7395-val_acc:0.8447
Epoch 261/5000
14s 29ms/step-loss:0.8046-acc:0.8175-val_loss:0.7319-val_acc:0.8470
Epoch 262/5000
14s 29ms/step-loss:0.7945-acc:0.8204-val_loss:0.7372-val_acc:0.8398
Epoch 263/5000
14s 29ms/step-loss:0.7995-acc:0.8181-val_loss:0.7467-val_acc:0.8421
Epoch 264/5000
14s 29ms/step-loss:0.8025-acc:0.8168-val_loss:0.7216-val_acc:0.8483
Epoch 265/5000
14s 29ms/step-loss:0.8051-acc:0.8167-val_loss:0.7334-val_acc:0.8440
Epoch 266/5000
14s 29ms/step-loss:0.7917-acc:0.8221-val_loss:0.7452-val_acc:0.8417
Epoch 267/5000
14s 29ms/step-loss:0.8009-acc:0.8181-val_loss:0.7270-val_acc:0.8465
Epoch 268/5000
14s 29ms/step-loss:0.7983-acc:0.8188-val_loss:0.7242-val_acc:0.8477
Epoch 269/5000
14s 29ms/step-loss:0.8044-acc:0.8162-val_loss:0.7402-val_acc:0.8418
Epoch 270/5000
14s 29ms/step-loss:0.7993-acc:0.8196-val_loss:0.7411-val_acc:0.8402
Epoch 271/5000
14s 29ms/step-loss:0.7981-acc:0.8188-val_loss:0.7554-val_acc:0.8427
Epoch 272/5000
14s 29ms/step-loss:0.8031-acc:0.8176-val_loss:0.7506-val_acc:0.8383
Epoch 273/5000
14s 29ms/step-loss:0.7973-acc:0.8203-val_loss:0.7229-val_acc:0.8523
Epoch 274/5000
14s 29ms/step-loss:0.7960-acc:0.8208-val_loss:0.7330-val_acc:0.8437
Epoch 275/5000
14s 29ms/step-loss:0.7953-acc:0.8189-val_loss:0.7349-val_acc:0.8428
Epoch 276/5000
14s 29ms/step-loss:0.7989-acc:0.8173-val_loss:0.7498-val_acc:0.8386
Epoch 277/5000
14s 29ms/step-loss:0.7967-acc:0.8187-val_loss:0.7153-val_acc:0.8524
Epoch 278/5000
14s 29ms/step-loss:0.8038-acc:0.8175-val_loss:0.7033-val_acc:0.8495
Epoch 279/5000
14s 29ms/step-loss:0.7964-acc:0.8188-val_loss:0.7159-val_acc:0.8529
Epoch 280/5000
14s 29ms/step-loss:0.7979-acc:0.8176-val_loss:0.7406-val_acc:0.8419
Epoch 281/5000
14s 29ms/step-loss:0.7985-acc:0.8196-val_loss:0.7250-val_acc:0.8493
Epoch 282/5000
14s 29ms/step-loss:0.7990-acc:0.8180-val_loss:0.7351-val_acc:0.8448
Epoch 283/5000
14s 29ms/step-loss:0.7967-acc:0.8202-val_loss:0.7554-val_acc:0.8332
Epoch 284/5000
14s 29ms/step-loss:0.7939-acc:0.8195-val_loss:0.7553-val_acc:0.8359
Epoch 285/5000
14s 29ms/step-loss:0.7956-acc:0.8200-val_loss:0.7495-val_acc:0.8414
Epoch 286/5000
14s 29ms/step-loss:0.7963-acc:0.8196-val_loss:0.7406-val_acc:0.8407
Epoch 287/5000
14s 29ms/step-loss:0.7997-acc:0.8182-val_loss:0.7359-val_acc:0.8465
Epoch 288/5000
14s 29ms/step-loss:0.8016-acc:0.8190-val_loss:0.7220-val_acc:0.8503
Epoch 289/5000
14s 29ms/step-loss:0.7904-acc:0.8218-val_loss:0.7447-val_acc:0.8406
Epoch 290/5000
14s 29ms/step-loss:0.7960-acc:0.8202-val_loss:0.7467-val_acc:0.8413
Epoch 291/5000
14s 29ms/step-loss:0.7978-acc:0.8166-val_loss:0.7273-val_acc:0.8470
Epoch 292/5000
14s 29ms/step-loss:0.7970-acc:0.8189-val_loss:0.7307-val_acc:0.8446
Epoch 293/5000
14s 29ms/step-loss:0.7947-acc:0.8213-val_loss:0.7372-val_acc:0.8441
Epoch 294/5000
14s 29ms/step-loss:0.8029-acc:0.8165-val_loss:0.7397-val_acc:0.8418
Epoch 295/5000
14s 29ms/step-loss:0.7929-acc:0.8225-val_loss:0.7531-val_acc:0.8365
Epoch 296/5000
14s 29ms/step-loss:0.7954-acc:0.8206-val_loss:0.7608-val_acc:0.8379
Epoch 297/5000
14s 28ms/step-loss:0.7976-acc:0.8192-val_loss:0.7340-val_acc:0.8435
Epoch 298/5000
14s 29ms/step-loss:0.8002-acc:0.8187-val_loss:0.7608-val_acc:0.8385
Epoch 299/5000
14s 29ms/step-loss:0.7967-acc:0.8202-val_loss:0.7556-val_acc:0.8365
Epoch 300/5000
14s 29ms/step-loss:0.7997-acc:0.8189-val_loss:0.7509-val_acc:0.8359
Epoch 301/5000
14s 29ms/step-loss:0.7992-acc:0.8174-val_loss:0.7490-val_acc:0.8382
Epoch 302/5000
14s 29ms/step-loss:0.7948-acc:0.8189-val_loss:0.7200-val_acc:0.8464
Epoch 303/5000
14s 29ms/step-loss:0.8011-acc:0.8174-val_loss:0.7219-val_acc:0.8461
Epoch 304/5000
14s 29ms/step-loss:0.7958-acc:0.8189-val_loss:0.7125-val_acc:0.8468
Epoch 305/5000
14s 29ms/step-loss:0.7948-acc:0.8195-val_loss:0.7306-val_acc:0.8474
Epoch 306/5000
14s 28ms/step-loss:0.7944-acc:0.8199-val_loss:0.7371-val_acc:0.8416
Epoch 307/5000
14s 29ms/step-loss:0.7984-acc:0.8180-val_loss:0.7553-val_acc:0.8365
Epoch 308/5000
14s 29ms/step-loss:0.7956-acc:0.8188-val_loss:0.7314-val_acc:0.8473
Epoch 309/5000
14s 29ms/step-loss:0.7971-acc:0.8196-val_loss:0.7239-val_acc:0.8480
Epoch 310/5000
14s 29ms/step-loss:0.7992-acc:0.8191-val_loss:0.7504-val_acc:0.8386
Epoch 311/5000
14s 29ms/step-loss:0.7944-acc:0.8205-val_loss:0.7498-val_acc:0.8404
Epoch 312/5000
14s 29ms/step-loss:0.7981-acc:0.8189-val_loss:0.7105-val_acc:0.8538
Epoch 313/5000
14s 29ms/step-loss:0.7945-acc:0.8174-val_loss:0.7346-val_acc:0.8420
Epoch 314/5000
14s 29ms/step-loss:0.7931-acc:0.8211-val_loss:0.7239-val_acc:0.8466
Epoch 315/5000
14s 29ms/step-loss:0.8007-acc:0.8165-val_loss:0.7138-val_acc:0.8538
Epoch 316/5000
14s 29ms/step-loss:0.7945-acc:0.8197-val_loss:0.7384-val_acc:0.8391
Epoch 317/5000
14s 29ms/step-loss:0.7965-acc:0.8194-val_loss:0.7387-val_acc:0.8435
Epoch 318/5000
14s 29ms/step-loss:0.7902-acc:0.8209-val_loss:0.7217-val_acc:0.8466
Epoch 319/5000
14s 29ms/step-loss:0.7971-acc:0.8185-val_loss:0.7375-val_acc:0.8441
Epoch 320/5000
14s 29ms/step-loss:0.7907-acc:0.8205-val_loss:0.7366-val_acc:0.8443
Epoch 321/5000
14s 29ms/step-loss:0.7930-acc:0.8202-val_loss:0.7164-val_acc:0.8515
Epoch 322/5000
14s 28ms/step-loss:0.7977-acc:0.8173-val_loss:0.7203-val_acc:0.8499
Epoch 323/5000
14s 29ms/step-loss:0.7979-acc:0.8202-val_loss:0.7311-val_acc:0.8426
Epoch 324/5000
14s 28ms/step-loss:0.7901-acc:0.8228-val_loss:0.7180-val_acc:0.8500
Epoch 325/5000
14s 28ms/step - loss:0.7986 - acc:0.8189 - val_loss:0.7442 - val_acc:0.8402
Epoch 326/5000
14s 28ms/step - loss:0.7940 - acc:0.8197 - val_loss:0.7268 - val_acc:0.8464
Epoch 327/5000
14s 28ms/step - loss:0.7939 - acc:0.8206 - val_loss:0.7613 - val_acc:0.8336
Epoch 328/5000
14s 28ms/step - loss:0.7937 - acc:0.8206 - val_loss:0.7193 - val_acc:0.8493
Epoch 329/5000
14s 28ms/step - loss:0.7936 - acc:0.8207 - val_loss:0.7299 - val_acc:0.8428
Epoch 330/5000
14s 28ms/step - loss:0.7907 - acc:0.8213 - val_loss:0.7597 - val_acc:0.8321
Epoch 331/5000
14s 28ms/step - loss:0.7921 - acc:0.8224 - val_loss:0.7331 - val_acc:0.8466
Epoch 332/5000
14s 28ms/step - loss:0.7991 - acc:0.8168 - val_loss:0.7172 - val_acc:0.8512
Epoch 333/5000
14s 28ms/step - loss:0.7886 - acc:0.8222 - val_loss:0.7147 - val_acc:0.8478
Epoch 334/5000
14s 28ms/step - loss:0.7889 - acc:0.8206 - val_loss:0.7311 - val_acc:0.8420
Epoch 335/5000
14s 28ms/step - loss:0.7922 - acc:0.8206 - val_loss:0.7256 - val_acc:0.8435
Epoch 336/5000
14s 28ms/step - loss:0.7888 - acc:0.8229 - val_loss:0.7329 - val_acc:0.8477
Epoch 337/5000
14s 28ms/step - loss:0.7970 - acc:0.8211 - val_loss:0.7333 - val_acc:0.8404
Epoch 338/5000
14s 28ms/step - loss:0.7903 - acc:0.8204 - val_loss:0.7601 - val_acc:0.8351
Epoch 339/5000
14s 28ms/step - loss:0.7947 - acc:0.8192 - val_loss:0.7236 - val_acc:0.8472
Epoch 340/5000
14s 28ms/step - loss:0.7905 - acc:0.8211 - val_loss:0.7479 - val_acc:0.8351
Epoch 341/5000
14s 28ms/step - loss:0.7978 - acc:0.8191 - val_loss:0.7375 - val_acc:0.8371
Epoch 342/5000
14s 28ms/step - loss:0.7980 - acc:0.8191 - val_loss:0.7290 - val_acc:0.8463
Epoch 343/5000
14s 28ms/step - loss:0.7875 - acc:0.8223 - val_loss:0.7219 - val_acc:0.8481
Epoch 344/5000
14s 28ms/step - loss:0.7920 - acc:0.8197 - val_loss:0.7331 - val_acc:0.8434
Epoch 345/5000
14s 28ms/step - loss:0.7907 - acc:0.8215 - val_loss:0.7237 - val_acc:0.8506
Epoch 346/5000
14s 28ms/step - loss:0.7927 - acc:0.8216 - val_loss:0.7544 - val_acc:0.8385
Epoch 347/5000
14s 28ms/step - loss:0.8009 - acc:0.8174 - val_loss:0.7244 - val_acc:0.8504
Epoch 348/5000
14s 28ms/step - loss:0.7926 - acc:0.8208 - val_loss:0.7503 - val_acc:0.8392
Epoch 349/5000
14s 28ms/step - loss:0.7914 - acc:0.8201 - val_loss:0.7273 - val_acc:0.8461
Epoch 350/5000
14s 28ms/step - loss:0.7978 - acc:0.8197 - val_loss:0.7437 - val_acc:0.8408
Epoch 351/5000
14s 28ms/step - loss:0.7884 - acc:0.8216 - val_loss:0.7357 - val_acc:0.8435
Epoch 352/5000
14s 28ms/step - loss:0.7922 - acc:0.8221 - val_loss:0.7278 - val_acc:0.8448
Epoch 353/5000
14s 28ms/step - loss:0.7969 - acc:0.8208 - val_loss:0.7199 - val_acc:0.8532
Epoch 354/5000
14s 28ms/step - loss:0.7901 - acc:0.8213 - val_loss:0.7201 - val_acc:0.8485
Epoch 355/5000
14s 28ms/step - loss:0.7930 - acc:0.8202 - val_loss:0.7350 - val_acc:0.8417
Epoch 356/5000
14s 28ms/step - loss:0.7958 - acc:0.8182 - val_loss:0.7275 - val_acc:0.8467
Epoch 357/5000
14s 28ms/step - loss:0.7976 - acc:0.8185 - val_loss:0.7361 - val_acc:0.8433
Epoch 358/5000
14s 28ms/step - loss:0.7973 - acc:0.8185 - val_loss:0.7140 - val_acc:0.8525
Epoch 359/5000
14s 28ms/step - loss:0.7891 - acc:0.8223 - val_loss:0.7193 - val_acc:0.8508
Epoch 360/5000
14s 28ms/step - loss:0.7976 - acc:0.8185 - val_loss:0.7289 - val_acc:0.8430
Epoch 361/5000
14s 28ms/step - loss:0.7961 - acc:0.8191 - val_loss:0.7136 - val_acc:0.8493
Epoch 362/5000
14s 28ms/step - loss:0.7894 - acc:0.8230 - val_loss:0.7322 - val_acc:0.8431
Epoch 363/5000
14s 28ms/step - loss:0.7949 - acc:0.8200 - val_loss:0.7290 - val_acc:0.8424
Epoch 364/5000
14s 28ms/step - loss:0.7907 - acc:0.8215 - val_loss:0.7415 - val_acc:0.8382
Epoch 365/5000
14s 28ms/step - loss:0.7963 - acc:0.8205 - val_loss:0.7449 - val_acc:0.8414
Epoch 366/5000
14s 28ms/step - loss:0.7946 - acc:0.8187 - val_loss:0.7290 - val_acc:0.8438
Epoch 367/5000
14s 28ms/step - loss:0.7922 - acc:0.8196 - val_loss:0.7456 - val_acc:0.8402
Epoch 368/5000
14s 28ms/step - loss:0.7924 - acc:0.8212 - val_loss:0.7350 - val_acc:0.8431
Epoch 369/5000
14s 28ms/step - loss:0.7904 - acc:0.8225 - val_loss:0.7435 - val_acc:0.8407
Epoch 370/5000
14s 28ms/step - loss:0.7904 - acc:0.8201 - val_loss:0.7368 - val_acc:0.8451
Epoch 371/5000
14s 28ms/step - loss:0.7915 - acc:0.8201 - val_loss:0.7398 - val_acc:0.8435
Epoch 372/5000
14s 28ms/step - loss:0.7902 - acc:0.8204 - val_loss:0.7211 - val_acc:0.8507
Epoch 373/5000
14s 28ms/step - loss:0.7905 - acc:0.8222 - val_loss:0.7466 - val_acc:0.8392
Epoch 374/5000
14s 28ms/step - loss:0.7921 - acc:0.8207 - val_loss:0.7133 - val_acc:0.8524
Epoch 375/5000
14s 28ms/step - loss:0.7918 - acc:0.8197 - val_loss:0.7360 - val_acc:0.8447
Epoch 376/5000
14s 28ms/step - loss:0.7918 - acc:0.8212 - val_loss:0.7277 - val_acc:0.8419
Epoch 377/5000
14s 28ms/step - loss:0.7995 - acc:0.8188 - val_loss:0.7595 - val_acc:0.8342
Epoch 378/5000
14s 28ms/step - loss:0.7909 - acc:0.8231 - val_loss:0.7525 - val_acc:0.8391
Epoch 379/5000
14s 28ms/step - loss:0.7995 - acc:0.8197 - val_loss:0.7502 - val_acc:0.8383
Epoch 380/5000
