Adaptive parameterized ReLU: Dynamic ReLU (parameter record 18) proposed by Harbin Institute of Technology Cifar10 ~ 94.28%

Posted May 25, 202064 min read

Adaptive parameterized ReLU is a dynamic activation function that performs different operations on each input sample, submitted to IEEE Transactions on Industrial Electronics on May 3, 2019, accepted on January 24, 2020 , Announced on the IEEE official website on February 13, 2020.

This paper increases the number of residual modules to 27. In fact, this has been done before, and the difference now is that the number of neurons in the first fully connected layer in adaptive parameterized ReLU is set to 1/16 of the number of feature channels. It is also tested on Cifar10.

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

Keras code is as follows:

#!/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, 9, 32, downsample = False)
net = residual_block(net, 1, 32, downsample = True)
net = residual_block(net, 8, 32, downsample = False)
net = residual_block(net, 1, 64, downsample = True)
net = residual_block(net, 8, 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 ease of viewing, the equal sign in the training record has been deleted):

Using TensorFlow backend.
x_train shape:(50000, 32, 32, 3)
50000 train samples
10000 test samples
Epoch 1/5000
107s 215ms/step-loss:2.9739-acc:0.3942-val_loss:2.5752-val_acc:0.5134
Epoch 2/5000
77s 155ms/step-loss:2.4558-acc:0.5143-val_loss:2.1374-val_acc:0.6048
Epoch 3/5000
78s 155ms/step-loss:2.1359-acc:0.5744-val_loss:1.8827-val_acc:0.6355
Epoch 4/5000
78s 155ms/step-loss:1.9044-acc:0.6088-val_loss:1.6888-val_acc:0.6620
Epoch 5/5000
78s 155ms/step-loss:1.7154-acc:0.6381-val_loss:1.5106-val_acc:0.6946
Epoch 6/5000
77s 155ms/step-loss:1.5849-acc:0.6528-val_loss:1.3992-val_acc:0.7031
Epoch 7/5000
77s 155ms/step-loss:1.4700-acc:0.6686-val_loss:1.2869-val_acc:0.7208
Epoch 8/5000
77s 155ms/step-loss:1.3735-acc:0.6851-val_loss:1.2068-val_acc:0.7400
Epoch 9/5000
77s 155ms/step-loss:1.2940-acc:0.6980-val_loss:1.1169-val_acc:0.7588
Epoch 10/5000
77s 155ms/step-loss:1.2318-acc:0.7058-val_loss:1.0696-val_acc:0.7647
Epoch 11/5000
77s 155ms/step-loss:1.1735-acc:0.7202-val_loss:1.0117-val_acc:0.7757
Epoch 12/5000
77s 155ms/step-loss:1.1366-acc:0.7240-val_loss:0.9968-val_acc:0.7770
Epoch 13/5000
77s 155ms/step-loss:1.0974-acc:0.7308-val_loss:0.9548-val_acc:0.7824
Epoch 14/5000
77s 155ms/step-loss:1.0653-acc:0.7390-val_loss:0.9196-val_acc:0.7885
Epoch 15/5000
77s 155ms/step-loss:1.0409-acc:0.7419-val_loss:0.9444-val_acc:0.7775
Epoch 16/5000
78s 155ms/step-loss:1.0122-acc:0.7526-val_loss:0.9039-val_acc:0.7893
Epoch 17/5000
78s 155ms/step-loss:0.9970-acc:0.7561-val_loss:0.8913-val_acc:0.7952
Epoch 18/5000
77s 155ms/step-loss:0.9819-acc:0.7562-val_loss:0.8748-val_acc:0.7995
Epoch 19/5000
77s 155ms/step-loss:0.9638-acc:0.7615-val_loss:0.8445-val_acc:0.8063
Epoch 20/5000
78s 155ms/step-loss:0.9516-acc:0.7662-val_loss:0.8522-val_acc:0.8011
Epoch 21/5000
78s 155ms/step-loss:0.9401-acc:0.7698-val_loss:0.8325-val_acc:0.8145
Epoch 22/5000
78s 155ms/step-loss:0.9302-acc:0.7731-val_loss:0.8266-val_acc:0.8141
Epoch 23/5000
78s 155ms/step-loss:0.9231-acc:0.7747-val_loss:0.8390-val_acc:0.8043
Epoch 24/5000
77s 155ms/step-loss:0.9105-acc:0.7786-val_loss:0.8009-val_acc:0.8191
Epoch 25/5000
77s 155ms/step-loss:0.9027-acc:0.7795-val_loss:0.7903-val_acc:0.8218
Epoch 26/5000
77s 155ms/step-loss:0.8946-acc:0.7863-val_loss:0.7812-val_acc:0.8271
Epoch 27/5000
78s 155ms/step-loss:0.8923-acc:0.7852-val_loss:0.7933-val_acc:0.8226
Epoch 28/5000
78s 155ms/step-loss:0.8808-acc:0.7890-val_loss:0.7597-val_acc:0.8346
Epoch 29/5000
78s 155ms/step-loss:0.8826-acc:0.7881-val_loss:0.7639-val_acc:0.8332
Epoch 30/5000
77s 155ms/step-loss:0.8685-acc:0.7941-val_loss:0.7807-val_acc:0.8278
Epoch 31/5000
78s 155ms/step-loss:0.8647-acc:0.7936-val_loss:0.7686-val_acc:0.8304
Epoch 32/5000
77s 155ms/step-loss:0.8611-acc:0.7971-val_loss:0.7619-val_acc:0.8324
Epoch 33/5000
77s 155ms/step-loss:0.8584-acc:0.7965-val_loss:0.7632-val_acc:0.8323
Epoch 34/5000