14s 28ms/step - loss:0.7931 - acc:0.8203 - val_loss:0.7302 - val_acc:0.8459
Epoch 381/5000
14s 28ms/step - loss:0.7938 - acc:0.8186 - val_loss:0.7347 - val_acc:0.8438
Epoch 382/5000
14s 28ms/step - loss:0.7904 - acc:0.8204 - val_loss:0.7291 - val_acc:0.8467
Epoch 383/5000
14s 28ms/step - loss:0.7924 - acc:0.8201 - val_loss:0.7319 - val_acc:0.8465
Epoch 384/5000
14s 28ms/step - loss:0.7920 - acc:0.8198 - val_loss:0.7269 - val_acc:0.8454
Epoch 385/5000
14s 28ms/step - loss:0.7903 - acc:0.8208 - val_loss:0.7381 - val_acc:0.8439
Epoch 386/5000
14s 28ms/step - loss:0.7938 - acc:0.8200 - val_loss:0.7326 - val_acc:0.8470
Epoch 387/5000
14s 28ms/step - loss:0.7996 - acc:0.8176 - val_loss:0.7418 - val_acc:0.8432
Epoch 388/5000
14s 28ms/step - loss:0.7919 - acc:0.8210 - val_loss:0.7385 - val_acc:0.8442
Epoch 389/5000
14s 28ms/step - loss:0.7910 - acc:0.8222 - val_loss:0.7606 - val_acc:0.8359
Epoch 390/5000
14s 28ms/step - loss:0.7888 - acc:0.8210 - val_loss:0.7250 - val_acc:0.8486
Epoch 391/5000
14s 28ms/step - loss:0.7941 - acc:0.8207 - val_loss:0.7276 - val_acc:0.8479
Epoch 392/5000
14s 28ms/step - loss:0.7938 - acc:0.8227 - val_loss:0.7232 - val_acc:0.8474
Epoch 393/5000
14s 28ms/step - loss:0.7924 - acc:0.8221 - val_loss:0.7188 - val_acc:0.8483
Epoch 394/5000
14s 28ms/step - loss:0.7929 - acc:0.8206 - val_loss:0.7263 - val_acc:0.8444
Epoch 395/5000
14s 28ms/step - loss:0.7942 - acc:0.8200 - val_loss:0.7290 - val_acc:0.8470
Epoch 396/5000
14s 28ms/step - loss:0.7892 - acc:0.8214 - val_loss:0.7212 - val_acc:0.8483
Epoch 397/5000
14s 28ms/step - loss:0.7952 - acc:0.8198 - val_loss:0.7321 - val_acc:0.8444
Epoch 398/5000
14s 28ms/step - loss:0.7909 - acc:0.8211 - val_loss:0.7210 - val_acc:0.8502
Epoch 399/5000
14s 28ms/step - loss:0.7910 - acc:0.8225 - val_loss:0.7176 - val_acc:0.8494
Epoch 400/5000
14s 28ms/step - loss:0.7897 - acc:0.8221 - val_loss:0.7578 - val_acc:0.8376
Epoch 401/5000
14s 28ms/step - loss:0.7904 - acc:0.8206 - val_loss:0.7290 - val_acc:0.8439
Epoch 402/5000
14s 28ms/step - loss:0.7891 - acc:0.8223 - val_loss:0.7578 - val_acc:0.8383
Epoch 403/5000
14s 28ms/step - loss:0.7936 - acc:0.8205 - val_loss:0.7260 - val_acc:0.8485
Epoch 404/5000
14s 28ms/step - loss:0.7900 - acc:0.8223 - val_loss:0.7307 - val_acc:0.8440
Epoch 405/5000
14s 28ms/step - loss:0.7905 - acc:0.8224 - val_loss:0.7157 - val_acc:0.8538
Epoch 406/5000
14s 28ms/step - loss:0.7924 - acc:0.8204 - val_loss:0.7455 - val_acc:0.8410
Epoch 407/5000
14s 28ms/step - loss:0.7914 - acc:0.8210 - val_loss:0.7252 - val_acc:0.8449
Epoch 408/5000
14s 28ms/step - loss:0.7904 - acc:0.8211 - val_loss:0.7389 - val_acc:0.8446
Epoch 409/5000
14s 28ms/step - loss:0.7898 - acc:0.8221 - val_loss:0.7590 - val_acc:0.8375
Epoch 410/5000
14s 28ms/step - loss:0.7895 - acc:0.8213 - val_loss:0.7298 - val_acc:0.8470
Epoch 411/5000
14s 28ms/step - loss:0.7901 - acc:0.8213 - val_loss:0.7164 - val_acc:0.8469
Epoch 412/5000
14s 28ms/step - loss:0.7929 - acc:0.8205 - val_loss:0.7126 - val_acc:0.8477
Epoch 413/5000
14s 28ms/step - loss:0.7890 - acc:0.8224 - val_loss:0.7402 - val_acc:0.8397
Epoch 414/5000
14s 28ms/step - loss:0.7907 - acc:0.8228 - val_loss:0.7410 - val_acc:0.8394
Epoch 415/5000
14s 28ms/step - loss:0.7911 - acc:0.8223 - val_loss:0.7331 - val_acc:0.8456
Epoch 416/5000
14s 28ms/step - loss:0.7876 - acc:0.8224 - val_loss:0.7213 - val_acc:0.8435
Epoch 417/5000
14s 28ms/step - loss:0.7891 - acc:0.8232 - val_loss:0.7221 - val_acc:0.8477
Epoch 418/5000
14s 28ms/step - loss:0.7876 - acc:0.8221 - val_loss:0.7295 - val_acc:0.8458
Epoch 419/5000
14s 28ms/step - loss:0.7936 - acc:0.8189 - val_loss:0.7259 - val_acc:0.8460
Epoch 420/5000
14s 28ms/step - loss:0.7862 - acc:0.8225 - val_loss:0.7266 - val_acc:0.8442
Epoch 421/5000
14s 28ms/step - loss:0.7924 - acc:0.8206 - val_loss:0.7199 - val_acc:0.8494
Epoch 422/5000
14s 28ms/step - loss:0.7884 - acc:0.8220 - val_loss:0.7452 - val_acc:0.8402
Epoch 423/5000
14s 28ms/step - loss:0.7850 - acc:0.8234 - val_loss:0.7295 - val_acc:0.8463
Epoch 424/5000
14s 28ms/step - loss:0.7922 - acc:0.8216 - val_loss:0.7228 - val_acc:0.8471
Epoch 425/5000
14s 28ms/step - loss:0.7883 - acc:0.8232 - val_loss:0.7336 - val_acc:0.8414
Epoch 426/5000
14s 28ms/step - loss:0.7896 - acc:0.8229 - val_loss:0.7173 - val_acc:0.8472
Epoch 427/5000
14s 28ms/step - loss:0.7887 - acc:0.8226 - val_loss:0.7450 - val_acc:0.8411
Epoch 428/5000
14s 28ms/step - loss:0.7873 - acc:0.8229 - val_loss:0.7104 - val_acc:0.8527
Epoch 429/5000
14s 28ms/step - loss:0.7910 - acc:0.8210 - val_loss:0.7176 - val_acc:0.8502
Epoch 430/5000
14s 28ms/step - loss:0.7899 - acc:0.8228 - val_loss:0.7041 - val_acc:0.8512
Epoch 431/5000
14s 28ms/step - loss:0.7932 - acc:0.8209 - val_loss:0.7444 - val_acc:0.8388
Epoch 432/5000
14s 28ms/step - loss:0.7903 - acc:0.8212 - val_loss:0.7429 - val_acc:0.8387
Epoch 433/5000
14s 28ms/step - loss:0.7889 - acc:0.8205 - val_loss:0.7196 - val_acc:0.8468
Epoch 434/5000
14s 28ms/step - loss:0.7919 - acc:0.8215 - val_loss:0.7182 - val_acc:0.8461
Epoch 435/5000
14s 28ms/step - loss:0.7884 - acc:0.8225 - val_loss:0.7478 - val_acc:0.8383
Epoch 436/5000
14s 28ms/step - loss:0.7883 - acc:0.8211 - val_loss:0.7398 - val_acc:0.8368
Epoch 437/5000
14s 28ms/step - loss:0.7931 - acc:0.8218 - val_loss:0.7214 - val_acc:0.8503
Epoch 438/5000
14s 28ms/step - loss:0.7857 - acc:0.8221 - val_loss:0.7163 - val_acc:0.8506
Epoch 439/5000
14s 28ms/step - loss:0.7959 - acc:0.8191 - val_loss:0.7325 - val_acc:0.8458
Epoch 440/5000
14s 28ms/step - loss:0.7860 - acc:0.8241 - val_loss:0.7304 - val_acc:0.8426
Epoch 441/5000
14s 28ms/step - loss:0.7884 - acc:0.8219 - val_loss:0.7270 - val_acc:0.8468
Epoch 442/5000
14s 28ms/step - loss:0.7876 - acc:0.8241 - val_loss:0.7499 - val_acc:0.8387
Epoch 443/5000
14s 28ms/step - loss:0.7900 - acc:0.8225 - val_loss:0.7243 - val_acc:0.8492
Epoch 444/5000
14s 28ms/step - loss:0.7920 - acc:0.8202 - val_loss:0.7360 - val_acc:0.8463
Epoch 445/5000
14s 28ms/step - loss:0.7891 - acc:0.8220 - val_loss:0.7233 - val_acc:0.8460
Epoch 446/5000
14s 28ms/step - loss:0.7907 - acc:0.8210 - val_loss:0.7301 - val_acc:0.8492
Epoch 447/5000
14s 28ms/step - loss:0.7890 - acc:0.8217 - val_loss:0.7263 - val_acc:0.8480
Epoch 448/5000
14s 28ms/step - loss:0.7910 - acc:0.8212 - val_loss:0.7444 - val_acc:0.8442
Epoch 449/5000
14s 28ms/step - loss:0.7863 - acc:0.8256 - val_loss:0.7507 - val_acc:0.8372
Epoch 450/5000
14s 28ms/step - loss:0.7901 - acc:0.8216 - val_loss:0.7289 - val_acc:0.8479
Epoch 451/5000
14s 28ms/step - loss:0.7904 - acc:0.8198 - val_loss:0.7432 - val_acc:0.8443
Epoch 452/5000
14s 28ms/step - loss:0.7868 - acc:0.8231 - val_loss:0.7074 - val_acc:0.8512
Epoch 453/5000
14s 28ms/step - loss:0.7912 - acc:0.8216 - val_loss:0.7367 - val_acc:0.8429
Epoch 454/5000
14s 28ms/step - loss:0.7901 - acc:0.8209 - val_loss:0.7404 - val_acc:0.8444
Epoch 455/5000
14s 28ms/step - loss:0.7900 - acc:0.8216 - val_loss:0.7532 - val_acc:0.8371
Epoch 456/5000
14s 28ms/step - loss:0.7945 - acc:0.8216 - val_loss:0.7233 - val_acc:0.8476
Epoch 457/5000
14s 28ms/step - loss:0.7873 - acc:0.8219 - val_loss:0.7322 - val_acc:0.8479
Epoch 458/5000
14s 28ms/step - loss:0.7911 - acc:0.8216 - val_loss:0.7216 - val_acc:0.8473
Epoch 459/5000
14s 28ms/step - loss:0.7859 - acc:0.8239 - val_loss:0.7413 - val_acc:0.8408
Epoch 460/5000
14s 28ms/step - loss:0.7908 - acc:0.8234 - val_loss:0.7384 - val_acc:0.8421
Epoch 461/5000
14s 28ms/step - loss:0.7903 - acc:0.8220 - val_loss:0.7488 - val_acc:0.8379
Epoch 462/5000
14s 28ms/step - loss:0.7907 - acc:0.8207 - val_loss:0.7564 - val_acc:0.8356
Epoch 463/5000
14s 28ms/step - loss:0.7887 - acc:0.8233 - val_loss:0.7222 - val_acc:0.8477
Epoch 464/5000
14s 28ms/step - loss:0.7901 - acc:0.8209 - val_loss:0.7183 - val_acc:0.8469
Epoch 465/5000
14s 28ms/step - loss:0.7875 - acc:0.8222 - val_loss:0.7285 - val_acc:0.8433
Epoch 466/5000
14s 28ms/step - loss:0.7909 - acc:0.8233 - val_loss:0.7222 - val_acc:0.8454
Epoch 467/5000
14s 28ms/step - loss:0.7908 - acc:0.8203 - val_loss:0.7051 - val_acc:0.8548
Epoch 468/5000
14s 28ms/step - loss:0.7864 - acc:0.8235 - val_loss:0.7249 - val_acc:0.8445
Epoch 469/5000
14s 28ms/step - loss:0.7920 - acc:0.8228 - val_loss:0.7553 - val_acc:0.8373
Epoch 470/5000
14s 28ms/step - loss:0.7959 - acc:0.8195 - val_loss:0.7188 - val_acc:0.8507
Epoch 471/5000
14s 28ms/step - loss:0.7868 - acc:0.8243 - val_loss:0.7258 - val_acc:0.8472
Epoch 472/5000
14s 28ms/step - loss:0.7887 - acc:0.8218 - val_loss:0.7247 - val_acc:0.8494
Epoch 473/5000
14s 28ms/step - loss:0.7964 - acc:0.8196 - val_loss:0.7377 - val_acc:0.8425
Epoch 474/5000
14s 28ms/step - loss:0.7911 - acc:0.8215 - val_loss:0.7329 - val_acc:0.8460
Epoch 475/5000
14s 28ms/step - loss:0.7885 - acc:0.8232 - val_loss:0.7323 - val_acc:0.8441
Epoch 476/5000
14s 28ms/step - loss:0.7883 - acc:0.8214 - val_loss:0.7275 - val_acc:0.8470
Epoch 477/5000
14s 28ms/step - loss:0.7927 - acc:0.8211 - val_loss:0.7213 - val_acc:0.8468
Epoch 478/5000
14s 28ms/step - loss:0.7934 - acc:0.8202 - val_loss:0.7472 - val_acc:0.8424
Epoch 479/5000
14s 28ms/step - loss:0.7884 - acc:0.8221 - val_loss:0.7224 - val_acc:0.8495
Epoch 480/5000
14s 28ms/step - loss:0.7911 - acc:0.8218 - val_loss:0.7194 - val_acc:0.8493
Epoch 481/5000
14s 28ms/step - loss:0.7887 - acc:0.8228 - val_loss:0.7405 - val_acc:0.8413
Epoch 482/5000
14s 28ms/step - loss:0.7872 - acc:0.8229 - val_loss:0.7193 - val_acc:0.8468
Epoch 483/5000
14s 28ms/step - loss:0.7890 - acc:0.8224 - val_loss:0.7088 - val_acc:0.8524
Epoch 484/5000
14s 28ms/step - loss:0.7928 - acc:0.8222 - val_loss:0.7363 - val_acc:0.8437
Epoch 485/5000
14s 28ms/step - loss:0.7908 - acc:0.8238 - val_loss:0.7479 - val_acc:0.8398
Epoch 486/5000
14s 28ms/step - loss:0.7902 - acc:0.8220 - val_loss:0.7529 - val_acc:0.8367
Epoch 487/5000
14s 28ms/step - loss:0.7874 - acc:0.8229 - val_loss:0.7374 - val_acc:0.8395
Epoch 488/5000
14s 28ms/step - loss:0.7864 - acc:0.8242 - val_loss:0.7204 - val_acc:0.8461
Epoch 489/5000
14s 28ms/step - loss:0.7881 - acc:0.8236 - val_loss:0.7274 - val_acc:0.8433
Epoch 490/5000
14s 28ms/step - loss:0.7855 - acc:0.8233 - val_loss:0.7439 - val_acc:0.8386
Epoch 491/5000
14s 28ms/step - loss:0.7899 - acc:0.8224 - val_loss:0.7493 - val_acc:0.8353
Epoch 492/5000
14s 28ms/step - loss:0.7900 - acc:0.8215 - val_loss:0.7421 - val_acc:0.8364
Epoch 493/5000
14s 28ms/step - loss:0.7858 - acc:0.8228 - val_loss:0.7262 - val_acc:0.8469
Epoch 494/5000
14s 28ms/step - loss:0.7847 - acc:0.8226 - val_loss:0.7126 - val_acc:0.8469
Epoch 495/5000
14s 28ms/step - loss:0.7911 - acc:0.8192 - val_loss:0.7356 - val_acc:0.8420
Epoch 496/5000
14s 28ms/step - loss:0.7879 - acc:0.8237 - val_loss:0.7354 - val_acc:0.8454
Epoch 497/5000
14s 28ms/step - loss:0.7880 - acc:0.8245 - val_loss:0.7111 - val_acc:0.8521
Epoch 498/5000
14s 28ms/step - loss:0.7895 - acc:0.8208 - val_loss:0.7249 - val_acc:0.8466
Epoch 499/5000
14s 28ms/step - loss:0.7907 - acc:0.8193 - val_loss:0.7279 - val_acc:0.8488
Epoch 500/5000
14s 28ms/step - loss:0.7890 - acc:0.8229 - val_loss:0.7470 - val_acc:0.8376
Epoch 501/5000
14s 28ms/step - loss:0.7889 - acc:0.8207 - val_loss:0.7140 - val_acc:0.8528
Epoch 502/5000
14s 28ms/step - loss:0.7862 - acc:0.8224 - val_loss:0.7495 - val_acc:0.8351
Epoch 503/5000
14s 28ms/step - loss:0.7868 - acc:0.8221 - val_loss:0.7306 - val_acc:0.8431
Epoch 504/5000
15s 29ms/step - loss:0.7828 - acc:0.8234 - val_loss:0.7212 - val_acc:0.8483
Epoch 505/5000
14s 28ms/step - loss:0.7918 - acc:0.8198 - val_loss:0.7266 - val_acc:0.8477
Epoch 506/5000
14s 28ms/step - loss:0.7915 - acc:0.8204 - val_loss:0.7501 - val_acc:0.8382
Epoch 507/5000
14s 28ms/step - loss:0.7832 - acc:0.8238 - val_loss:0.7234 - val_acc:0.8476
Epoch 508/5000
14s 29ms/step - loss:0.7917 - acc:0.8203 - val_loss:0.7229 - val_acc:0.8489
Epoch 509/5000
14s 29ms/step - loss:0.7859 - acc:0.8234 - val_loss:0.7051 - val_acc:0.8556
Epoch 510/5000
14s 29ms/step - loss:0.7839 - acc:0.8234 - val_loss:0.7327 - val_acc:0.8458
Epoch 511/5000
14s 29ms/step - loss:0.7860 - acc:0.8228 - val_loss:0.7295 - val_acc:0.8429
Epoch 512/5000
14s 29ms/step - loss:0.7880 - acc:0.8216 - val_loss:0.7199 - val_acc:0.8515
Epoch 513/5000
14s 29ms/step - loss:0.7864 - acc:0.8238 - val_loss:0.7402 - val_acc:0.8385
Epoch 514/5000
14s 29ms/step - loss:0.7858 - acc:0.8246 - val_loss:0.7485 - val_acc:0.8334
Epoch 515/5000
14s 29ms/step - loss:0.7910 - acc:0.8205 - val_loss:0.7222 - val_acc:0.8496
Epoch 516/5000
14s 29ms/step - loss:0.7879 - acc:0.8218 - val_loss:0.7276 - val_acc:0.8437
Epoch 517/5000
14s 29ms/step - loss:0.7886 - acc:0.8231 - val_loss:0.7160 - val_acc:0.8509
Epoch 518/5000
14s 29ms/step - loss:0.7847 - acc:0.8237 - val_loss:0.7216 - val_acc:0.8469
Epoch 519/5000
14s 29ms/step - loss:0.7872 - acc:0.8209 - val_loss:0.7188 - val_acc:0.8496
Epoch 520/5000
14s 29ms/step - loss:0.7856 - acc:0.8227 - val_loss:0.7323 - val_acc:0.8474
Epoch 521/5000
14s 29ms/step - loss:0.7833 - acc:0.8225 - val_loss:0.7458 - val_acc:0.8410
Epoch 522/5000
14s 29ms/step - loss:0.7816 - acc:0.8243 - val_loss:0.7213 - val_acc:0.8486
Epoch 523/5000
14s 29ms/step - loss:0.7909 - acc:0.8215 - val_loss:0.7266 - val_acc:0.8416
Epoch 524/5000
14s 29ms/step - loss:0.7902 - acc:0.8236 - val_loss:0.7367 - val_acc:0.8418
Epoch 525/5000
14s 29ms/step - loss:0.7882 - acc:0.8212 - val_loss:0.7105 - val_acc:0.8538
Epoch 526/5000
14s 29ms/step - loss:0.7878 - acc:0.8240 - val_loss:0.7232 - val_acc:0.8481
Epoch 527/5000
14s 29ms/step - loss:0.7867 - acc:0.8219 - val_loss:0.7338 - val_acc:0.8444
Epoch 528/5000
14s 29ms/step - loss:0.7873 - acc:0.8218 - val_loss:0.7291 - val_acc:0.8444
Epoch 529/5000
14s 29ms/step - loss:0.7934 - acc:0.8187 - val_loss:0.7549 - val_acc:0.8334
Epoch 530/5000
14s 29ms/step - loss:0.7836 - acc:0.8256 - val_loss:0.7376 - val_acc:0.8456
Epoch 531/5000
14s 29ms/step - loss:0.7883 - acc:0.8208 - val_loss:0.7219 - val_acc:0.8502
Epoch 532/5000
14s 29ms/step - loss:0.7880 - acc:0.8232 - val_loss:0.7381 - val_acc:0.8423
Epoch 533/5000
14s 29ms/step - loss:0.7876 - acc:0.8222 - val_loss:0.7241 - val_acc:0.8463
Epoch 534/5000
14s 29ms/step - loss:0.7872 - acc:0.8246 - val_loss:0.7250 - val_acc:0.8454
Epoch 535/5000
14s 29ms/step - loss:0.7876 - acc:0.8210 - val_loss:0.7289 - val_acc:0.8469
Epoch 536/5000
14s 29ms/step - loss:0.7866 - acc:0.8226 - val_loss:0.7171 - val_acc:0.8471
Epoch 537/5000
14s 28ms/step - loss:0.7824 - acc:0.8233 - val_loss:0.7309 - val_acc:0.8425
Epoch 538/5000
14s 29ms/step - loss:0.7824 - acc:0.8245 - val_loss:0.7448 - val_acc:0.8397
Epoch 539/5000
14s 29ms/step - loss:0.7864 - acc:0.8214 - val_loss:0.7241 - val_acc:0.8436
Epoch 540/5000
14s 29ms/step - loss:0.7864 - acc:0.8214 - val_loss:0.7238 - val_acc:0.8465
Epoch 541/5000
14s 29ms/step - loss:0.7876 - acc:0.8236 - val_loss:0.7355 - val_acc:0.8392
Epoch 542/5000
14s 29ms/step - loss:0.7910 - acc:0.8218 - val_loss:0.7397 - val_acc:0.8424
Epoch 543/5000
14s 29ms/step - loss:0.7837 - acc:0.8232 - val_loss:0.7409 - val_acc:0.8399
Epoch 544/5000
14s 29ms/step - loss:0.7875 - acc:0.8236 - val_loss:0.7401 - val_acc:0.8417
Epoch 545/5000
14s 29ms/step - loss:0.7867 - acc:0.8224 - val_loss:0.7164 - val_acc:0.8531
Epoch 546/5000
14s 29ms/step - loss:0.7890 - acc:0.8225 - val_loss:0.6964 - val_acc:0.8551
Epoch 547/5000
14s 29ms/step - loss:0.7829 - acc:0.8236 - val_loss:0.7346 - val_acc:0.8439
Epoch 548/5000
14s 29ms/step - loss:0.7909 - acc:0.8210 - val_loss:0.7175 - val_acc:0.8491
Epoch 549/5000
14s 29ms/step - loss:0.7831 - acc:0.8232 - val_loss:0.7228 - val_acc:0.8485
Epoch 550/5000
14s 29ms/step - loss:0.7830 - acc:0.8240 - val_loss:0.7257 - val_acc:0.8451
Epoch 551/5000
14s 29ms/step - loss:0.7904 - acc:0.8213 - val_loss:0.7202 - val_acc:0.8476
Epoch 552/5000
14s 29ms/step - loss:0.7867 - acc:0.8238 - val_loss:0.7470 - val_acc:0.8385
Epoch 553/5000
14s 28ms/step - loss:0.7860 - acc:0.8243 - val_loss:0.7103 - val_acc:0.8506
Epoch 554/5000
14s 29ms/step - loss:0.7841 - acc:0.8230 - val_loss:0.7212 - val_acc:0.8504
Epoch 555/5000
14s 29ms/step - loss:0.7869 - acc:0.8228 - val_loss:0.7157 - val_acc:0.8477
Epoch 556/5000
14s 29ms/step - loss:0.7891 - acc:0.8217 - val_loss:0.7359 - val_acc:0.8415
Epoch 557/5000
14s 29ms/step - loss:0.7842 - acc:0.8225 - val_loss:0.7377 - val_acc:0.8412
Epoch 558/5000
14s 29ms/step - loss:0.7878 - acc:0.8214 - val_loss:0.7348 - val_acc:0.8471
Epoch 559/5000
14s 29ms/step - loss:0.7820 - acc:0.8244 - val_loss:0.7293 - val_acc:0.8471
Epoch 560/5000
14s 29ms/step - loss:0.7897 - acc:0.8212 - val_loss:0.7555 - val_acc:0.8381
Epoch 561/5000
14s 29ms/step - loss:0.7839 - acc:0.8244 - val_loss:0.7105 - val_acc:0.8507
Epoch 562/5000
14s 29ms/step - loss:0.7863 - acc:0.8243 - val_loss:0.7182 - val_acc:0.8462
Epoch 563/5000
14s 29ms/step - loss:0.7867 - acc:0.8229 - val_loss:0.7173 - val_acc:0.8520
Epoch 564/5000
14s 28ms/step - loss:0.7843 - acc:0.8224 - val_loss:0.7329 - val_acc:0.8434
Epoch 565/5000
14s 29ms/step - loss:0.7868 - acc:0.8220 - val_loss:0.7076 - val_acc:0.8517
Epoch 566/5000
14s 29ms/step - loss:0.7862 - acc:0.8240 - val_loss:0.7195 - val_acc:0.8464
Epoch 567/5000
14s 29ms/step - loss:0.7841 - acc:0.8215 - val_loss:0.7119 - val_acc:0.8506
Epoch 568/5000
14s 29ms/step - loss:0.7864 - acc:0.8222 - val_loss:0.7070 - val_acc:0.8505
Epoch 569/5000
14s 29ms/step - loss:0.7873 - acc:0.8220 - val_loss:0.7249 - val_acc:0.8456
Epoch 570/5000
14s 29ms/step - loss:0.7846 - acc:0.8230 - val_loss:0.7318 - val_acc:0.8432
Epoch 571/5000
14s 29ms/step - loss:0.7803 - acc:0.8253 - val_loss:0.7491 - val_acc:0.8324
Epoch 572/5000
14s 29ms/step - loss:0.7888 - acc:0.8222 - val_loss:0.7374 - val_acc:0.8389
Epoch 573/5000
14s 29ms/step - loss:0.7863 - acc:0.8237 - val_loss:0.7252 - val_acc:0.8450
Epoch 574/5000
14s 29ms/step - loss:0.7908 - acc:0.8226 - val_loss:0.7231 - val_acc:0.8470
Epoch 575/5000
14s 29ms/step - loss:0.7852 - acc:0.8233 - val_loss:0.7316 - val_acc:0.8433
Epoch 576/5000
14s 29ms/step - loss:0.7847 - acc:0.8232 - val_loss:0.7231 - val_acc:0.8464
Epoch 577/5000
14s 29ms/step - loss:0.7869 - acc:0.8223 - val_loss:0.7538 - val_acc:0.8374
Epoch 578/5000
14s 28ms/step - loss:0.7845 - acc:0.8239 - val_loss:0.7411 - val_acc:0.8378
Epoch 579/5000
14s 29ms/step - loss:0.7869 - acc:0.8216 - val_loss:0.7270 - val_acc:0.8464
Epoch 580/5000
14s 29ms/step - loss:0.7830 - acc:0.8246 - val_loss:0.7010 - val_acc:0.8542
Epoch 581/5000
14s 29ms/step - loss:0.7889 - acc:0.8222 - val_loss:0.7353 - val_acc:0.8437
Epoch 582/5000
14s 29ms/step - loss:0.7835 - acc:0.8240 - val_loss:0.7153 - val_acc:0.8461
Epoch 583/5000
14s 29ms/step - loss:0.7886 - acc:0.8208 - val_loss:0.7357 - val_acc:0.8421
Epoch 584/5000
14s 29ms/step - loss:0.7904 - acc:0.8230 - val_loss:0.7176 - val_acc:0.8446
Epoch 585/5000
14s 29ms/step - loss:0.7861 - acc:0.8230 - val_loss:0.7678 - val_acc:0.8285
Epoch 586/5000
14s 29ms/step - loss:0.7901 - acc:0.8217 - val_loss:0.7487 - val_acc:0.8363
Epoch 587/5000
14s 28ms/step - loss:0.7887 - acc:0.8211 - val_loss:0.7400 - val_acc:0.8426
Epoch 588/5000
14s 29ms/step - loss:0.7829 - acc:0.8234 - val_loss:0.7117 - val_acc:0.8529
Epoch 589/5000
14s 29ms/step - loss:0.7845 - acc:0.8238 - val_loss:0.7595 - val_acc:0.8350
Epoch 590/5000
14s 29ms/step - loss:0.7875 - acc:0.8226 - val_loss:0.7112 - val_acc:0.8499
Epoch 591/5000
14s 29ms/step - loss:0.7838 - acc:0.8233 - val_loss:0.7156 - val_acc:0.8485
Epoch 592/5000
14s 29ms/step - loss:0.7843 - acc:0.8225 - val_loss:0.7237 - val_acc:0.8474
Epoch 593/5000
14s 29ms/step - loss:0.7888 - acc:0.8225 - val_loss:0.7290 - val_acc:0.8455
Epoch 594/5000
14s 29ms/step - loss:0.7876 - acc:0.8233 - val_loss:0.7346 - val_acc:0.8438
Epoch 595/5000
14s 29ms/step - loss:0.7906 - acc:0.8214 - val_loss:0.7223 - val_acc:0.8450
Epoch 596/5000
14s 29ms/step - loss:0.7828 - acc:0.8233 - val_loss:0.7248 - val_acc:0.8466
Epoch 597/5000
14s 29ms/step - loss:0.7805 - acc:0.8251 - val_loss:0.7219 - val_acc:0.8479
Epoch 598/5000
14s 29ms/step - loss:0.7873 - acc:0.8230 - val_loss:0.7362 - val_acc:0.8438
Epoch 599/5000
14s 29ms/step - loss:0.7867 - acc:0.8247 - val_loss:0.7001 - val_acc:0.8563
Epoch 600/5000
14s 29ms/step - loss:0.7870 - acc:0.8247 - val_loss:0.7105 - val_acc:0.8518
Epoch 601/5000
14s 29ms/step - loss:0.7811 - acc:0.8256 - val_loss:0.7327 - val_acc:0.8407
Epoch 602/5000
14s 29ms/step - loss:0.7863 - acc:0.8213 - val_loss:0.7418 - val_acc:0.8377
Epoch 603/5000
14s 29ms/step - loss:0.7815 - acc:0.8256 - val_loss:0.7202 - val_acc:0.8453
Epoch 604/5000
14s 29ms/step - loss:0.7885 - acc:0.8217 - val_loss:0.7289 - val_acc:0.8461
Epoch 605/5000
14s 29ms/step - loss:0.7861 - acc:0.8238 - val_loss:0.7215 - val_acc:0.8449
Epoch 606/5000
14s 29ms/step - loss:0.7815 - acc:0.8248 - val_loss:0.7062 - val_acc:0.8526
Epoch 607/5000
14s 29ms/step - loss:0.7814 - acc:0.8233 - val_loss:0.7171 - val_acc:0.8495
Epoch 608/5000
14s 29ms/step - loss:0.7878 - acc:0.8215 - val_loss:0.7230 - val_acc:0.8442