77s 155ms/step-loss:0.8513-acc:0.8000-val_loss:0.7575-val_acc:0.8363
Epoch 35/5000
77s 155ms/step-loss:0.8494-acc:0.7990-val_loss:0.7669-val_acc:0.8293
Epoch 36/5000
77s 155ms/step-loss:0.8486-acc:0.8024-val_loss:0.7269-val_acc:0.8488
Epoch 37/5000
78s 155ms/step-loss:0.8432-acc:0.8032-val_loss:0.7633-val_acc:0.8355
Epoch 38/5000
78s 155ms/step-loss:0.8380-acc:0.8061-val_loss:0.7554-val_acc:0.8356
Epoch 39/5000
77s 155ms/step-loss:0.8340-acc:0.8071-val_loss:0.7587-val_acc:0.8378
Epoch 40/5000
77s 155ms/step-loss:0.8310-acc:0.8098-val_loss:0.7495-val_acc:0.8345
Epoch 41/5000
78s 155ms/step-loss:0.8313-acc:0.8092-val_loss:0.7370-val_acc:0.8446
Epoch 42/5000
77s 155ms/step-loss:0.8239-acc:0.8118-val_loss:0.7481-val_acc:0.8398
Epoch 43/5000
78s 155ms/step-loss:0.8244-acc:0.8125-val_loss:0.7351-val_acc:0.8473
Epoch 44/5000
77s 155ms/step-loss:0.8197-acc:0.8122-val_loss:0.7396-val_acc:0.8444
Epoch 45/5000
78s 155ms/step-loss:0.8152-acc:0.8143-val_loss:0.7500-val_acc:0.8444
Epoch 46/5000
78s 155ms/step-loss:0.8158-acc:0.8162-val_loss:0.7657-val_acc:0.8358
Epoch 47/5000
77s 155ms/step-loss:0.8120-acc:0.8173-val_loss:0.7409-val_acc:0.8431
Epoch 48/5000
77s 155ms/step-loss:0.8141-acc:0.8155-val_loss:0.7370-val_acc:0.8458
Epoch 49/5000
77s 155ms/step-loss:0.8054-acc:0.8202-val_loss:0.7485-val_acc:0.8412
Epoch 50/5000
77s 154ms/step-loss:0.8030-acc:0.8189-val_loss:0.7240-val_acc:0.8494
Epoch 51/5000
77s 155ms/step-loss:0.8020-acc:0.8212-val_loss:0.7283-val_acc:0.8472
Epoch 52/5000
77s 155ms/step-loss:0.7991-acc:0.8221-val_loss:0.7443-val_acc:0.8416
Epoch 53/5000
77s 155ms/step-loss:0.7915-acc:0.8252-val_loss:0.7322-val_acc:0.8468
Epoch 54/5000
77s 155ms/step-loss:0.7956-acc:0.8231-val_loss:0.7171-val_acc:0.8502
Epoch 55/5000
77s 155ms/step-loss:0.7890-acc:0.8257-val_loss:0.7102-val_acc:0.8563
Epoch 56/5000
77s 155ms/step-loss:0.7930-acc:0.8233-val_loss:0.7081-val_acc:0.8569
Epoch 57/5000
77s 155ms/step-loss:0.7912-acc:0.8261-val_loss:0.7117-val_acc:0.8597
Epoch 58/5000
77s 154ms/step-loss:0.7878-acc:0.8259-val_loss:0.7217-val_acc:0.8504
Epoch 59/5000
78s 155ms/step-loss:0.7851-acc:0.8294-val_loss:0.6983-val_acc:0.8614
Epoch 60/5000
77s 155ms/step-loss:0.7844-acc:0.8276-val_loss:0.7018-val_acc:0.8598
Epoch 61/5000
77s 155ms/step-loss:0.7840-acc:0.8290-val_loss:0.7333-val_acc:0.8507
Epoch 62/5000
77s 154ms/step-loss:0.7848-acc:0.8288-val_loss:0.7279-val_acc:0.8503
Epoch 63/5000
77s 155ms/step-loss:0.7819-acc:0.8305-val_loss:0.7187-val_acc:0.8520
Epoch 64/5000
77s 155ms/step-loss:0.7822-acc:0.8290-val_loss:0.7123-val_acc:0.8568
Epoch 65/5000
77s 154ms/step-loss:0.7768-acc:0.8323-val_loss:0.6983-val_acc:0.8621
Epoch 66/5000
77s 155ms/step-loss:0.7759-acc:0.8318-val_loss:0.7027-val_acc:0.8614
Epoch 67/5000
77s 155ms/step-loss:0.7783-acc:0.8329-val_loss:0.7249-val_acc:0.8558
Epoch 68/5000
77s 155ms/step-loss:0.7772-acc:0.8324-val_loss:0.7089-val_acc:0.8595
Epoch 69/5000
77s 155ms/step-loss:0.7760-acc:0.8341-val_loss:0.7116-val_acc:0.8562
Epoch 70/5000
77s 155ms/step-loss:0.7720-acc:0.8344-val_loss:0.7378-val_acc:0.8486
Epoch 71/5000
77s 155ms/step-loss:0.7721-acc:0.8357-val_loss:0.6936-val_acc:0.8653
Epoch 72/5000
77s 155ms/step-loss:0.7706-acc:0.8353-val_loss:0.7158-val_acc:0.8580
Epoch 73/5000
77s 155ms/step-loss:0.7727-acc:0.8345-val_loss:0.7100-val_acc:0.8605
Epoch 74/5000
77s 155ms/step-loss:0.7682-acc:0.8385-val_loss:0.6988-val_acc:0.8621
Epoch 75/5000
77s 155ms/step-loss:0.7705-acc:0.8353-val_loss:0.7062-val_acc:0.8553
Epoch 76/5000
77s 155ms/step-loss:0.7682-acc:0.8365-val_loss:0.7227-val_acc:0.8571
Epoch 77/5000
77s 155ms/step-loss:0.7621-acc:0.8388-val_loss:0.6973-val_acc:0.8635
Epoch 78/5000
77s 155ms/step-loss:0.7617-acc:0.8393-val_loss:0.7023-val_acc:0.8591
Epoch 79/5000
77s 155ms/step-loss:0.7618-acc:0.8374-val_loss:0.6919-val_acc:0.8656
Epoch 80/5000
77s 155ms/step-loss:0.7658-acc:0.8372-val_loss:0.7192-val_acc:0.8559
Epoch 81/5000
77s 155ms/step-loss:0.7600-acc:0.8415-val_loss:0.7004-val_acc:0.8628
Epoch 82/5000
77s 155ms/step-loss:0.7623-acc:0.8378-val_loss:0.6683-val_acc:0.8748
Epoch 83/5000
77s 154ms/step-loss:0.7579-acc:0.8407-val_loss:0.7009-val_acc:0.8604
Epoch 84/5000
77s 155ms/step-loss:0.7569-acc:0.8407-val_loss:0.6992-val_acc:0.8611
Epoch 85/5000
77s 155ms/step-loss:0.7515-acc:0.8431-val_loss:0.7052-val_acc:0.8606
Epoch 86/5000
77s 155ms/step-loss:0.7581-acc:0.8420-val_loss:0.7094-val_acc:0.8549
Epoch 87/5000
77s 155ms/step-loss:0.7555-acc:0.8413-val_loss:0.7164-val_acc:0.8573
Epoch 88/5000
77s 154ms/step-loss:0.7555-acc:0.8413-val_loss:0.7003-val_acc:0.8671
Epoch 89/5000
77s 155ms/step-loss:0.7523-acc:0.8468-val_loss:0.6850-val_acc:0.8698
Epoch 90/5000
77s 155ms/step-loss:0.7511-acc:0.8451-val_loss:0.6796-val_acc:0.8720
Epoch 91/5000
77s 155ms/step-loss:0.7539-acc:0.8430-val_loss:0.6969-val_acc:0.8632
Epoch 92/5000
77s 155ms/step-loss:0.7519-acc:0.8438-val_loss:0.7286-val_acc:0.8538
Epoch 93/5000
77s 155ms/step-loss:0.7509-acc:0.8443-val_loss:0.6878-val_acc:0.8669
Epoch 94/5000
77s 155ms/step-loss:0.7487-acc:0.8455-val_loss:0.6985-val_acc:0.8661
Epoch 95/5000
77s 155ms/step-loss:0.7497-acc:0.8444-val_loss:0.6983-val_acc:0.8646
Epoch 96/5000
77s 155ms/step-loss:0.7501-acc:0.8437-val_loss:0.6890-val_acc:0.8677
Epoch 97/5000
77s 155ms/step-loss:0.7471-acc:0.8461-val_loss:0.6912-val_acc:0.8662
Epoch 98/5000
77s 154ms/step-loss:0.7472-acc:0.8466-val_loss:0.6830-val_acc:0.8695
Epoch 99/5000
77s 155ms/step-loss:0.7476-acc:0.8451-val_loss:0.7109-val_acc:0.8630
Epoch 100/5000
77s 155ms/step-loss:0.7452-acc:0.8473-val_loss:0.6877-val_acc:0.8684
Epoch 101/5000
78s 155ms/step-loss:0.7436-acc:0.8483-val_loss:0.7104-val_acc:0.8597
Epoch 102/5000
77s 155ms/step-loss:0.7479-acc:0.8471-val_loss:0.6644-val_acc:0.8757
Epoch 103/5000
77s 154ms/step-loss:0.7395-acc:0.8489-val_loss:0.6755-val_acc:0.8717
Epoch 104/5000
77s 155ms/step-loss:0.7394-acc:0.8501-val_loss:0.6735-val_acc:0.8696
Epoch 105/5000
77s 155ms/step-loss:0.7442-acc:0.8465-val_loss:0.6777-val_acc:0.8741
Epoch 106/5000
77s 154ms/step-loss:0.7429-acc:0.8485-val_loss:0.6860-val_acc:0.8713
Epoch 107/5000
77s 155ms/step-loss:0.7420-acc:0.8494-val_loss:0.6858-val_acc:0.8711
Epoch 108/5000
77s 155ms/step-loss:0.7438-acc:0.8483-val_loss:0.6807-val_acc:0.8702
Epoch 109/5000
77s 154ms/step-loss:0.7385-acc:0.8506-val_loss:0.6778-val_acc:0.8713
Epoch 110/5000
77s 155ms/step-loss:0.7409-acc:0.8482-val_loss:0.7039-val_acc:0.8640
Epoch 111/5000
77s 155ms/step-loss:0.7376-acc:0.8501-val_loss:0.6737-val_acc:0.8745
Epoch 112/5000
77s 155ms/step-loss:0.7388-acc:0.8497-val_loss:0.6785-val_acc:0.8711
Epoch 113/5000
77s 155ms/step-loss:0.7307-acc:0.8534-val_loss:0.6741-val_acc:0.8719
Epoch 114/5000
77s 155ms/step-loss:0.7443-acc:0.8496-val_loss:0.6898-val_acc:0.8699
Epoch 115/5000
77s 155ms/step-loss:0.7340-acc:0.8514-val_loss:0.6953-val_acc:0.8666
Epoch 116/5000
77s 155ms/step-loss:0.7367-acc:0.8516-val_loss:0.6951-val_acc:0.8656
Epoch 117/5000
77s 155ms/step-loss:0.7367-acc:0.8508-val_loss:0.6809-val_acc:0.8709
Epoch 118/5000
77s 155ms/step-loss:0.7324-acc:0.8521-val_loss:0.6809-val_acc:0.8746
Epoch 119/5000
77s 155ms/step-loss:0.7335-acc:0.8528-val_loss:0.6919-val_acc:0.8663
Epoch 120/5000
77s 155ms/step-loss:0.7363-acc:0.8507-val_loss:0.6922-val_acc:0.8693
Epoch 121/5000
77s 155ms/step-loss:0.7341-acc:0.8530-val_loss:0.6859-val_acc:0.8717
Epoch 122/5000
77s 155ms/step-loss:0.7334-acc:0.8533-val_loss:0.7199-val_acc:0.8596
Epoch 123/5000
77s 155ms/step-loss:0.7328-acc:0.8527-val_loss:0.6934-val_acc:0.8658
Epoch 124/5000
77s 155ms/step-loss:0.7278-acc:0.8532-val_loss:0.6822-val_acc:0.8684
Epoch 125/5000
77s 155ms/step-loss:0.7338-acc:0.8532-val_loss:0.6865-val_acc:0.8700
Epoch 126/5000
77s 155ms/step-loss:0.7319-acc:0.8528-val_loss:0.6759-val_acc:0.8732
Epoch 127/5000
78s 155ms/step-loss:0.7335-acc:0.8519-val_loss:0.6776-val_acc:0.8744
Epoch 128/5000
77s 155ms/step-loss:0.7302-acc:0.8521-val_loss:0.6883-val_acc:0.8678
Epoch 129/5000
77s 155ms/step-loss:0.7299-acc:0.8543-val_loss:0.6868-val_acc:0.8697
Epoch 130/5000
77s 155ms/step-loss:0.7318-acc:0.8527-val_loss:0.6784-val_acc:0.8735
Epoch 131/5000
77s 155ms/step-loss:0.7280-acc:0.8559-val_loss:0.6750-val_acc:0.8745