Epoch 609/5000
14s 29ms/step - loss:0.7821 - acc:0.8244 - val_loss:0.7295 - val_acc:0.8476
Epoch 610/5000
14s 28ms/step - loss:0.7858 - acc:0.8218 - val_loss:0.7366 - val_acc:0.8411
Epoch 611/5000
14s 29ms/step - loss:0.7887 - acc:0.8218 - val_loss:0.7110 - val_acc:0.8499
Epoch 612/5000
14s 29ms/step - loss:0.7917 - acc:0.8206 - val_loss:0.7094 - val_acc:0.8540
Epoch 613/5000
14s 28ms/step - loss:0.7826 - acc:0.8241 - val_loss:0.6942 - val_acc:0.8548
Epoch 614/5000
14s 28ms/step - loss:0.7845 - acc:0.8233 - val_loss:0.7119 - val_acc:0.8496
Epoch 615/5000
14s 28ms/step - loss:0.7824 - acc:0.8249 - val_loss:0.7234 - val_acc:0.8471
Epoch 616/5000
14s 28ms/step - loss:0.7837 - acc:0.8220 - val_loss:0.7226 - val_acc:0.8481
Epoch 617/5000
14s 28ms/step - loss:0.7834 - acc:0.8233 - val_loss:0.7059 - val_acc:0.8516
Epoch 618/5000
14s 28ms/step - loss:0.7806 - acc:0.8244 - val_loss:0.7116 - val_acc:0.8511
Epoch 619/5000
14s 28ms/step - loss:0.7861 - acc:0.8225 - val_loss:0.7207 - val_acc:0.8437
Epoch 620/5000
14s 28ms/step - loss:0.7830 - acc:0.8234 - val_loss:0.7345 - val_acc:0.8428
Epoch 621/5000
14s 28ms/step - loss:0.7830 - acc:0.8232 - val_loss:0.7335 - val_acc:0.8431
Epoch 622/5000
14s 28ms/step - loss:0.7852 - acc:0.8231 - val_loss:0.7109 - val_acc:0.8528
Epoch 623/5000
14s 28ms/step - loss:0.7849 - acc:0.8220 - val_loss:0.7252 - val_acc:0.8443
Epoch 624/5000
14s 28ms/step - loss:0.7858 - acc:0.8227 - val_loss:0.7056 - val_acc:0.8544
Epoch 625/5000
14s 28ms/step - loss:0.7814 - acc:0.8242 - val_loss:0.7218 - val_acc:0.8459
Epoch 626/5000
14s 28ms/step - loss:0.7824 - acc:0.8256 - val_loss:0.7179 - val_acc:0.8509
Epoch 627/5000
14s 28ms/step - loss:0.7840 - acc:0.8230 - val_loss:0.7445 - val_acc:0.8378
Epoch 628/5000
14s 28ms/step - loss:0.7890 - acc:0.8221 - val_loss:0.7291 - val_acc:0.8432
Epoch 629/5000
14s 28ms/step - loss:0.7780 - acc:0.8242 - val_loss:0.7305 - val_acc:0.8440
Epoch 630/5000
14s 28ms/step - loss:0.7870 - acc:0.8220 - val_loss:0.7329 - val_acc:0.8427
Epoch 631/5000
14s 28ms/step - loss:0.7901 - acc:0.8223 - val_loss:0.7152 - val_acc:0.8513
Epoch 632/5000
14s 28ms/step - loss:0.7849 - acc:0.8222 - val_loss:0.7248 - val_acc:0.8465
Epoch 633/5000
14s 28ms/step - loss:0.7769 - acc:0.8270 - val_loss:0.7084 - val_acc:0.8510
Epoch 634/5000
14s 28ms/step - loss:0.7813 - acc:0.8237 - val_loss:0.7297 - val_acc:0.8467
Epoch 635/5000
14s 28ms/step - loss:0.7853 - acc:0.8225 - val_loss:0.7219 - val_acc:0.8479
Epoch 636/5000
14s 28ms/step - loss:0.7814 - acc:0.8251 - val_loss:0.7101 - val_acc:0.8508
Epoch 637/5000
14s 28ms/step - loss:0.7818 - acc:0.8251 - val_loss:0.7232 - val_acc:0.8498
Epoch 638/5000
14s 28ms/step - loss:0.7867 - acc:0.8222 - val_loss:0.7100 - val_acc:0.8483
Epoch 639/5000
14s 28ms/step - loss:0.7847 - acc:0.8233 - val_loss:0.7252 - val_acc:0.8462
Epoch 640/5000
14s 28ms/step - loss:0.7837 - acc:0.8233 - val_loss:0.7194 - val_acc:0.8511
Epoch 641/5000
14s 28ms/step - loss:0.7827 - acc:0.8261 - val_loss:0.7027 - val_acc:0.8563
Epoch 642/5000
14s 28ms/step - loss:0.7886 - acc:0.8207 - val_loss:0.7021 - val_acc:0.8548
Epoch 643/5000
14s 28ms/step - loss:0.7846 - acc:0.8241 - val_loss:0.7164 - val_acc:0.8485
Epoch 644/5000
14s 28ms/step - loss:0.7843 - acc:0.8229 - val_loss:0.7375 - val_acc:0.8416
Epoch 645/5000
14s 28ms/step - loss:0.7842 - acc:0.8238 - val_loss:0.7363 - val_acc:0.8393
Epoch 646/5000
14s 28ms/step - loss:0.7864 - acc:0.8223 - val_loss:0.7321 - val_acc:0.8447
Epoch 647/5000
14s 28ms/step - loss:0.7833 - acc:0.8238 - val_loss:0.7332 - val_acc:0.8405
Epoch 648/5000
14s 28ms/step - loss:0.7840 - acc:0.8238 - val_loss:0.7176 - val_acc:0.8505
Epoch 649/5000
14s 28ms/step - loss:0.7844 - acc:0.8223 - val_loss:0.7175 - val_acc:0.8495
Epoch 650/5000
14s 28ms/step - loss:0.7859 - acc:0.8227 - val_loss:0.7159 - val_acc:0.8492
Epoch 651/5000
14s 28ms/step - loss:0.7808 - acc:0.8239 - val_loss:0.7448 - val_acc:0.8381
Epoch 652/5000
14s 28ms/step - loss:0.7888 - acc:0.8211 - val_loss:0.7015 - val_acc:0.8527
Epoch 653/5000
14s 28ms/step - loss:0.7843 - acc:0.8226 - val_loss:0.7164 - val_acc:0.8480
Epoch 654/5000
14s 28ms/step - loss:0.7878 - acc:0.8222 - val_loss:0.7244 - val_acc:0.8489
Epoch 655/5000
14s 28ms/step - loss:0.7807 - acc:0.8247 - val_loss:0.7388 - val_acc:0.8422
Epoch 656/5000
14s 28ms/step - loss:0.7839 - acc:0.8243 - val_loss:0.7301 - val_acc:0.8442
Epoch 657/5000
14s 28ms/step - loss:0.7864 - acc:0.8222 - val_loss:0.7428 - val_acc:0.8439
Epoch 658/5000
14s 28ms/step - loss:0.7831 - acc:0.8242 - val_loss:0.7397 - val_acc:0.8408
Epoch 659/5000
14s 28ms/step - loss:0.7828 - acc:0.8240 - val_loss:0.7554 - val_acc:0.8364
Epoch 660/5000
14s 28ms/step - loss:0.7836 - acc:0.8240 - val_loss:0.7063 - val_acc:0.8538
Epoch 661/5000
14s 28ms/step - loss:0.7853 - acc:0.8210 - val_loss:0.7164 - val_acc:0.8522
Epoch 662/5000
14s 28ms/step - loss:0.7871 - acc:0.8239 - val_loss:0.7089 - val_acc:0.8512
Epoch 663/5000
14s 28ms/step - loss:0.7820 - acc:0.8253 - val_loss:0.7228 - val_acc:0.8448
Epoch 664/5000
14s 28ms/step - loss:0.7860 - acc:0.8217 - val_loss:0.7503 - val_acc:0.8356
Epoch 665/5000
14s 28ms/step - loss:0.7856 - acc:0.8221 - val_loss:0.7177 - val_acc:0.8482
Epoch 666/5000
14s 28ms/step - loss:0.7898 - acc:0.8220 - val_loss:0.7208 - val_acc:0.8463
Epoch 667/5000
14s 28ms/step - loss:0.7865 - acc:0.8222 - val_loss:0.7238 - val_acc:0.8484
Epoch 668/5000
14s 28ms/step - loss:0.7913 - acc:0.8210 - val_loss:0.7344 - val_acc:0.8414
Epoch 669/5000
14s 28ms/step - loss:0.7824 - acc:0.8254 - val_loss:0.7163 - val_acc:0.8474
Epoch 670/5000
14s 28ms/step - loss:0.7866 - acc:0.8208 - val_loss:0.7318 - val_acc:0.8441
Epoch 671/5000
14s 28ms/step - loss:0.7810 - acc:0.8242 - val_loss:0.7266 - val_acc:0.8476
Epoch 672/5000
14s 28ms/step - loss:0.7830 - acc:0.8246 - val_loss:0.7050 - val_acc:0.8528
Epoch 673/5000
14s 28ms/step - loss:0.7841 - acc:0.8238 - val_loss:0.7006 - val_acc:0.8517
Epoch 674/5000
14s 28ms/step - loss:0.7843 - acc:0.8228 - val_loss:0.7250 - val_acc:0.8458
Epoch 675/5000
14s 28ms/step - loss:0.7842 - acc:0.8240 - val_loss:0.7231 - val_acc:0.8437
Epoch 676/5000
14s 28ms/step - loss:0.7862 - acc:0.8234 - val_loss:0.7340 - val_acc:0.8441
Epoch 677/5000
14s 28ms/step - loss:0.7839 - acc:0.8245 - val_loss:0.7236 - val_acc:0.8447
Epoch 678/5000
14s 28ms/step - loss:0.7893 - acc:0.8220 - val_loss:0.7145 - val_acc:0.8514
Epoch 679/5000
14s 28ms/step - loss:0.7849 - acc:0.8234 - val_loss:0.7144 - val_acc:0.8514
Epoch 680/5000
14s 28ms/step - loss:0.7807 - acc:0.8218 - val_loss:0.7195 - val_acc:0.8491
Epoch 681/5000
14s 28ms/step - loss:0.7786 - acc:0.8243 - val_loss:0.7352 - val_acc:0.8447
Epoch 682/5000
14s 28ms/step - loss:0.7866 - acc:0.8234 - val_loss:0.7361 - val_acc:0.8437
Epoch 683/5000
14s 28ms/step - loss:0.7787 - acc:0.8233 - val_loss:0.7347 - val_acc:0.8415
Epoch 684/5000
14s 28ms/step - loss:0.7800 - acc:0.8253 - val_loss:0.7076 - val_acc:0.8515
Epoch 685/5000
14s 28ms/step - loss:0.7853 - acc:0.8238 - val_loss:0.7299 - val_acc:0.8437
Epoch 686/5000
14s 28ms/step - loss:0.7860 - acc:0.8248 - val_loss:0.7174 - val_acc:0.8471
Epoch 687/5000
14s 28ms/step - loss:0.7875 - acc:0.8234 - val_loss:0.7084 - val_acc:0.8462
Epoch 688/5000
14s 28ms/step - loss:0.7816 - acc:0.8230 - val_loss:0.7142 - val_acc:0.8494
Epoch 689/5000
14s 28ms/step - loss:0.7854 - acc:0.8235 - val_loss:0.7362 - val_acc:0.8455
Epoch 690/5000
14s 28ms/step - loss:0.7836 - acc:0.8250 - val_loss:0.7111 - val_acc:0.8532
Epoch 691/5000
14s 28ms/step - loss:0.7859 - acc:0.8240 - val_loss:0.7599 - val_acc:0.8316
Epoch 692/5000
14s 28ms/step - loss:0.7847 - acc:0.8235 - val_loss:0.7387 - val_acc:0.8427
Epoch 693/5000
14s 28ms/step - loss:0.7831 - acc:0.8248 - val_loss:0.7239 - val_acc:0.8452
Epoch 694/5000
14s 28ms/step - loss:0.7805 - acc:0.8218 - val_loss:0.7169 - val_acc:0.8499
Epoch 695/5000
14s 28ms/step - loss:0.7820 - acc:0.8238 - val_loss:0.7301 - val_acc:0.8437
Epoch 696/5000
14s 28ms/step - loss:0.7831 - acc:0.8256 - val_loss:0.7250 - val_acc:0.8424
Epoch 697/5000
14s 28ms/step - loss:0.7840 - acc:0.8228 - val_loss:0.7416 - val_acc:0.8417
Epoch 698/5000
14s 28ms/step - loss:0.7852 - acc:0.8232 - val_loss:0.7391 - val_acc:0.8396
Epoch 699/5000
14s 28ms/step - loss:0.7831 - acc:0.8246 - val_loss:0.7284 - val_acc:0.8469
Epoch 700/5000
14s 28ms/step - loss:0.7797 - acc:0.8249 - val_loss:0.7227 - val_acc:0.8468
Epoch 701/5000
14s 28ms/step - loss:0.7816 - acc:0.8238 - val_loss:0.7284 - val_acc:0.8418
Epoch 702/5000
14s 28ms/step - loss:0.7856 - acc:0.8229 - val_loss:0.7172 - val_acc:0.8469
Epoch 703/5000
14s 28ms/step - loss:0.7823 - acc:0.8253 - val_loss:0.7016 - val_acc:0.8549
Epoch 704/5000
14s 28ms/step - loss:0.7801 - acc:0.8259 - val_loss:0.7564 - val_acc:0.8362
Epoch 705/5000
14s 28ms/step - loss:0.7858 - acc:0.8226 - val_loss:0.7202 - val_acc:0.8454
Epoch 706/5000
14s 28ms/step - loss:0.7823 - acc:0.8255 - val_loss:0.7226 - val_acc:0.8469
Epoch 707/5000
14s 28ms/step - loss:0.7797 - acc:0.8245 - val_loss:0.7329 - val_acc:0.8442
Epoch 708/5000
14s 28ms/step - loss:0.7866 - acc:0.8224 - val_loss:0.7066 - val_acc:0.8508
Epoch 709/5000
14s 28ms/step - loss:0.7784 - acc:0.8245 - val_loss:0.7156 - val_acc:0.8503
Epoch 710/5000
14s 28ms/step - loss:0.7797 - acc:0.8247 - val_loss:0.7305 - val_acc:0.8414
Epoch 711/5000
14s 28ms/step - loss:0.7799 - acc:0.8251 - val_loss:0.7333 - val_acc:0.8458
Epoch 712/5000
14s 28ms/step - loss:0.7853 - acc:0.8232 - val_loss:0.7375 - val_acc:0.8406
Epoch 713/5000
14s 28ms/step - loss:0.7805 - acc:0.8243 - val_loss:0.7154 - val_acc:0.8489
Epoch 714/5000
14s 28ms/step - loss:0.7811 - acc:0.8248 - val_loss:0.7180 - val_acc:0.8473
Epoch 715/5000
14s 28ms/step - loss:0.7838 - acc:0.8214 - val_loss:0.7283 - val_acc:0.8463
Epoch 716/5000
14s 28ms/step - loss:0.7815 - acc:0.8253 - val_loss:0.7445 - val_acc:0.8424
Epoch 717/5000
14s 28ms/step - loss:0.7851 - acc:0.8224 - val_loss:0.7114 - val_acc:0.8569
Epoch 718/5000
14s 28ms/step - loss:0.7833 - acc:0.8236 - val_loss:0.7333 - val_acc:0.8413
Epoch 719/5000
14s 28ms/step - loss:0.7847 - acc:0.8235 - val_loss:0.7156 - val_acc:0.8488
Epoch 720/5000
14s 28ms/step - loss:0.7847 - acc:0.8222 - val_loss:0.7342 - val_acc:0.8432
Epoch 721/5000
14s 28ms/step - loss:0.7853 - acc:0.8230 - val_loss:0.7261 - val_acc:0.8445
Epoch 722/5000
14s 28ms/step - loss:0.7820 - acc:0.8243 - val_loss:0.7328 - val_acc:0.8436
Epoch 723/5000
14s 28ms/step - loss:0.7782 - acc:0.8252 - val_loss:0.7123 - val_acc:0.8487
Epoch 724/5000
14s 28ms/step - loss:0.7834 - acc:0.8226 - val_loss:0.7240 - val_acc:0.8473
Epoch 725/5000
14s 28ms/step - loss:0.7828 - acc:0.8236 - val_loss:0.7346 - val_acc:0.8440
Epoch 726/5000
14s 28ms/step - loss:0.7809 - acc:0.8264 - val_loss:0.7216 - val_acc:0.8455
Epoch 727/5000
14s 29ms/step - loss:0.7836 - acc:0.8224 - val_loss:0.7294 - val_acc:0.8433
Epoch 728/5000
14s 28ms/step - loss:0.7844 - acc:0.8240 - val_loss:0.7086 - val_acc:0.8495
Epoch 729/5000
14s 28ms/step - loss:0.7763 - acc:0.8269 - val_loss:0.7415 - val_acc:0.8377
Epoch 730/5000
14s 28ms/step - loss:0.7855 - acc:0.8240 - val_loss:0.7218 - val_acc:0.8490
Epoch 731/5000
14s 28ms/step - loss:0.7839 - acc:0.8228 - val_loss:0.7271 - val_acc:0.8484
Epoch 732/5000
14s 28ms/step - loss:0.7801 - acc:0.8247 - val_loss:0.7131 - val_acc:0.8511
Epoch 733/5000
14s 28ms/step - loss:0.7848 - acc:0.8245 - val_loss:0.7158 - val_acc:0.8489
Epoch 734/5000
14s 28ms/step - loss:0.7857 - acc:0.8222 - val_loss:0.7256 - val_acc:0.8494
Epoch 735/5000
14s 28ms/step - loss:0.7837 - acc:0.8224 - val_loss:0.7269 - val_acc:0.8425
Epoch 736/5000
14s 28ms/step - loss:0.7813 - acc:0.8246 - val_loss:0.7387 - val_acc:0.8391
Epoch 737/5000
14s 28ms/step - loss:0.7838 - acc:0.8232 - val_loss:0.7271 - val_acc:0.8420
Epoch 738/5000
14s 28ms/step - loss:0.7823 - acc:0.8251 - val_loss:0.7336 - val_acc:0.8439
Epoch 739/5000
14s 28ms/step - loss:0.7883 - acc:0.8225 - val_loss:0.7112 - val_acc:0.8510
Epoch 740/5000
14s 28ms/step - loss:0.7852 - acc:0.8224 - val_loss:0.7089 - val_acc:0.8508
Epoch 741/5000
14s 28ms/step - loss:0.7837 - acc:0.8233 - val_loss:0.7316 - val_acc:0.8441
Epoch 742/5000
14s 28ms/step - loss:0.7879 - acc:0.8235 - val_loss:0.7358 - val_acc:0.8455
Epoch 743/5000
14s 28ms/step - loss:0.7857 - acc:0.8222 - val_loss:0.7181 - val_acc:0.8485
Epoch 744/5000
14s 28ms/step - loss:0.7803 - acc:0.8243 - val_loss:0.7073 - val_acc:0.8544
Epoch 745/5000
14s 28ms/step - loss:0.7833 - acc:0.8247 - val_loss:0.7098 - val_acc:0.8492
Epoch 746/5000
14s 28ms/step - loss:0.7794 - acc:0.8234 - val_loss:0.7003 - val_acc:0.8547
Epoch 747/5000
14s 28ms/step - loss:0.7825 - acc:0.8222 - val_loss:0.7412 - val_acc:0.8404
Epoch 748/5000
14s 28ms/step - loss:0.7821 - acc:0.8257 - val_loss:0.7185 - val_acc:0.8493
Epoch 749/5000
14s 28ms/step - loss:0.7815 - acc:0.8246 - val_loss:0.7386 - val_acc:0.8424
Epoch 750/5000
14s 28ms/step - loss:0.7802 - acc:0.8258 - val_loss:0.7081 - val_acc:0.8514
Epoch 751/5000
14s 28ms/step - loss:0.7848 - acc:0.8226 - val_loss:0.7197 - val_acc:0.8472
Epoch 752/5000
14s 28ms/step - loss:0.7822 - acc:0.8255 - val_loss:0.7303 - val_acc:0.8454
Epoch 753/5000
14s 28ms/step - loss:0.7840 - acc:0.8228 - val_loss:0.7244 - val_acc:0.8437
Epoch 754/5000
14s 28ms/step - loss:0.7876 - acc:0.8216 - val_loss:0.7130 - val_acc:0.8487
Epoch 755/5000
14s 28ms/step - loss:0.7851 - acc:0.8223 - val_loss:0.7112 - val_acc:0.8515
Epoch 756/5000
14s 28ms/step - loss:0.7815 - acc:0.8253 - val_loss:0.7193 - val_acc:0.8524
Epoch 757/5000
14s 28ms/step - loss:0.7819 - acc:0.8242 - val_loss:0.7013 - val_acc:0.8551
Epoch 758/5000
14s 28ms/step - loss:0.7878 - acc:0.8202 - val_loss:0.7089 - val_acc:0.8497
Epoch 759/5000
14s 28ms/step - loss:0.7831 - acc:0.8222 - val_loss:0.7246 - val_acc:0.8442
Epoch 760/5000
14s 28ms/step - loss:0.7892 - acc:0.8210 - val_loss:0.7071 - val_acc:0.8516
Epoch 761/5000
14s 28ms/step - loss:0.7841 - acc:0.8234 - val_loss:0.7316 - val_acc:0.8433
Epoch 762/5000
14s 28ms/step - loss:0.7831 - acc:0.8234 - val_loss:0.7339 - val_acc:0.8411
Epoch 763/5000
14s 28ms/step - loss:0.7804 - acc:0.8240 - val_loss:0.7551 - val_acc:0.8328
Epoch 764/5000
14s 28ms/step - loss:0.7903 - acc:0.8215 - val_loss:0.7129 - val_acc:0.8507
Epoch 765/5000
14s 28ms/step - loss:0.7812 - acc:0.8241 - val_loss:0.7170 - val_acc:0.8483
Epoch 766/5000
14s 28ms/step - loss:0.7829 - acc:0.8227 - val_loss:0.7177 - val_acc:0.8476
Epoch 767/5000
14s 28ms/step - loss:0.7811 - acc:0.8251 - val_loss:0.7173 - val_acc:0.8526
Epoch 768/5000
14s 28ms/step - loss:0.7806 - acc:0.8252 - val_loss:0.7297 - val_acc:0.8457
Epoch 769/5000
14s 28ms/step - loss:0.7792 - acc:0.8247 - val_loss:0.7204 - val_acc:0.8475
Epoch 770/5000
14s 28ms/step - loss:0.7893 - acc:0.8204 - val_loss:0.7083 - val_acc:0.8540
Epoch 771/5000
14s 28ms/step - loss:0.7832 - acc:0.8246 - val_loss:0.7318 - val_acc:0.8437
Epoch 772/5000
14s 28ms/step - loss:0.7831 - acc:0.8239 - val_loss:0.7283 - val_acc:0.8481
Epoch 773/5000
14s 28ms/step - loss:0.7847 - acc:0.8220 - val_loss:0.7225 - val_acc:0.8482
Epoch 774/5000
14s 28ms/step - loss:0.7766 - acc:0.8246 - val_loss:0.7225 - val_acc:0.8454
Epoch 775/5000
14s 28ms/step - loss:0.7832 - acc:0.8248 - val_loss:0.7137 - val_acc:0.8502
Epoch 776/5000
14s 28ms/step - loss:0.7778 - acc:0.8228 - val_loss:0.7212 - val_acc:0.8467
Epoch 777/5000
14s 28ms/step - loss:0.7782 - acc:0.8244 - val_loss:0.7470 - val_acc:0.8395
Epoch 778/5000
14s 28ms/step - loss:0.7806 - acc:0.8254 - val_loss:0.7177 - val_acc:0.8476
Epoch 779/5000
14s 28ms/step - loss:0.7839 - acc:0.8252 - val_loss:0.7398 - val_acc:0.8406
Epoch 780/5000
14s 28ms/step - loss:0.7834 - acc:0.8249 - val_loss:0.7253 - val_acc:0.8429
Epoch 781/5000
14s 28ms/step - loss:0.7815 - acc:0.8234 - val_loss:0.7426 - val_acc:0.8399
Epoch 782/5000
14s 28ms/step - loss:0.7802 - acc:0.8246 - val_loss:0.6874 - val_acc:0.8599
Epoch 783/5000
14s 28ms/step - loss:0.7774 - acc:0.8257 - val_loss:0.7227 - val_acc:0.8448
Epoch 784/5000
14s 28ms/step - loss:0.7809 - acc:0.8248 - val_loss:0.7142 - val_acc:0.8524
Epoch 785/5000
14s 28ms/step - loss:0.7837 - acc:0.8240 - val_loss:0.7227 - val_acc:0.8454
Epoch 786/5000
14s 28ms/step - loss:0.7819 - acc:0.8239 - val_loss:0.7005 - val_acc:0.8533
Epoch 787/5000
14s 28ms/step - loss:0.7764 - acc:0.8267 - val_loss:0.7127 - val_acc:0.8516
Epoch 788/5000
14s 28ms/step - loss:0.7845 - acc:0.8236 - val_loss:0.7140 - val_acc:0.8466
Epoch 789/5000
14s 28ms/step - loss:0.7874 - acc:0.8224 - val_loss:0.7294 - val_acc:0.8432
Epoch 790/5000
14s 28ms/step - loss:0.7804 - acc:0.8246 - val_loss:0.7202 - val_acc:0.8457
Epoch 791/5000
14s 28ms/step - loss:0.7788 - acc:0.8250 - val_loss:0.7000 - val_acc:0.8514
Epoch 792/5000
14s 28ms/step - loss:0.7833 - acc:0.8227 - val_loss:0.7244 - val_acc:0.8460
Epoch 793/5000
14s 28ms/step - loss:0.7792 - acc:0.8252 - val_loss:0.7233 - val_acc:0.8484
Epoch 794/5000
14s 28ms/step - loss:0.7741 - acc:0.8259 - val_loss:0.7221 - val_acc:0.8484
Epoch 795/5000
14s 28ms/step - loss:0.7801 - acc:0.8245 - val_loss:0.7174 - val_acc:0.8518
Epoch 796/5000
14s 28ms/step - loss:0.7803 - acc:0.8260 - val_loss:0.7172 - val_acc:0.8499
Epoch 797/5000
14s 28ms/step - loss:0.7811 - acc:0.8234 - val_loss:0.7316 - val_acc:0.8468
Epoch 798/5000
14s 28ms/step - loss:0.7838 - acc:0.8235 - val_loss:0.7206 - val_acc:0.8448
Epoch 799/5000
14s 28ms/step - loss:0.7803 - acc:0.8237 - val_loss:0.7139 - val_acc:0.8509
Epoch 800/5000
14s 28ms/step - loss:0.7806 - acc:0.8239 - val_loss:0.7115 - val_acc:0.8491
Epoch 801/5000
14s 28ms/step - loss:0.7788 - acc:0.8257 - val_loss:0.7374 - val_acc:0.8385
Epoch 802/5000
14s 28ms/step - loss:0.7828 - acc:0.8241 - val_loss:0.7166 - val_acc:0.8526
Epoch 803/5000
14s 28ms/step - loss:0.7870 - acc:0.8208 - val_loss:0.7066 - val_acc:0.8491
Epoch 804/5000
14s 28ms/step - loss:0.7838 - acc:0.8248 - val_loss:0.7172 - val_acc:0.8477
Epoch 805/5000
14s 28ms/step - loss:0.7816 - acc:0.8237 - val_loss:0.7226 - val_acc:0.8497
Epoch 806/5000
14s 28ms/step - loss:0.7777 - acc:0.8242 - val_loss:0.7323 - val_acc:0.8410
Epoch 807/5000
14s 28ms/step - loss:0.7771 - acc:0.8245 - val_loss:0.7329 - val_acc:0.8443
Epoch 808/5000
14s 28ms/step - loss:0.7825 - acc:0.8244 - val_loss:0.7174 - val_acc:0.8462
Epoch 809/5000
14s 28ms/step - loss:0.7783 - acc:0.8251 - val_loss:0.7005 - val_acc:0.8534
Epoch 810/5000
14s 28ms/step - loss:0.7828 - acc:0.8244 - val_loss:0.7229 - val_acc:0.8474
Epoch 811/5000
14s 28ms/step - loss:0.7804 - acc:0.8242 - val_loss:0.7527 - val_acc:0.8373
Epoch 812/5000
14s 28ms/step - loss:0.7861 - acc:0.8230 - val_loss:0.7435 - val_acc:0.8425
Epoch 813/5000
14s 28ms/step - loss:0.7795 - acc:0.8236 - val_loss:0.7270 - val_acc:0.8464
Epoch 814/5000
14s 28ms/step - loss:0.7807 - acc:0.8229 - val_loss:0.7087 - val_acc:0.8525
Epoch 815/5000
14s 28ms/step - loss:0.7810 - acc:0.8242 - val_loss:0.7209 - val_acc:0.8492
Epoch 816/5000
14s 28ms/step - loss:0.7826 - acc:0.8240 - val_loss:0.7426 - val_acc:0.8409
Epoch 817/5000
14s 28ms/step - loss:0.7763 - acc:0.8243 - val_loss:0.7202 - val_acc:0.8462
Epoch 818/5000
14s 28ms/step - loss:0.7841 - acc:0.8246 - val_loss:0.7022 - val_acc:0.8530
Epoch 819/5000
14s 28ms/step - loss:0.7787 - acc:0.8252 - val_loss:0.7151 - val_acc:0.8481
Epoch 820/5000
14s 28ms/step - loss:0.7792 - acc:0.8244 - val_loss:0.7048 - val_acc:0.8545
Epoch 821/5000
14s 28ms/step - loss:0.7834 - acc:0.8231 - val_loss:0.7229 - val_acc:0.8458
Epoch 822/5000
14s 28ms/step - loss:0.7774 - acc:0.8260 - val_loss:0.7032 - val_acc:0.8534
Epoch 823/5000
14s 28ms/step - loss:0.7768 - acc:0.8285 - val_loss:0.7006 - val_acc:0.8538
Epoch 824/5000
14s 28ms/step - loss:0.7765 - acc:0.8265 - val_loss:0.7072 - val_acc:0.8521
Epoch 825/5000
14s 28ms/step - loss:0.7805 - acc:0.8233 - val_loss:0.7227 - val_acc:0.8474
Epoch 826/5000
14s 28ms/step - loss:0.7779 - acc:0.8256 - val_loss:0.7080 - val_acc:0.8503
Epoch 827/5000
14s 28ms/step - loss:0.7800 - acc:0.8241 - val_loss:0.7094 - val_acc:0.8480
Epoch 828/5000
14s 28ms/step - loss:0.7796 - acc:0.8236 - val_loss:0.7105 - val_acc:0.8499
Epoch 829/5000
14s 28ms/step - loss:0.7782 - acc:0.8246 - val_loss:0.7168 - val_acc:0.8464
Epoch 830/5000
14s 28ms/step - loss:0.7806 - acc:0.8233 - val_loss:0.7130 - val_acc:0.8471
Epoch 831/5000
14s 28ms/step - loss:0.7784 - acc:0.8242 - val_loss:0.7091 - val_acc:0.8464
Epoch 832/5000
14s 28ms/step - loss:0.7839 - acc:0.8239 - val_loss:0.7287 - val_acc:0.8429
Epoch 833/5000
14s 28ms/step - loss:0.7779 - acc:0.8259 - val_loss:0.7162 - val_acc:0.8485
Epoch 834/5000
14s 28ms/step - loss:0.7814 - acc:0.8255 - val_loss:0.7113 - val_acc:0.8481
Epoch 835/5000
14s 28ms/step - loss:0.7797 - acc:0.8249 - val_loss:0.7283 - val_acc:0.8447
Epoch 836/5000
14s 28ms/step - loss:0.7860 - acc:0.8239 - val_loss:0.7272 - val_acc:0.8399