Epoch 132/5000
77s 155ms/step-loss:0.7301-acc:0.8543-val_loss:0.6815-val_acc:0.8721
Epoch 133/5000
77s 155ms/step-loss:0.7319-acc:0.8536-val_loss:0.6647-val_acc:0.8762
Epoch 134/5000
77s 155ms/step-loss:0.7338-acc:0.8532-val_loss:0.6733-val_acc:0.8767
Epoch 135/5000
77s 155ms/step-loss:0.7330-acc:0.8533-val_loss:0.6891-val_acc:0.8705
Epoch 136/5000
77s 155ms/step-loss:0.7251-acc:0.8563-val_loss:0.6765-val_acc:0.8781
Epoch 137/5000
77s 154ms/step-loss:0.7315-acc:0.8543-val_loss:0.6875-val_acc:0.8701
Epoch 138/5000
77s 155ms/step-loss:0.7290-acc:0.8546-val_loss:0.6824-val_acc:0.8701
Epoch 139/5000
77s 155ms/step-loss:0.7256-acc:0.8565-val_loss:0.6717-val_acc:0.8731
Epoch 140/5000
77s 155ms/step-loss:0.7240-acc:0.8548-val_loss:0.6846-val_acc:0.8727
Epoch 141/5000
77s 155ms/step-loss:0.7244-acc:0.8580-val_loss:0.6681-val_acc:0.8793
Epoch 142/5000
77s 155ms/step-loss:0.7270-acc:0.8555-val_loss:0.6734-val_acc:0.8781
Epoch 143/5000
77s 154ms/step-loss:0.7295-acc:0.8567-val_loss:0.6731-val_acc:0.8783
Epoch 144/5000
77s 154ms/step-loss:0.7271-acc:0.8549-val_loss:0.6803-val_acc:0.8758
Epoch 145/5000
77s 154ms/step-loss:0.7257-acc:0.8544-val_loss:0.6675-val_acc:0.8763
Epoch 146/5000
78s 157ms/step-loss:0.7257-acc:0.8547-val_loss:0.6824-val_acc:0.8709
Epoch 147/5000
78s 156ms/step-loss:0.7259-acc:0.8550-val_loss:0.6763-val_acc:0.8733
Epoch 148/5000
77s 155ms/step-loss:0.7291-acc:0.8542-val_loss:0.6908-val_acc:0.8683
Epoch 149/5000
78s 156ms/step-loss:0.7262-acc:0.8571-val_loss:0.6593-val_acc:0.8818
Epoch 150/5000
78s 157ms/step-loss:0.7260-acc:0.8565-val_loss:0.6801-val_acc:0.8763
Epoch 151/5000
78s 156ms/step-loss:0.7256-acc:0.8574-val_loss:0.6660-val_acc:0.8800
Epoch 152/5000
78s 155ms/step-loss:0.7201-acc:0.8602-val_loss:0.6659-val_acc:0.8799
Epoch 153/5000
78s 156ms/step-loss:0.7257-acc:0.8561-val_loss:0.6740-val_acc:0.8764
Epoch 154/5000
77s 154ms/step-loss:0.7273-acc:0.8552-val_loss:0.6778-val_acc:0.8751
Epoch 155/5000
77s 154ms/step-loss:0.7214-acc:0.8579-val_loss:0.6649-val_acc:0.8803
Epoch 156/5000
77s 154ms/step-loss:0.7220-acc:0.8558-val_loss:0.6748-val_acc:0.8782
Epoch 157/5000
77s 154ms/step-loss:0.7227-acc:0.8584-val_loss:0.6671-val_acc:0.8779
Epoch 158/5000
77s 154ms/step-loss:0.7264-acc:0.8558-val_loss:0.6607-val_acc:0.8780
Epoch 159/5000
77s 154ms/step-loss:0.7202-acc:0.8597-val_loss:0.6702-val_acc:0.8785
Epoch 160/5000
77s 154ms/step-loss:0.7211-acc:0.8563-val_loss:0.6630-val_acc:0.8812
Epoch 161/5000
77s 154ms/step-loss:0.7229-acc:0.8579-val_loss:0.6743-val_acc:0.8769
Epoch 162/5000
77s 154ms/step-loss:0.7216-acc:0.8571-val_loss:0.6772-val_acc:0.8761
Epoch 163/5000
77s 154ms/step-loss:0.7168-acc:0.8599-val_loss:0.6661-val_acc:0.8786
Epoch 164/5000
77s 154ms/step-loss:0.7208-acc:0.8573-val_loss:0.6801-val_acc:0.8763
Epoch 165/5000
77s 154ms/step-loss:0.7240-acc:0.8590-val_loss:0.6678-val_acc:0.8781
Epoch 166/5000
79s 158ms/step-loss:0.7154-acc:0.8621-val_loss:0.6768-val_acc:0.8744
Epoch 167/5000
78s 155ms/step-loss:0.7177-acc:0.8600-val_loss:0.6536-val_acc:0.8816
Epoch 168/5000
78s 155ms/step-loss:0.7160-acc:0.8585-val_loss:0.7057-val_acc:0.8640
Epoch 169/5000
77s 155ms/step-loss:0.7196-acc:0.8598-val_loss:0.6517-val_acc:0.8854
Epoch 170/5000
77s 154ms/step-loss:0.7153-acc:0.8581-val_loss:0.6592-val_acc:0.8844
Epoch 171/5000
77s 154ms/step-loss:0.7189-acc:0.8587-val_loss:0.6797-val_acc:0.8774
Epoch 172/5000
77s 154ms/step-loss:0.7182-acc:0.8583-val_loss:0.6625-val_acc:0.8767
Epoch 173/5000
77s 154ms/step-loss:0.7161-acc:0.8597-val_loss:0.6863-val_acc:0.8726
Epoch 174/5000
77s 154ms/step-loss:0.7171-acc:0.8602-val_loss:0.6963-val_acc:0.8669
Epoch 175/5000
77s 154ms/step-loss:0.7211-acc:0.8589-val_loss:0.6638-val_acc:0.8830
Epoch 176/5000
77s 154ms/step-loss:0.7149-acc:0.8607-val_loss:0.6717-val_acc:0.8723
Epoch 177/5000
77s 153ms/step-loss:0.7135-acc:0.8619-val_loss:0.7025-val_acc:0.8681
Epoch 178/5000
77s 154ms/step-loss:0.7175-acc:0.8587-val_loss:0.6832-val_acc:0.8726
Epoch 179/5000
77s 154ms/step-loss:0.7155-acc:0.8598-val_loss:0.6633-val_acc:0.8790
Epoch 180/5000