Epoch 837/5000
14s 28ms/step - loss:0.7809 - acc:0.8228 - val_loss:0.7195 - val_acc:0.8448
Epoch 838/5000
14s 28ms/step - loss:0.7773 - acc:0.8238 - val_loss:0.7253 - val_acc:0.8416
Epoch 839/5000
14s 28ms/step - loss:0.7824 - acc:0.8253 - val_loss:0.7327 - val_acc:0.8461
Epoch 840/5000
14s 28ms/step - loss:0.7765 - acc:0.8258 - val_loss:0.7081 - val_acc:0.8485
Epoch 841/5000
14s 28ms/step - loss:0.7802 - acc:0.8243 - val_loss:0.7072 - val_acc:0.8497
Epoch 842/5000
14s 28ms/step - loss:0.7830 - acc:0.8221 - val_loss:0.7185 - val_acc:0.8489
Epoch 843/5000
14s 28ms/step - loss:0.7797 - acc:0.8243 - val_loss:0.7171 - val_acc:0.8488
Epoch 844/5000
14s 28ms/step - loss:0.7801 - acc:0.8244 - val_loss:0.7162 - val_acc:0.8472
Epoch 845/5000
14s 28ms/step - loss:0.7801 - acc:0.8238 - val_loss:0.7266 - val_acc:0.8437
Epoch 846/5000
14s 28ms/step - loss:0.7795 - acc:0.8260 - val_loss:0.7141 - val_acc:0.8452
Epoch 847/5000
14s 28ms/step - loss:0.7825 - acc:0.8233 - val_loss:0.7494 - val_acc:0.8373
Epoch 848/5000
14s 28ms/step - loss:0.7818 - acc:0.8231 - val_loss:0.7374 - val_acc:0.8453
Epoch 849/5000
14s 28ms/step - loss:0.7832 - acc:0.8234 - val_loss:0.7021 - val_acc:0.8535
Epoch 850/5000
14s 28ms/step - loss:0.7826 - acc:0.8231 - val_loss:0.7120 - val_acc:0.8495
Epoch 851/5000
14s 28ms/step - loss:0.7858 - acc:0.8228 - val_loss:0.7365 - val_acc:0.8417
Epoch 852/5000
14s 28ms/step - loss:0.7834 - acc:0.8234 - val_loss:0.7074 - val_acc:0.8555
Epoch 853/5000
14s 28ms/step - loss:0.7841 - acc:0.8229 - val_loss:0.7089 - val_acc:0.8523
Epoch 854/5000
14s 28ms/step - loss:0.7810 - acc:0.8222 - val_loss:0.7109 - val_acc:0.8525
Epoch 855/5000
14s 28ms/step - loss:0.7758 - acc:0.8269 - val_loss:0.7126 - val_acc:0.8486
Epoch 856/5000
14s 28ms/step - loss:0.7869 - acc:0.8235 - val_loss:0.7143 - val_acc:0.8475
Epoch 857/5000
14s 28ms/step - loss:0.7773 - acc:0.8251 - val_loss:0.6890 - val_acc:0.8624
Epoch 858/5000
14s 28ms/step - loss:0.7847 - acc:0.8225 - val_loss:0.7095 - val_acc:0.8526
Epoch 859/5000
14s 28ms/step - loss:0.7844 - acc:0.8246 - val_loss:0.7208 - val_acc:0.8506
Epoch 860/5000
14s 28ms/step - loss:0.7820 - acc:0.8249 - val_loss:0.7156 - val_acc:0.8440
Epoch 861/5000
14s 28ms/step - loss:0.7761 - acc:0.8252 - val_loss:0.7047 - val_acc:0.8493
Epoch 862/5000
14s 28ms/step - loss:0.7827 - acc:0.8228 - val_loss:0.6973 - val_acc:0.8560
Epoch 863/5000
14s 28ms/step - loss:0.7832 - acc:0.8227 - val_loss:0.7305 - val_acc:0.8465
Epoch 864/5000
14s 28ms/step - loss:0.7874 - acc:0.8219 - val_loss:0.7195 - val_acc:0.8482
Epoch 865/5000
14s 28ms/step - loss:0.7773 - acc:0.8240 - val_loss:0.6973 - val_acc:0.8539
Epoch 866/5000
14s 28ms/step - loss:0.7804 - acc:0.8232 - val_loss:0.7176 - val_acc:0.8470
Epoch 867/5000
14s 28ms/step - loss:0.7847 - acc:0.8230 - val_loss:0.7182 - val_acc:0.8496
Epoch 868/5000
14s 28ms/step - loss:0.7797 - acc:0.8230 - val_loss:0.7030 - val_acc:0.8497
Epoch 869/5000
14s 28ms/step - loss:0.7821 - acc:0.8227 - val_loss:0.7124 - val_acc:0.8506
Epoch 870/5000
14s 28ms/step - loss:0.7804 - acc:0.8247 - val_loss:0.7173 - val_acc:0.8465
Epoch 871/5000
14s 28ms/step - loss:0.7797 - acc:0.8246 - val_loss:0.7341 - val_acc:0.8417
Epoch 872/5000
14s 28ms/step - loss:0.7821 - acc:0.8256 - val_loss:0.7237 - val_acc:0.8469
Epoch 873/5000
14s 28ms/step - loss:0.7762 - acc:0.8260 - val_loss:0.7080 - val_acc:0.8503
Epoch 874/5000
14s 28ms/step - loss:0.7849 - acc:0.8229 - val_loss:0.7202 - val_acc:0.8450
Epoch 875/5000
14s 28ms/step - loss:0.7809 - acc:0.8263 - val_loss:0.7264 - val_acc:0.8504
Epoch 876/5000
14s 28ms/step - loss:0.7810 - acc:0.8239 - val_loss:0.7219 - val_acc:0.8499
Epoch 877/5000
14s 28ms/step - loss:0.7803 - acc:0.8240 - val_loss:0.7327 - val_acc:0.8421
Epoch 878/5000
14s 28ms/step - loss:0.7800 - acc:0.8250 - val_loss:0.7104 - val_acc:0.8508
Epoch 879/5000
14s 28ms/step - loss:0.7804 - acc:0.8250 - val_loss:0.7094 - val_acc:0.8508
Epoch 880/5000
14s 28ms/step - loss:0.7850 - acc:0.8223 - val_loss:0.7199 - val_acc:0.8519
Epoch 881/5000
14s 28ms/step - loss:0.7810 - acc:0.8252 - val_loss:0.7030 - val_acc:0.8562
Epoch 882/5000
14s 28ms/step - loss:0.7782 - acc:0.8259 - val_loss:0.7353 - val_acc:0.8411
Epoch 883/5000
14s 28ms/step - loss:0.7773 - acc:0.8265 - val_loss:0.6957 - val_acc:0.8559
Epoch 884/5000
14s 28ms/step - loss:0.7799 - acc:0.8237 - val_loss:0.7225 - val_acc:0.8471
Epoch 885/5000
14s 28ms/step - loss:0.7769 - acc:0.8262 - val_loss:0.7133 - val_acc:0.8527
Epoch 886/5000
14s 28ms/step - loss:0.7843 - acc:0.8240 - val_loss:0.7235 - val_acc:0.8465
Epoch 887/5000
14s 28ms/step - loss:0.7773 - acc:0.8268 - val_loss:0.7314 - val_acc:0.8444
Epoch 888/5000
14s 28ms/step - loss:0.7817 - acc:0.8246 - val_loss:0.7176 - val_acc:0.8507
Epoch 889/5000
14s 28ms/step - loss:0.7822 - acc:0.8242 - val_loss:0.7156 - val_acc:0.8492
Epoch 890/5000
14s 28ms/step - loss:0.7752 - acc:0.8253 - val_loss:0.7359 - val_acc:0.8421
Epoch 891/5000
14s 28ms/step - loss:0.7781 - acc:0.8258 - val_loss:0.7158 - val_acc:0.8493
Epoch 892/5000
14s 28ms/step - loss:0.7846 - acc:0.8216 - val_loss:0.7205 - val_acc:0.8487
Epoch 893/5000
14s 28ms/step - loss:0.7845 - acc:0.8219 - val_loss:0.6983 - val_acc:0.8532
Epoch 894/5000
14s 28ms/step - loss:0.7838 - acc:0.8248 - val_loss:0.7096 - val_acc:0.8520
Epoch 895/5000
14s 28ms/step - loss:0.7798 - acc:0.8243 - val_loss:0.7106 - val_acc:0.8537
Epoch 896/5000
14s 28ms/step - loss:0.7801 - acc:0.8242 - val_loss:0.7180 - val_acc:0.8467
Epoch 897/5000
14s 28ms/step - loss:0.7794 - acc:0.8237 - val_loss:0.7227 - val_acc:0.8476
Epoch 898/5000
14s 28ms/step - loss:0.7789 - acc:0.8239 - val_loss:0.7105 - val_acc:0.8513
Epoch 899/5000
14s 28ms/step - loss:0.7794 - acc:0.8241 - val_loss:0.7178 - val_acc:0.8511
Epoch 900/5000
14s 28ms/step - loss:0.7776 - acc:0.8250 - val_loss:0.7270 - val_acc:0.8480
Epoch 901/5000
14s 28ms/step - loss:0.7824 - acc:0.8226 - val_loss:0.7174 - val_acc:0.8452
Epoch 902/5000
14s 28ms/step - loss:0.7822 - acc:0.8237 - val_loss:0.6972 - val_acc:0.8520
Epoch 903/5000
14s 28ms/step - loss:0.7742 - acc:0.8251 - val_loss:0.7054 - val_acc:0.8521
Epoch 904/5000
14s 28ms/step - loss:0.7781 - acc:0.8244 - val_loss:0.7166 - val_acc:0.8510
Epoch 905/5000
14s 28ms/step - loss:0.7801 - acc:0.8235 - val_loss:0.7097 - val_acc:0.8490
Epoch 906/5000
14s 28ms/step - loss:0.7778 - acc:0.8253 - val_loss:0.7309 - val_acc:0.8442
Epoch 907/5000
14s 28ms/step - loss:0.7814 - acc:0.8254 - val_loss:0.7039 - val_acc:0.8514
Epoch 908/5000
14s 28ms/step - loss:0.7799 - acc:0.8246 - val_loss:0.7347 - val_acc:0.8395
Epoch 909/5000
14s 28ms/step - loss:0.7739 - acc:0.8261 - val_loss:0.7010 - val_acc:0.8542
Epoch 910/5000
14s 28ms/step - loss:0.7797 - acc:0.8248 - val_loss:0.7322 - val_acc:0.8428
Epoch 911/5000
14s 28ms/step - loss:0.7788 - acc:0.8253 - val_loss:0.7366 - val_acc:0.8418
Epoch 912/5000
14s 28ms/step - loss:0.7861 - acc:0.8226 - val_loss:0.7011 - val_acc:0.8568
Epoch 913/5000
14s 28ms/step - loss:0.7801 - acc:0.8244 - val_loss:0.6968 - val_acc:0.8560
Epoch 914/5000
14s 28ms/step - loss:0.7812 - acc:0.8238 - val_loss:0.7325 - val_acc:0.8383
Epoch 915/5000
14s 28ms/step - loss:0.7781 - acc:0.8239 - val_loss:0.7323 - val_acc:0.8416
Epoch 916/5000
14s 28ms/step - loss:0.7773 - acc:0.8245 - val_loss:0.7187 - val_acc:0.8464
Epoch 917/5000
14s 28ms/step - loss:0.7746 - acc:0.8262 - val_loss:0.7141 - val_acc:0.8484
Epoch 918/5000
14s 28ms/step - loss:0.7820 - acc:0.8229 - val_loss:0.7188 - val_acc:0.8476
Epoch 919/5000
14s 28ms/step - loss:0.7798 - acc:0.8227 - val_loss:0.7166 - val_acc:0.8459
Epoch 920/5000
14s 28ms/step - loss:0.7801 - acc:0.8248 - val_loss:0.7265 - val_acc:0.8438
Epoch 921/5000
14s 28ms/step - loss:0.7773 - acc:0.8257 - val_loss:0.7139 - val_acc:0.8456
Epoch 922/5000
14s 28ms/step - loss:0.7853 - acc:0.8236 - val_loss:0.7258 - val_acc:0.8431
Epoch 923/5000
14s 28ms/step - loss:0.7806 - acc:0.8232 - val_loss:0.7302 - val_acc:0.8440
Epoch 924/5000
14s 28ms/step - loss:0.7784 - acc:0.8245 - val_loss:0.7190 - val_acc:0.8476
Epoch 925/5000
14s 28ms/step - loss:0.7818 - acc:0.8227 - val_loss:0.7139 - val_acc:0.8480
Epoch 926/5000
14s 28ms/step - loss:0.7779 - acc:0.8267 - val_loss:0.7152 - val_acc:0.8533
Epoch 927/5000
15s 29ms/step - loss:0.7790 - acc:0.8242 - val_loss:0.7014 - val_acc:0.8520
Epoch 928/5000
14s 28ms/step - loss:0.7787 - acc:0.8264 - val_loss:0.7274 - val_acc:0.8445
Epoch 929/5000
14s 28ms/step - loss:0.7769 - acc:0.8246 - val_loss:0.7101 - val_acc:0.8457
Epoch 930/5000
14s 29ms/step - loss:0.7826 - acc:0.8242 - val_loss:0.7131 - val_acc:0.8502
Epoch 931/5000
14s 29ms/step - loss:0.7770 - acc:0.8260 - val_loss:0.7165 - val_acc:0.8492
Epoch 932/5000
14s 29ms/step - loss:0.7812 - acc:0.8240 - val_loss:0.7143 - val_acc:0.8517
Epoch 933/5000
14s 29ms/step - loss:0.7774 - acc:0.8250 - val_loss:0.6973 - val_acc:0.8551
Epoch 934/5000
14s 29ms/step - loss:0.7747 - acc:0.8256 - val_loss:0.7229 - val_acc:0.8469
Epoch 935/5000
14s 29ms/step - loss:0.7803 - acc:0.8248 - val_loss:0.7103 - val_acc:0.8532
Epoch 936/5000
14s 29ms/step - loss:0.7770 - acc:0.8273 - val_loss:0.7221 - val_acc:0.8475
Epoch 937/5000
14s 28ms/step - loss:0.7828 - acc:0.8241 - val_loss:0.7053 - val_acc:0.8541
Epoch 938/5000
14s 29ms/step - loss:0.7760 - acc:0.8251 - val_loss:0.7360 - val_acc:0.8417
Epoch 939/5000
14s 29ms/step - loss:0.7789 - acc:0.8248 - val_loss:0.7297 - val_acc:0.8446
Epoch 940/5000
14s 29ms/step - loss:0.7808 - acc:0.8250 - val_loss:0.7342 - val_acc:0.8445
Epoch 941/5000
14s 29ms/step - loss:0.7798 - acc:0.8247 - val_loss:0.7191 - val_acc:0.8469
Epoch 942/5000
14s 29ms/step - loss:0.7810 - acc:0.8243 - val_loss:0.7038 - val_acc:0.8537
Epoch 943/5000
14s 29ms/step - loss:0.7766 - acc:0.8234 - val_loss:0.7158 - val_acc:0.8497
Epoch 944/5000
14s 28ms/step - loss:0.7749 - acc:0.8285 - val_loss:0.7142 - val_acc:0.8502
Epoch 945/5000
14s 28ms/step - loss:0.7757 - acc:0.8276 - val_loss:0.7203 - val_acc:0.8459
Epoch 946/5000
14s 28ms/step - loss:0.7853 - acc:0.8229 - val_loss:0.7134 - val_acc:0.8510
Epoch 947/5000
14s 28ms/step - loss:0.7785 - acc:0.8253 - val_loss:0.7214 - val_acc:0.8443
Epoch 948/5000
14s 28ms/step - loss:0.7776 - acc:0.8260 - val_loss:0.7191 - val_acc:0.8467
Epoch 949/5000
14s 28ms/step - loss:0.7815 - acc:0.8235 - val_loss:0.7117 - val_acc:0.8541
Epoch 950/5000
14s 28ms/step - loss:0.7805 - acc:0.8250 - val_loss:0.7047 - val_acc:0.8485