77s 154ms/step-loss:0.7189-acc:0.8598-val_loss:0.6783-val_acc:0.8756
Epoch 181/5000
77s 154ms/step-loss:0.7187-acc:0.8605-val_loss:0.6682-val_acc:0.8805
Epoch 182/5000
77s 154ms/step-loss:0.7174-acc:0.8607-val_loss:0.6748-val_acc:0.8792
Epoch 183/5000
77s 154ms/step-loss:0.7133-acc:0.8619-val_loss:0.6691-val_acc:0.8773
Epoch 184/5000
77s 154ms/step-loss:0.7180-acc:0.8589-val_loss:0.6698-val_acc:0.8804
Epoch 185/5000
77s 154ms/step-loss:0.7133-acc:0.8629-val_loss:0.6720-val_acc:0.8753
Epoch 186/5000
77s 154ms/step-loss:0.7128-acc:0.8615-val_loss:0.6919-val_acc:0.8699
Epoch 187/5000
77s 154ms/step-loss:0.7196-acc:0.8598-val_loss:0.6849-val_acc:0.8721
Epoch 188/5000
77s 154ms/step-loss:0.7207-acc:0.8581-val_loss:0.6754-val_acc:0.8780
Epoch 189/5000
77s 154ms/step-loss:0.7150-acc:0.8619-val_loss:0.6571-val_acc:0.8837
Epoch 190/5000
77s 154ms/step-loss:0.7159-acc:0.8617-val_loss:0.6698-val_acc:0.8783
Epoch 191/5000
77s 154ms/step-loss:0.7158-acc:0.8606-val_loss:0.6782-val_acc:0.8772
Epoch 192/5000
77s 153ms/step-loss:0.7121-acc:0.8609-val_loss:0.6745-val_acc:0.8786
Epoch 193/5000
77s 154ms/step-loss:0.7137-acc:0.8624-val_loss:0.6800-val_acc:0.8765
Epoch 194/5000
77s 154ms/step-loss:0.7158-acc:0.8607-val_loss:0.6836-val_acc:0.8734
Epoch 195/5000
77s 153ms/step-loss:0.7067-acc:0.8640-val_loss:0.6691-val_acc:0.8784
Epoch 196/5000
77s 154ms/step-loss:0.7111-acc:0.8629-val_loss:0.6716-val_acc:0.8759
Epoch 197/5000
77s 154ms/step-loss:0.7139-acc:0.8611-val_loss:0.6686-val_acc:0.8777
Epoch 198/5000
77s 154ms/step-loss:0.7134-acc:0.8621-val_loss:0.6709-val_acc:0.8767
Epoch 199/5000
77s 154ms/step-loss:0.7101-acc:0.8625-val_loss:0.6513-val_acc:0.8863
Epoch 200/5000
77s 154ms/step-loss:0.7128-acc:0.8617-val_loss:0.6713-val_acc:0.8768
Epoch 201/5000
77s 154ms/step-loss:0.7171-acc:0.8620-val_loss:0.6620-val_acc:0.8830
Epoch 202/5000
77s 153ms/step-loss:0.7122-acc:0.8617-val_loss:0.6694-val_acc:0.8821
Epoch 203/5000
77s 154ms/step-loss:0.7127-acc:0.8604-val_loss:0.6717-val_acc:0.8797
Epoch 204/5000
77s 154ms/step-loss:0.7103-acc:0.8634-val_loss:0.6683-val_acc:0.8826
Epoch 205/5000
77s 154ms/step-loss:0.7123-acc:0.8612-val_loss:0.6576-val_acc:0.8831
Epoch 206/5000
77s 154ms/step-loss:0.7078-acc:0.8632-val_loss:0.6453-val_acc:0.8842
Epoch 207/5000
77s 154ms/step-loss:0.7135-acc:0.8623-val_loss:0.6683-val_acc:0.8804
Epoch 208/5000
77s 154ms/step-loss:0.7038-acc:0.8655-val_loss:0.6795-val_acc:0.8755
Epoch 209/5000
77s 154ms/step-loss:0.7160-acc:0.8607-val_loss:0.6709-val_acc:0.8773
Epoch 210/5000
77s 154ms/step-loss:0.7122-acc:0.8629-val_loss:0.6917-val_acc:0.8718
Epoch 211/5000
77s 154ms/step-loss:0.7064-acc:0.8643-val_loss:0.6831-val_acc:0.8701
Epoch 212/5000
77s 154ms/step-loss:0.7090-acc:0.8629-val_loss:0.6475-val_acc:0.8875
Epoch 213/5000
77s 154ms/step-loss:0.7086-acc:0.8621-val_loss:0.6740-val_acc:0.8741
Epoch 214/5000
77s 154ms/step-loss:0.7105-acc:0.8611-val_loss:0.6682-val_acc:0.8792
Epoch 215/5000
77s 154ms/step-loss:0.7129-acc:0.8616-val_loss:0.6930-val_acc:0.8682
Epoch 216/5000
77s 154ms/step-loss:0.7105-acc:0.8632-val_loss:0.6647-val_acc:0.8776
Epoch 217/5000
77s 154ms/step-loss:0.7086-acc:0.8634-val_loss:0.6555-val_acc:0.8832
Epoch 218/5000
77s 154ms/step-loss:0.7128-acc:0.8634-val_loss:0.6665-val_acc:0.8780
Epoch 219/5000
77s 153ms/step-loss:0.7050-acc:0.8641-val_loss:0.6698-val_acc:0.8800
Epoch 220/5000
77s 154ms/step-loss:0.7042-acc:0.8628-val_loss:0.6882-val_acc:0.8706
Epoch 221/5000
77s 154ms/step-loss:0.7098-acc:0.8615-val_loss:0.6649-val_acc:0.8802
Epoch 222/5000
77s 154ms/step-loss:0.7053-acc:0.8648-val_loss:0.6672-val_acc:0.8808
Epoch 223/5000
77s 154ms/step-loss:0.7064-acc:0.8638-val_loss:0.6609-val_acc:0.8823
Epoch 224/5000
77s 154ms/step-loss:0.7071-acc:0.8627-val_loss:0.6677-val_acc:0.8812
Epoch 225/5000
77s 154ms/step-loss:0.7049-acc:0.8655-val_loss:0.6656-val_acc:0.8784
Epoch 226/5000
77s 154ms/step-loss:0.7065-acc:0.8649-val_loss:0.6582-val_acc:0.8839
Epoch 227/5000
77s 154ms/step-loss:0.7049-acc:0.8644-val_loss:0.6812-val_acc:0.8763
Epoch 228/5000
77s 154ms/step-loss:0.7052-acc:0.8657-val_loss:0.6639-val_acc:0.8794
Epoch 229/5000
77s 154ms/step-loss:0.7054-acc:0.8654-val_loss:0.6662-val_acc:0.8816
Epoch 230/5000
77s 154ms/step-loss:0.7096-acc:0.8639-val_loss:0.6789-val_acc:0.8752
Epoch 231/5000
77s 154ms/step-loss:0.7049-acc:0.8667-val_loss:0.6748-val_acc:0.8768
Epoch 232/5000
77s 154ms/step-loss:0.7047-acc:0.8654-val_loss:0.6710-val_acc:0.8773
Epoch 233/5000
78s 155ms/step-loss:0.7051-acc:0.8648-val_loss:0.6516-val_acc:0.8839
Epoch 234/5000
77s 155ms/step-loss:0.7056-acc:0.8619-val_loss:0.6996-val_acc:0.8685
Epoch 235/5000
77s 155ms/step-loss:0.7043-acc:0.8652-val_loss:0.6481-val_acc:0.8843
Epoch 236/5000
77s 155ms/step-loss:0.7038-acc:0.8638-val_loss:0.6760-val_acc:0.8808
Epoch 237/5000
77s 155ms/step-loss:0.7035-acc:0.8660-val_loss:0.6597-val_acc:0.8833
Epoch 238/5000
77s 155ms/step-loss:0.7042-acc:0.8642-val_loss:0.6615-val_acc:0.8825
Epoch 239/5000
77s 155ms/step-loss:0.7061-acc:0.8645-val_loss:0.6715-val_acc:0.8753
Epoch 240/5000
77s 155ms/step-loss:0.7057-acc:0.8648-val_loss:0.6609-val_acc:0.8834
Epoch 241/5000
77s 155ms/step-loss:0.6990-acc:0.8671-val_loss:0.6591-val_acc:0.8849
Epoch 242/5000
77s 155ms/step-loss:0.7092-acc:0.8638-val_loss:0.6439-val_acc:0.8888
Epoch 243/5000
77s 155ms/step-loss:0.7043-acc:0.8650-val_loss:0.6699-val_acc:0.8803
Epoch 244/5000
77s 155ms/step-loss:0.7055-acc:0.8641-val_loss:0.6740-val_acc:0.8780
Epoch 245/5000
78s 155ms/step-loss:0.7010-acc:0.8668-val_loss:0.6673-val_acc:0.8807
Epoch 246/5000
78s 155ms/step-loss:0.7043-acc:0.8649-val_loss:0.6574-val_acc:0.8857
Epoch 247/5000
77s 155ms/step-loss:0.7071-acc:0.8643-val_loss:0.6640-val_acc:0.8831
Epoch 248/5000
78s 155ms/step-loss:0.7048-acc:0.8664-val_loss:0.6647-val_acc:0.8825
Epoch 249/5000
77s 155ms/step-loss:0.7033-acc:0.8649-val_loss:0.6821-val_acc:0.8750
Epoch 250/5000
77s 155ms/step-loss:0.7035-acc:0.8665-val_loss:0.6776-val_acc:0.8757
Epoch 251/5000
77s 155ms/step-loss:0.7050-acc:0.8643-val_loss:0.6857-val_acc:0.8721
Epoch 252/5000
78s 155ms/step-loss:0.7044-acc:0.8664-val_loss:0.6780-val_acc:0.8746
Epoch 253/5000
78s 155ms/step-loss:0.7033-acc:0.8657-val_loss:0.6739-val_acc:0.8799
Epoch 254/5000
78s 155ms/step-loss:0.7057-acc:0.8670-val_loss:0.6654-val_acc:0.8812
Epoch 255/5000
77s 155ms/step-loss:0.7065-acc:0.8656-val_loss:0.6798-val_acc:0.8752
Epoch 256/5000
78s 155ms/step - loss:0.7033 - acc:0.8656 - val_loss:0.6670 - val_acc:0.8814
Epoch 257/5000
78s 155ms/step - loss:0.7041 - acc:0.8648 - val_loss:0.6699 - val_acc:0.8823
Epoch 258/5000
77s 155ms/step - loss:0.6975 - acc:0.8682 - val_loss:0.6650 - val_acc:0.8792
Epoch 259/5000
78s 155ms/step - loss:0.7007 - acc:0.8681 - val_loss:0.6572 - val_acc:0.8843
Epoch 260/5000
77s 155ms/step - loss:0.6987 - acc:0.8668 - val_loss:0.6633 - val_acc:0.8820
Epoch 261/5000
77s 155ms/step - loss:0.7003 - acc:0.8667 - val_loss:0.6728 - val_acc:0.8835
Epoch 262/5000
77s 155ms/step - loss:0.7007 - acc:0.8669 - val_loss:0.6813 - val_acc:0.8791
Epoch 263/5000
78s 155ms/step - loss:0.7036 - acc:0.8659 - val_loss:0.6670 - val_acc:0.8805
Epoch 264/5000
78s 155ms/step - loss:0.7001 - acc:0.8667 - val_loss:0.6954 - val_acc:0.8714
Epoch 265/5000
77s 155ms/step - loss:0.7016 - acc:0.8678 - val_loss:0.6727 - val_acc:0.8774
Epoch 266/5000
78s 155ms/step - loss:0.7005 - acc:0.8664 - val_loss:0.6804 - val_acc:0.8751
Epoch 267/5000
77s 155ms/step - loss:0.7004 - acc:0.8665 - val_loss:0.6690 - val_acc:0.8828
Epoch 268/5000
77s 155ms/step - loss:0.7030 - acc:0.8672 - val_loss:0.6656 - val_acc:0.8791
Epoch 269/5000
78s 155ms/step - loss:0.7049 - acc:0.8659 - val_loss:0.6549 - val_acc:0.8850
Epoch 270/5000
78s 155ms/step - loss:0.7012 - acc:0.8669 - val_loss:0.6743 - val_acc:0.8775
Epoch 271/5000
77s 155ms/step - loss:0.7024 - acc:0.8673 - val_loss:0.6573 - val_acc:0.8847
Epoch 272/5000
77s 155ms/step - loss:0.6991 - acc:0.8676 - val_loss:0.6792 - val_acc:0.8737
Epoch 273/5000
77s 155ms/step - loss:0.7014 - acc:0.8664 - val_loss:0.6658 - val_acc:0.8832
Epoch 274/5000
77s 155ms/step - loss:0.6974 - acc:0.8688 - val_loss:0.6721 - val_acc:0.8805
Epoch 275/5000