Epoch 951/5000
14s 28ms/step - loss:0.7816 - acc:0.8244 - val_loss:0.7113 - val_acc:0.8516
Epoch 952/5000
14s 28ms/step - loss:0.7752 - acc:0.8263 - val_loss:0.7217 - val_acc:0.8486
Epoch 953/5000
14s 28ms/step - loss:0.7805 - acc:0.8238 - val_loss:0.7264 - val_acc:0.8471
Epoch 954/5000
14s 28ms/step - loss:0.7809 - acc:0.8240 - val_loss:0.7176 - val_acc:0.8461
Epoch 955/5000
14s 28ms/step - loss:0.7737 - acc:0.8266 - val_loss:0.7265 - val_acc:0.8421
Epoch 956/5000
14s 28ms/step - loss:0.7777 - acc:0.8255 - val_loss:0.7178 - val_acc:0.8502
Epoch 957/5000
14s 28ms/step - loss:0.7841 - acc:0.8241 - val_loss:0.7262 - val_acc:0.8425
Epoch 958/5000
14s 28ms/step - loss:0.7793 - acc:0.8251 - val_loss:0.7250 - val_acc:0.8396
Epoch 959/5000
14s 28ms/step - loss:0.7811 - acc:0.8235 - val_loss:0.7398 - val_acc:0.8405
Epoch 960/5000
14s 28ms/step - loss:0.7792 - acc:0.8248 - val_loss:0.7114 - val_acc:0.8484
Epoch 961/5000
14s 28ms/step - loss:0.7858 - acc:0.8233 - val_loss:0.7259 - val_acc:0.8452
Epoch 962/5000
14s 28ms/step - loss:0.7799 - acc:0.8230 - val_loss:0.7461 - val_acc:0.8352
Epoch 963/5000
14s 29ms/step - loss:0.7783 - acc:0.8257 - val_loss:0.7260 - val_acc:0.8460
Epoch 964/5000
14s 29ms/step - loss:0.7831 - acc:0.8224 - val_loss:0.6883 - val_acc:0.8593
Epoch 965/5000
14s 29ms/step - loss:0.7790 - acc:0.8229 - val_loss:0.7218 - val_acc:0.8459
Epoch 966/5000
14s 29ms/step - loss:0.7783 - acc:0.8247 - val_loss:0.7211 - val_acc:0.8505
Epoch 967/5000
14s 29ms/step - loss:0.7743 - acc:0.8274 - val_loss:0.7158 - val_acc:0.8510
Epoch 968/5000
14s 29ms/step - loss:0.7791 - acc:0.8225 - val_loss:0.7430 - val_acc:0.8424
Epoch 969/5000
14s 29ms/step - loss:0.7774 - acc:0.8251 - val_loss:0.7204 - val_acc:0.8523
Epoch 970/5000
14s 29ms/step - loss:0.7749 - acc:0.8244 - val_loss:0.7635 - val_acc:0.8290
Epoch 971/5000
14s 29ms/step - loss:0.7794 - acc:0.8254 - val_loss:0.7212 - val_acc:0.8459
Epoch 972/5000
14s 29ms/step - loss:0.7794 - acc:0.8255 - val_loss:0.7031 - val_acc:0.8499
Epoch 973/5000
14s 29ms/step - loss:0.7798 - acc:0.8234 - val_loss:0.7360 - val_acc:0.8424
Epoch 974/5000
14s 29ms/step - loss:0.7814 - acc:0.8276 - val_loss:0.7231 - val_acc:0.8518
Epoch 975/5000
14s 29ms/step - loss:0.7846 - acc:0.8230 - val_loss:0.7012 - val_acc:0.8543
Epoch 976/5000
14s 29ms/step - loss:0.7787 - acc:0.8267 - val_loss:0.7313 - val_acc:0.8431
Epoch 977/5000
14s 29ms/step - loss:0.7765 - acc:0.8266 - val_loss:0.7172 - val_acc:0.8510
Epoch 978/5000
14s 29ms/step - loss:0.7816 - acc:0.8226 - val_loss:0.7083 - val_acc:0.8525
Epoch 979/5000
14s 29ms/step - loss:0.7845 - acc:0.8240 - val_loss:0.7105 - val_acc:0.8517
Epoch 980/5000
14s 29ms/step - loss:0.7844 - acc:0.8234 - val_loss:0.7149 - val_acc:0.8473
Epoch 981/5000
14s 29ms/step - loss:0.7819 - acc:0.8255 - val_loss:0.7239 - val_acc:0.8493
Epoch 982/5000
14s 29ms/step - loss:0.7810 - acc:0.8244 - val_loss:0.7355 - val_acc:0.8443
Epoch 983/5000
14s 29ms/step - loss:0.7825 - acc:0.8237 - val_loss:0.7261 - val_acc:0.8431
Epoch 984/5000
14s 29ms/step - loss:0.7780 - acc:0.8252 - val_loss:0.7254 - val_acc:0.8457
Epoch 985/5000
14s 29ms/step - loss:0.7823 - acc:0.8232 - val_loss:0.7270 - val_acc:0.8454
Epoch 986/5000
14s 29ms/step - loss:0.7749 - acc:0.8283 - val_loss:0.7009 - val_acc:0.8570
Epoch 987/5000
14s 29ms/step - loss:0.7762 - acc:0.8244 - val_loss:0.7412 - val_acc:0.8425
Epoch 988/5000
14s 29ms/step - loss:0.7781 - acc:0.8241 - val_loss:0.7306 - val_acc:0.8423
Epoch 989/5000
14s 29ms/step - loss:0.7792 - acc:0.8239 - val_loss:0.7388 - val_acc:0.8426
Epoch 990/5000
14s 29ms/step - loss:0.7819 - acc:0.8240 - val_loss:0.7208 - val_acc:0.8469
Epoch 991/5000
14s 29ms/step - loss:0.7777 - acc:0.8255 - val_loss:0.7487 - val_acc:0.8369
Epoch 992/5000
14s 29ms/step - loss:0.7858 - acc:0.8223 - val_loss:0.7234 - val_acc:0.8483
Epoch 993/5000
14s 29ms/step - loss:0.7829 - acc:0.8223 - val_loss:0.6959 - val_acc:0.8574
Epoch 994/5000
14s 29ms/step - loss:0.7779 - acc:0.8273 - val_loss:0.7067 - val_acc:0.8490
Epoch 995/5000
14s 29ms/step - loss:0.7805 - acc:0.8252 - val_loss:0.7195 - val_acc:0.8481
Epoch 996/5000
14s 29ms/step - loss:0.7781 - acc:0.8259 - val_loss:0.7349 - val_acc:0.8419
Epoch 997/5000
14s 29ms/step - loss:0.7790 - acc:0.8245 - val_loss:0.7397 - val_acc:0.8435
Epoch 998/5000
14s 29ms/step - loss:0.7830 - acc:0.8242 - val_loss:0.7082 - val_acc:0.8482
Epoch 999/5000
14s 29ms/step - loss:0.7783 - acc:0.8254 - val_loss:0.7019 - val_acc:0.8525
Epoch 1000/5000
14s 29ms/step - loss:0.7797 - acc:0.8233 - val_loss:0.7401 - val_acc:0.8410
Epoch 1001/5000
14s 29ms/step - loss:0.7790 - acc:0.8245 - val_loss:0.7112 - val_acc:0.8519
Epoch 1002/5000
14s 29ms/step - loss:0.7789 - acc:0.8248 - val_loss:0.7175 - val_acc:0.8467
Epoch 1003/5000
14s 29ms/step - loss:0.7805 - acc:0.8244 - val_loss:0.7222 - val_acc:0.8446
Epoch 1004/5000
14s 29ms/step - loss:0.7802 - acc:0.8257 - val_loss:0.7068 - val_acc:0.8480
Epoch 1005/5000
14s 29ms/step - loss:0.7844 - acc:0.8238 - val_loss:0.7358 - val_acc:0.8437
Epoch 1006/5000
14s 29ms/step - loss:0.7751 - acc:0.8261 - val_loss:0.7125 - val_acc:0.8507
Epoch 1007/5000
14s 29ms/step - loss:0.7783 - acc:0.8266 - val_loss:0.7003 - val_acc:0.8556
Epoch 1008/5000
14s 29ms/step - loss:0.7743 - acc:0.8262 - val_loss:0.7247 - val_acc:0.8475
Epoch 1009/5000
14s 29ms/step - loss:0.7791 - acc:0.8236 - val_loss:0.7057 - val_acc:0.8531
Epoch 1010/5000
14s 29ms/step - loss:0.7748 - acc:0.8265 - val_loss:0.7362 - val_acc:0.8432
Epoch 1011/5000
14s 29ms/step - loss:0.7807 - acc:0.8239 - val_loss:0.7104 - val_acc:0.8481
Epoch 1012/5000
14s 29ms/step - loss:0.7834 - acc:0.8236 - val_loss:0.6972 - val_acc:0.8531
Epoch 1013/5000
14s 29ms/step - loss:0.7806 - acc:0.8236 - val_loss:0.7255 - val_acc:0.8440
Epoch 1014/5000
14s 29ms/step - loss:0.7790 - acc:0.8237 - val_loss:0.7018 - val_acc:0.8494
Epoch 1015/5000
14s 29ms/step - loss:0.7799 - acc:0.8236 - val_loss:0.7155 - val_acc:0.8487
Epoch 1016/5000
14s 28ms/step - loss:0.7833 - acc:0.8235 - val_loss:0.7130 - val_acc:0.8474
Epoch 1017/5000
14s 28ms/step - loss:0.7816 - acc:0.8231 - val_loss:0.7271 - val_acc:0.8450
Epoch 1018/5000
14s 28ms/step - loss:0.7818 - acc:0.8236 - val_loss:0.7161 - val_acc:0.8496
Epoch 1019/5000
14s 28ms/step - loss:0.7763 - acc:0.8253 - val_loss:0.7211 - val_acc:0.8461
Epoch 1020/5000
14s 29ms/step - loss:0.7785 - acc:0.8242 - val_loss:0.7382 - val_acc:0.8436
Epoch 1021/5000
14s 29ms/step - loss:0.7789 - acc:0.8266 - val_loss:0.6980 - val_acc:0.8530
Epoch 1022/5000
14s 29ms/step - loss:0.7788 - acc:0.8228 - val_loss:0.7033 - val_acc:0.8538
Epoch 1023/5000
14s 29ms/step - loss:0.7788 - acc:0.8242 - val_loss:0.6995 - val_acc:0.8549
Epoch 1024/5000
14s 29ms/step - loss:0.7774 - acc:0.8250 - val_loss:0.6947 - val_acc:0.8555
Epoch 1025/5000
14s 29ms/step - loss:0.7794 - acc:0.8236 - val_loss:0.7180 - val_acc:0.8468
Epoch 1026/5000
14s 29ms/step - loss:0.7758 - acc:0.8269 - val_loss:0.7098 - val_acc:0.8508
Epoch 1027/5000
14s 29ms/step - loss:0.7784 - acc:0.8251 - val_loss:0.7089 - val_acc:0.8502
Epoch 1028/5000
14s 29ms/step - loss:0.7844 - acc:0.8232 - val_loss:0.7211 - val_acc:0.8466
Epoch 1029/5000
14s 29ms/step - loss:0.7752 - acc:0.8276 - val_loss:0.7218 - val_acc:0.8458
Epoch 1030/5000
14s 29ms/step - loss:0.7824 - acc:0.8247 - val_loss:0.7100 - val_acc:0.8519
Epoch 1031/5000
14s 29ms/step - loss:0.7716 - acc:0.8277 - val_loss:0.7142 - val_acc:0.8523
Epoch 1032/5000
14s 29ms/step - loss:0.7780 - acc:0.8258 - val_loss:0.7486 - val_acc:0.8361
Epoch 1033/5000
14s 28ms/step - loss:0.7803 - acc:0.8224 - val_loss:0.7230 - val_acc:0.8487
Epoch 1034/5000
14s 29ms/step - loss:0.7806 - acc:0.8251 - val_loss:0.7247 - val_acc:0.8513
Epoch 1035/5000
14s 29ms/step - loss:0.7824 - acc:0.8243 - val_loss:0.7092 - val_acc:0.8515
Epoch 1036/5000
14s 29ms/step - loss:0.7850 - acc:0.8229 - val_loss:0.6972 - val_acc:0.8570
Epoch 1037/5000
14s 29ms/step - loss:0.7823 - acc:0.8229 - val_loss:0.7169 - val_acc:0.8495
Epoch 1038/5000
14s 29ms/step - loss:0.7752 - acc:0.8272 - val_loss:0.7231 - val_acc:0.8501
Epoch 1039/5000
14s 29ms/step - loss:0.7815 - acc:0.8234 - val_loss:0.7282 - val_acc:0.8438
Epoch 1040/5000
14s 29ms/step - loss:0.7769 - acc:0.8272 - val_loss:0.7229 - val_acc:0.8480
Epoch 1041/5000
14s 29ms/step - loss:0.7835 - acc:0.8246 - val_loss:0.7148 - val_acc:0.8522
Epoch 1042/5000
14s 29ms/step - loss:0.7768 - acc:0.8255 - val_loss:0.7029 - val_acc:0.8534
Epoch 1043/5000
14s 29ms/step - loss:0.7798 - acc:0.8255 - val_loss:0.7144 - val_acc:0.8557
Epoch 1044/5000
14s 29ms/step - loss:0.7792 - acc:0.8240 - val_loss:0.7350 - val_acc:0.8462
Epoch 1045/5000
14s 29ms/step - loss:0.7811 - acc:0.8237 - val_loss:0.7037 - val_acc:0.8550
Epoch 1046/5000
14s 29ms/step - loss:0.7764 - acc:0.8250 - val_loss:0.7233 - val_acc:0.8492
Epoch 1047/5000
14s 29ms/step - loss:0.7830 - acc:0.8248 - val_loss:0.7457 - val_acc:0.8377
Epoch 1048/5000
14s 29ms/step - loss:0.7783 - acc:0.8251 - val_loss:0.7084 - val_acc:0.8507
Epoch 1049/5000
14s 29ms/step - loss:0.7828 - acc:0.8219 - val_loss:0.7300 - val_acc:0.8417
Epoch 1050/5000
14s 29ms/step - loss:0.7825 - acc:0.8231 - val_loss:0.7113 - val_acc:0.8505
Epoch 1051/5000
14s 29ms/step - loss:0.7813 - acc:0.8234 - val_loss:0.7355 - val_acc:0.8439
Epoch 1052/5000
14s 29ms/step - loss:0.7783 - acc:0.8244 - val_loss:0.7220 - val_acc:0.8477
Epoch 1053/5000
14s 29ms/step - loss:0.7827 - acc:0.8226 - val_loss:0.7097 - val_acc:0.8507
Epoch 1054/5000
14s 29ms/step - loss:0.7769 - acc:0.8258 - val_loss:0.7107 - val_acc:0.8503
Epoch 1055/5000
14s 29ms/step - loss:0.7770 - acc:0.8253 - val_loss:0.7379 - val_acc:0.8416
Epoch 1056/5000
14s 29ms/step - loss:0.7834 - acc:0.8213 - val_loss:0.7321 - val_acc:0.8442
Epoch 1057/5000
14s 29ms/step - loss:0.7792 - acc:0.8253 - val_loss:0.7138 - val_acc:0.8478
Epoch 1058/5000
14s 29ms/step - loss:0.7807 - acc:0.8243 - val_loss:0.6981 - val_acc:0.8542
Epoch 1059/5000
14s 29ms/step - loss:0.7794 - acc:0.8250 - val_loss:0.7019 - val_acc:0.8562
Epoch 1060/5000
14s 29ms/step - loss:0.7781 - acc:0.8252 - val_loss:0.6955 - val_acc:0.8552
Epoch 1061/5000
14s 29ms/step - loss:0.7785 - acc:0.8247 - val_loss:0.7077 - val_acc:0.8496
Epoch 1062/5000
14s 29ms/step - loss:0.7772 - acc:0.8241 - val_loss:0.7209 - val_acc:0.8492
Epoch 1063/5000
14s 29ms/step - loss:0.7782 - acc:0.8250 - val_loss:0.7165 - val_acc:0.8488
Epoch 1064/5000