77s 155ms/step - loss:0.6985 - acc:0.8683 - val_loss:0.6641 - val_acc:0.8829
Epoch 276/5000
77s 155ms/step - loss:0.6971 - acc:0.8678 - val_loss:0.6491 - val_acc:0.8868
Epoch 277/5000
77s 155ms/step - loss:0.7014 - acc:0.8653 - val_loss:0.6572 - val_acc:0.8849
Epoch 278/5000
77s 155ms/step - loss:0.6943 - acc:0.8698 - val_loss:0.6613 - val_acc:0.8827
Epoch 279/5000
77s 155ms/step - loss:0.6974 - acc:0.8690 - val_loss:0.6941 - val_acc:0.8707
Epoch 280/5000
77s 155ms/step - loss:0.6994 - acc:0.8688 - val_loss:0.6803 - val_acc:0.8740
Epoch 281/5000
78s 155ms/step - loss:0.6995 - acc:0.8693 - val_loss:0.6676 - val_acc:0.8803
Epoch 282/5000
77s 155ms/step - loss:0.7024 - acc:0.8660 - val_loss:0.6690 - val_acc:0.8795
Epoch 283/5000
78s 155ms/step - loss:0.6965 - acc:0.8688 - val_loss:0.6608 - val_acc:0.8861
Epoch 284/5000
77s 155ms/step - loss:0.6945 - acc:0.8700 - val_loss:0.6706 - val_acc:0.8777
Epoch 285/5000
77s 155ms/step - loss:0.7016 - acc:0.8672 - val_loss:0.6635 - val_acc:0.8812
Epoch 286/5000
78s 155ms/step - loss:0.6989 - acc:0.8673 - val_loss:0.6629 - val_acc:0.8844
Epoch 287/5000
77s 155ms/step - loss:0.7025 - acc:0.8665 - val_loss:0.6578 - val_acc:0.8829
Epoch 288/5000
77s 155ms/step - loss:0.7009 - acc:0.8667 - val_loss:0.6617 - val_acc:0.8814
Epoch 289/5000
77s 155ms/step - loss:0.6981 - acc:0.8687 - val_loss:0.6838 - val_acc:0.8745
Epoch 290/5000
77s 155ms/step - loss:0.7025 - acc:0.8667 - val_loss:0.6643 - val_acc:0.8828
Epoch 291/5000
77s 155ms/step - loss:0.6984 - acc:0.8683 - val_loss:0.6492 - val_acc:0.8867
Epoch 292/5000
77s 155ms/step - loss:0.6973 - acc:0.8692 - val_loss:0.6480 - val_acc:0.8868
Epoch 293/5000
78s 155ms/step - loss:0.6918 - acc:0.8712 - val_loss:0.6666 - val_acc:0.8834
Epoch 294/5000
77s 155ms/step - loss:0.6997 - acc:0.8672 - val_loss:0.6919 - val_acc:0.8714
Epoch 295/5000
77s 155ms/step - loss:0.6990 - acc:0.8692 - val_loss:0.6528 - val_acc:0.8848
Epoch 296/5000
77s 155ms/step - loss:0.6974 - acc:0.8694 - val_loss:0.6756 - val_acc:0.8767
Epoch 297/5000
77s 155ms/step - loss:0.6972 - acc:0.8669 - val_loss:0.6588 - val_acc:0.8849
Epoch 298/5000
77s 155ms/step - loss:0.6992 - acc:0.8689 - val_loss:0.6678 - val_acc:0.8807
Epoch 299/5000
78s 155ms/step - loss:0.6936 - acc:0.8700 - val_loss:0.6497 - val_acc:0.8875
Epoch 300/5000
77s 155ms/step - loss:0.6958 - acc:0.8695 - val_loss:0.6750 - val_acc:0.8788
Epoch 301/5000
77s 155ms/step - loss:0.7019 - acc:0.8670 - val_loss:0.6845 - val_acc:0.8746
Epoch 302/5000
78s 155ms/step - loss:0.6974 - acc:0.8676 - val_loss:0.6784 - val_acc:0.8783
Epoch 303/5000
78s 155ms/step - loss:0.6962 - acc:0.8690 - val_loss:0.6511 - val_acc:0.8864
Epoch 304/5000
77s 155ms/step - loss:0.6995 - acc:0.8689 - val_loss:0.6477 - val_acc:0.8922
Epoch 305/5000
77s 155ms/step - loss:0.6979 - acc:0.8693 - val_loss:0.6682 - val_acc:0.8800
Epoch 306/5000
77s 155ms/step - loss:0.6963 - acc:0.8689 - val_loss:0.6852 - val_acc:0.8775
Epoch 307/5000
78s 155ms/step - loss:0.6956 - acc:0.8703 - val_loss:0.6773 - val_acc:0.8776
Epoch 308/5000
77s 155ms/step - loss:0.6969 - acc:0.8692 - val_loss:0.6762 - val_acc:0.8760
Epoch 309/5000
78s 155ms/step - loss:0.6962 - acc:0.8700 - val_loss:0.6636 - val_acc:0.8826
Epoch 310/5000
78s 155ms/step - loss:0.6941 - acc:0.8700 - val_loss:0.6491 - val_acc:0.8877
Epoch 311/5000
77s 155ms/step - loss:0.6922 - acc:0.8696 - val_loss:0.6534 - val_acc:0.8848
Epoch 312/5000
77s 155ms/step - loss:0.6936 - acc:0.8691 - val_loss:0.6530 - val_acc:0.8858
Epoch 313/5000
77s 155ms/step - loss:0.6985 - acc:0.8692 - val_loss:0.6421 - val_acc:0.8904
Epoch 314/5000
77s 155ms/step - loss:0.7032 - acc:0.8679 - val_loss:0.6421 - val_acc:0.8906
Epoch 315/5000
77s 155ms/step - loss:0.6911 - acc:0.8714 - val_loss:0.6497 - val_acc:0.8868
Epoch 316/5000
77s 155ms/step - loss:0.6993 - acc:0.8690 - val_loss:0.6567 - val_acc:0.8860
Epoch 317/5000
77s 155ms/step - loss:0.6943 - acc:0.8704 - val_loss:0.6646 - val_acc:0.8847
Epoch 318/5000
77s 155ms/step - loss:0.6950 - acc:0.8709 - val_loss:0.6642 - val_acc:0.8801
Epoch 319/5000
77s 155ms/step - loss:0.7008 - acc:0.8676 - val_loss:0.6778 - val_acc:0.8788