14s 29ms/step - loss:0.7790 - acc:0.8260 - val_loss:0.7276 - val_acc:0.8461
Epoch 1065/5000
14s 29ms/step - loss:0.7766 - acc:0.8262 - val_loss:0.7097 - val_acc:0.8469
Epoch 1066/5000
14s 29ms/step - loss:0.7731 - acc:0.8254 - val_loss:0.7111 - val_acc:0.8486
Epoch 1067/5000
14s 29ms/step - loss:0.7792 - acc:0.8245 - val_loss:0.7196 - val_acc:0.8486
Epoch 1068/5000
14s 29ms/step - loss:0.7797 - acc:0.8262 - val_loss:0.7094 - val_acc:0.8520
Epoch 1069/5000
14s 29ms/step - loss:0.7803 - acc:0.8241 - val_loss:0.7225 - val_acc:0.8466
Epoch 1070/5000
14s 29ms/step - loss:0.7816 - acc:0.8241 - val_loss:0.7219 - val_acc:0.8468
Epoch 1071/5000
14s 29ms/step - loss:0.7797 - acc:0.8244 - val_loss:0.7090 - val_acc:0.8506
Epoch 1072/5000
14s 29ms/step - loss:0.7759 - acc:0.8250 - val_loss:0.7081 - val_acc:0.8443
Epoch 1073/5000
14s 29ms/step - loss:0.7796 - acc:0.8228 - val_loss:0.7139 - val_acc:0.8498
Epoch 1074/5000
14s 29ms/step - loss:0.7785 - acc:0.8260 - val_loss:0.7201 - val_acc:0.8486
Epoch 1075/5000
14s 29ms/step - loss:0.7816 - acc:0.8235 - val_loss:0.7206 - val_acc:0.8496
Epoch 1076/5000
14s 29ms/step - loss:0.7771 - acc:0.8258 - val_loss:0.7568 - val_acc:0.8361
Epoch 1077/5000
14s 29ms/step - loss:0.7788 - acc:0.8228 - val_loss:0.7031 - val_acc:0.8568
Epoch 1078/5000
14s 29ms/step - loss:0.7724 - acc:0.8253 - val_loss:0.7129 - val_acc:0.8502
Epoch 1079/5000
14s 29ms/step - loss:0.7768 - acc:0.8255 - val_loss:0.7303 - val_acc:0.8415
Epoch 1080/5000
14s 29ms/step - loss:0.7798 - acc:0.8247 - val_loss:0.7180 - val_acc:0.8505
Epoch 1081/5000
14s 29ms/step - loss:0.7785 - acc:0.8252 - val_loss:0.7125 - val_acc:0.8516
Epoch 1082/5000
14s 29ms/step - loss:0.7741 - acc:0.8275 - val_loss:0.7217 - val_acc:0.8468
Epoch 1083/5000
14s 28ms/step - loss:0.7768 - acc:0.8246 - val_loss:0.7232 - val_acc:0.8474
Epoch 1084/5000
14s 29ms/step - loss:0.7779 - acc:0.8267 - val_loss:0.7130 - val_acc:0.8503
Epoch 1085/5000
14s 29ms/step - loss:0.7811 - acc:0.8235 - val_loss:0.7002 - val_acc:0.8526
Epoch 1086/5000
14s 29ms/step - loss:0.7752 - acc:0.8256 - val_loss:0.7155 - val_acc:0.8494
Epoch 1087/5000
14s 29ms/step - loss:0.7872 - acc:0.8228 - val_loss:0.7084 - val_acc:0.8490
Epoch 1088/5000
14s 29ms/step - loss:0.7799 - acc:0.8247 - val_loss:0.7207 - val_acc:0.8489
Epoch 1089/5000
14s 29ms/step - loss:0.7770 - acc:0.8271 - val_loss:0.7220 - val_acc:0.8447
Epoch 1090/5000
14s 29ms/step - loss:0.7768 - acc:0.8261 - val_loss:0.7084 - val_acc:0.8491
Epoch 1091/5000
14s 29ms/step - loss:0.7790 - acc:0.8246 - val_loss:0.7292 - val_acc:0.8428
Epoch 1092/5000
14s 29ms/step - loss:0.7794 - acc:0.8245 - val_loss:0.7222 - val_acc:0.8469
Epoch 1093/5000
14s 29ms/step - loss:0.7715 - acc:0.8295 - val_loss:0.7113 - val_acc:0.8482
Epoch 1094/5000
14s 29ms/step - loss:0.7801 - acc:0.8239 - val_loss:0.6976 - val_acc:0.8531
Epoch 1095/5000
14s 29ms/step - loss:0.7783 - acc:0.8242 - val_loss:0.7212 - val_acc:0.8458
Epoch 1096/5000
14s 29ms/step - loss:0.7786 - acc:0.8255 - val_loss:0.6960 - val_acc:0.8539
Epoch 1097/5000
14s 28ms/step - loss:0.7762 - acc:0.8245 - val_loss:0.7055 - val_acc:0.8517
Epoch 1098/5000
14s 29ms/step - loss:0.7756 - acc:0.8257 - val_loss:0.7114 - val_acc:0.8511
Epoch 1099/5000
14s 29ms/step - loss:0.7806 - acc:0.8239 - val_loss:0.7336 - val_acc:0.8440
Epoch 1100/5000
14s 29ms/step - loss:0.7761 - acc:0.8264 - val_loss:0.7261 - val_acc:0.8464
Epoch 1101/5000
14s 29ms/step - loss:0.7782 - acc:0.8243 - val_loss:0.7241 - val_acc:0.8438
Epoch 1102/5000
14s 29ms/step - loss:0.7760 - acc:0.8240 - val_loss:0.6991 - val_acc:0.8552
Epoch 1103/5000
14s 29ms/step - loss:0.7768 - acc:0.8264 - val_loss:0.7288 - val_acc:0.8440
Epoch 1104/5000
14s 29ms/step - loss:0.7808 - acc:0.8240 - val_loss:0.7311 - val_acc:0.8432
Epoch 1105/5000
14s 29ms/step - loss:0.7763 - acc:0.8250 - val_loss:0.7220 - val_acc:0.8479
Epoch 1106/5000
14s 29ms/step - loss:0.7824 - acc:0.8235 - val_loss:0.7057 - val_acc:0.8540
Epoch 1107/5000
14s 29ms/step - loss:0.7772 - acc:0.8246 - val_loss:0.7026 - val_acc:0.8513
Epoch 1108/5000
14s 29ms/step - loss:0.7803 - acc:0.8235 - val_loss:0.7070 - val_acc:0.8511
Epoch 1109/5000
14s 29ms/step - loss:0.7835 - acc:0.8236 - val_loss:0.7282 - val_acc:0.8472
Epoch 1110/5000
14s 29ms/step - loss:0.7773 - acc:0.8264 - val_loss:0.7311 - val_acc:0.8467
Epoch 1111/5000
14s 29ms/step - loss:0.7801 - acc:0.8231 - val_loss:0.7171 - val_acc:0.8543
Epoch 1112/5000
14s 29ms/step - loss:0.7818 - acc:0.8241 - val_loss:0.7142 - val_acc:0.8478
Epoch 1113/5000
14s 29ms/step - loss:0.7820 - acc:0.8233 - val_loss:0.7107 - val_acc:0.8494
Epoch 1114/5000
14s 29ms/step - loss:0.7786 - acc:0.8257 - val_loss:0.7278 - val_acc:0.8438
Epoch 1115/5000
14s 29ms/step - loss:0.7801 - acc:0.8247 - val_loss:0.7138 - val_acc:0.8511
Epoch 1116/5000
14s 29ms/step - loss:0.7811 - acc:0.8238 - val_loss:0.7075 - val_acc:0.8521
Epoch 1117/5000
14s 29ms/step - loss:0.7803 - acc:0.8250 - val_loss:0.6918 - val_acc:0.8581
Epoch 1118/5000
14s 29ms/step - loss:0.7748 - acc:0.8257 - val_loss:0.7333 - val_acc:0.8438
Epoch 1119/5000
14s 29ms/step - loss:0.7801 - acc:0.8253 - val_loss:0.7202 - val_acc:0.8472
Epoch 1120/5000
14s 29ms/step - loss:0.7784 - acc:0.8253 - val_loss:0.7171 - val_acc:0.8517
Epoch 1121/5000
14s 29ms/step - loss:0.7747 - acc:0.8259 - val_loss:0.7117 - val_acc:0.8483
Epoch 1122/5000
14s 28ms/step - loss:0.7778 - acc:0.8258 - val_loss:0.7101 - val_acc:0.8501
Epoch 1123/5000
14s 28ms/step - loss:0.7793 - acc:0.8245 - val_loss:0.7326 - val_acc:0.8421
Epoch 1124/5000
14s 28ms/step - loss:0.7832 - acc:0.8227 - val_loss:0.7386 - val_acc:0.8403
Epoch 1125/5000
14s 28ms/step - loss:0.7796 - acc:0.8249 - val_loss:0.6999 - val_acc:0.8527
Epoch 1126/5000
14s 28ms/step - loss:0.7832 - acc:0.8238 - val_loss:0.7254 - val_acc:0.8440
Epoch 1127/5000
14s 28ms/step - loss:0.7801 - acc:0.8229 - val_loss:0.7216 - val_acc:0.8523
Epoch 1128/5000
14s 28ms/step - loss:0.7825 - acc:0.8243 - val_loss:0.7132 - val_acc:0.8464
Epoch 1129/5000
14s 28ms/step - loss:0.7819 - acc:0.8237 - val_loss:0.7357 - val_acc:0.8445
Epoch 1130/5000
14s 28ms/step - loss:0.7771 - acc:0.8245 - val_loss:0.7292 - val_acc:0.8399
Epoch 1131/5000
14s 28ms/step - loss:0.7803 - acc:0.8241 - val_loss:0.7126 - val_acc:0.8532
Epoch 1132/5000
14s 28ms/step - loss:0.7840 - acc:0.8225 - val_loss:0.7195 - val_acc:0.8467
Epoch 1133/5000
14s 28ms/step - loss:0.7818 - acc:0.8247 - val_loss:0.7167 - val_acc:0.8462
Epoch 1134/5000
14s 28ms/step - loss:0.7802 - acc:0.8243 - val_loss:0.7180 - val_acc:0.8485
Epoch 1135/5000
14s 28ms/step - loss:0.7771 - acc:0.8255 - val_loss:0.7354 - val_acc:0.8404
Epoch 1136/5000
14s 28ms/step - loss:0.7804 - acc:0.8241 - val_loss:0.7151 - val_acc:0.8499
Epoch 1137/5000
14s 28ms/step - loss:0.7722 - acc:0.8276 - val_loss:0.7180 - val_acc:0.8478
Epoch 1138/5000
14s 28ms/step - loss:0.7803 - acc:0.8242 - val_loss:0.7294 - val_acc:0.8413
Epoch 1139/5000
14s 28ms/step - loss:0.7787 - acc:0.8240 - val_loss:0.7112 - val_acc:0.8497
Epoch 1140/5000
14s 28ms/step - loss:0.7827 - acc:0.8220 - val_loss:0.7258 - val_acc:0.8462
Epoch 1141/5000
14s 28ms/step - loss:0.7783 - acc:0.8255 - val_loss:0.6970 - val_acc:0.8542
Epoch 1142/5000
14s 28ms/step - loss:0.7835 - acc:0.8218 - val_loss:0.7143 - val_acc:0.8519
Epoch 1143/5000
14s 28ms/step - loss:0.7795 - acc:0.8235 - val_loss:0.7167 - val_acc:0.8486
Epoch 1144/5000
14s 28ms/step - loss:0.7782 - acc:0.8266 - val_loss:0.7335 - val_acc:0.8416
Epoch 1145/5000
14s 28ms/step - loss:0.7783 - acc:0.8251 - val_loss:0.7014 - val_acc:0.8528
Epoch 1146/5000
14s 28ms/step - loss:0.7766 - acc:0.8234 - val_loss:0.7010 - val_acc:0.8550
Epoch 1147/5000
14s 28ms/step - loss:0.7820 - acc:0.8245 - val_loss:0.7037 - val_acc:0.8545
Epoch 1148/5000
14s 28ms/step - loss:0.7740 - acc:0.8264 - val_loss:0.7141 - val_acc:0.8519
Epoch 1149/5000
14s 28ms/step - loss:0.7791 - acc:0.8246 - val_loss:0.7495 - val_acc:0.8421
Epoch 1150/5000
14s 28ms/step - loss:0.7785 - acc:0.8252 - val_loss:0.7398 - val_acc:0.8373
Epoch 1151/5000
14s 28ms/step - loss:0.7832 - acc:0.8237 - val_loss:0.7199 - val_acc:0.8472
Epoch 1152/5000
14s 28ms/step - loss:0.7823 - acc:0.8240 - val_loss:0.7073 - val_acc:0.8535
Epoch 1153/5000
14s 28ms/step - loss:0.7805 - acc:0.8251 - val_loss:0.7187 - val_acc:0.8499
Epoch 1154/5000
14s 28ms/step - loss:0.7820 - acc:0.8228 - val_loss:0.7399 - val_acc:0.8407
Epoch 1155/5000
15s 29ms/step - loss:0.7829 - acc:0.8224 - val_loss:0.7405 - val_acc:0.8377
Epoch 1156/5000
14s 29ms/step - loss:0.7805 - acc:0.8248 - val_loss:0.7229 - val_acc:0.8470
Epoch 1157/5000
14s 28ms/step - loss:0.7794 - acc:0.8263 - val_loss:0.7350 - val_acc:0.8440
Epoch 1158/5000
14s 28ms/step - loss:0.7799 - acc:0.8241 - val_loss:0.7069 - val_acc:0.8525
Epoch 1159/5000
14s 28ms/step - loss:0.7801 - acc:0.8253 - val_loss:0.7056 - val_acc:0.8543
Epoch 1160/5000
14s 28ms/step - loss:0.7777 - acc:0.8258 - val_loss:0.7226 - val_acc:0.8501
Epoch 1161/5000
14s 28ms/step - loss:0.7806 - acc:0.8246 - val_loss:0.7263 - val_acc:0.8458
Epoch 1162/5000
14s 28ms/step - loss:0.7793 - acc:0.8243 - val_loss:0.7063 - val_acc:0.8522
Epoch 1163/5000
14s 28ms/step - loss:0.7783 - acc:0.8263 - val_loss:0.7391 - val_acc:0.8430
Epoch 1164/5000
14s 28ms/step - loss:0.7753 - acc:0.8263 - val_loss:0.7254 - val_acc:0.8465
Epoch 1165/5000
14s 28ms/step - loss:0.7838 - acc:0.8232 - val_loss:0.7287 - val_acc:0.8479
Epoch 1166/5000
14s 28ms/step - loss:0.7827 - acc:0.8229 - val_loss:0.7269 - val_acc:0.8464
Epoch 1167/5000
14s 28ms/step - loss:0.7782 - acc:0.8262 - val_loss:0.7305 - val_acc:0.8438
Epoch 1168/5000
14s 28ms/step - loss:0.7778 - acc:0.8251 - val_loss:0.7065 - val_acc:0.8501
Epoch 1169/5000
14s 28ms/step - loss:0.7768 - acc:0.8249 - val_loss:0.7039 - val_acc:0.8540
Epoch 1170/5000
14s 28ms/step - loss:0.7797 - acc:0.8261 - val_loss:0.7052 - val_acc:0.8547
Epoch 1171/5000
14s 29ms/step - loss:0.7799 - acc:0.8245 - val_loss:0.6993 - val_acc:0.8564
Epoch 1172/5000
14s 29ms/step - loss:0.7768 - acc:0.8253 - val_loss:0.7237 - val_acc:0.8473



     ReLU                     1/16                      Squeeze-and-Excitation network       

Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht, Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis, IEEE Transactions on Industrial Electronics, 2020, DOI:10.1109/TIE.2020.2972458, Date of Publication :13 February 2020

https://ieeexplore.ieee.org/d...