Epoch 320/5000
78s 155ms/step - loss:0.6947 - acc:0.8717 - val_loss:0.6420 - val_acc:0.8915
Epoch 321/5000
77s 155ms/step - loss:0.6945 - acc:0.8702 - val_loss:0.6391 - val_acc:0.8939
Epoch 322/5000
77s 155ms/step - loss:0.6917 - acc:0.8712 - val_loss:0.6846 - val_acc:0.8776
Epoch 323/5000
78s 155ms/step - loss:0.6968 - acc:0.8687 - val_loss:0.6690 - val_acc:0.8842
Epoch 324/5000
77s 155ms/step - loss:0.6949 - acc:0.8708 - val_loss:0.6511 - val_acc:0.8841
Epoch 325/5000
78s 155ms/step - loss:0.6947 - acc:0.8701 - val_loss:0.6517 - val_acc:0.8892
Epoch 326/5000
77s 155ms/step - loss:0.6958 - acc:0.8670 - val_loss:0.6714 - val_acc:0.8804
Epoch 327/5000
77s 155ms/step - loss:0.6959 - acc:0.8694 - val_loss:0.6856 - val_acc:0.8744
Epoch 328/5000
78s 155ms/step - loss:0.6903 - acc:0.8703 - val_loss:0.6671 - val_acc:0.8798
Epoch 329/5000
77s 155ms/step - loss:0.6921 - acc:0.8705 - val_loss:0.6651 - val_acc:0.8860
Epoch 330/5000
77s 155ms/step - loss:0.6956 - acc:0.8693 - val_loss:0.6903 - val_acc:0.8742
Epoch 331/5000
77s 155ms/step - loss:0.6951 - acc:0.8692 - val_loss:0.6567 - val_acc:0.8875
Epoch 332/5000
78s 155ms/step - loss:0.6924 - acc:0.8714 - val_loss:0.6648 - val_acc:0.8825
Epoch 333/5000
77s 155ms/step - loss:0.6998 - acc:0.8689 - val_loss:0.6581 - val_acc:0.8837
Epoch 334/5000
77s 155ms/step - loss:0.6931 - acc:0.8703 - val_loss:0.6723 - val_acc:0.8789
Epoch 335/5000
78s 155ms/step - loss:0.6987 - acc:0.8698 - val_loss:0.6769 - val_acc:0.8788
Epoch 336/5000
77s 155ms/step - loss:0.6917 - acc:0.8707 - val_loss:0.6494 - val_acc:0.8886
Epoch 337/5000
78s 155ms/step - loss:0.6906 - acc:0.8724 - val_loss:0.6733 - val_acc:0.8784
Epoch 338/5000
77s 155ms/step - loss:0.6948 - acc:0.8704 - val_loss:0.6510 - val_acc:0.8882
Epoch 339/5000
78s 155ms/step - loss:0.6908 - acc:0.8714 - val_loss:0.6726 - val_acc:0.8794
Epoch 340/5000
77s 155ms/step - loss:0.6919 - acc:0.8726 - val_loss:0.6660 - val_acc:0.8814
Epoch 341/5000
78s 155ms/step - loss:0.6947 - acc:0.8704 - val_loss:0.6462 - val_acc:0.8891
Epoch 342/5000
78s 155ms/step - loss:0.6911 - acc:0.8721 - val_loss:0.6821 - val_acc:0.8761
Epoch 343/5000
78s 155ms/step - loss:0.6962 - acc:0.8683 - val_loss:0.6709 - val_acc:0.8791
Epoch 344/5000
77s 155ms/step - loss:0.6938 - acc:0.8701 - val_loss:0.6776 - val_acc:0.8769
Epoch 345/5000
77s 155ms/step - loss:0.6917 - acc:0.8717 - val_loss:0.6769 - val_acc:0.8779
Epoch 346/5000
78s 155ms/step - loss:0.6915 - acc:0.8697 - val_loss:0.6473 - val_acc:0.8895
Epoch 347/5000
77s 155ms/step - loss:0.6918 - acc:0.8702 - val_loss:0.6543 - val_acc:0.8865
Epoch 348/5000
77s 155ms/step - loss:0.6907 - acc:0.8725 - val_loss:0.6867 - val_acc:0.8748
Epoch 349/5000
77s 155ms/step - loss:0.6962 - acc:0.8687 - val_loss:0.6580 - val_acc:0.8866
Epoch 350/5000
77s 155ms/step - loss:0.6922 - acc:0.8704 - val_loss:0.6766 - val_acc:0.8766
Epoch 351/5000
78s 155ms/step - loss:0.6901 - acc:0.8708 - val_loss:0.6742 - val_acc:0.8797
Epoch 352/5000
77s 155ms/step - loss:0.6910 - acc:0.8723 - val_loss:0.6587 - val_acc:0.8828
Epoch 353/5000
78s 155ms/step - loss:0.6941 - acc:0.8717 - val_loss:0.6960 - val_acc:0.8708
Epoch 354/5000
77s 155ms/step - loss:0.6929 - acc:0.8699 - val_loss:0.6612 - val_acc:0.8853
Epoch 355/5000
77s 155ms/step - loss:0.6947 - acc:0.8716 - val_loss:0.6795 - val_acc:0.8772
Epoch 356/5000
77s 155ms/step - loss:0.6958 - acc:0.8717 - val_loss:0.6750 - val_acc:0.8788
Epoch 357/5000
77s 155ms/step - loss:0.6885 - acc:0.8721 - val_loss:0.6617 - val_acc:0.8830
Epoch 358/5000
78s 155ms/step - loss:0.6851 - acc:0.8742 - val_loss:0.6671 - val_acc:0.8781
Epoch 359/5000
78s 155ms/step - loss:0.6898 - acc:0.8696 - val_loss:0.6511 - val_acc:0.8861
Epoch 360/5000
77s 155ms/step - loss:0.6967 - acc:0.8681 - val_loss:0.6567 - val_acc:0.8867
Epoch 361/5000
77s 155ms/step - loss:0.6931 - acc:0.8700 - val_loss:0.7052 - val_acc:0.8687
Epoch 362/5000
77s 155ms/step - loss:0.6953 - acc:0.8702 - val_loss:0.6465 - val_acc:0.8923
Epoch 363/5000
77s 154ms/step - loss:0.6956 - acc:0.8695 - val_loss:0.6305 - val_acc:0.8971
Epoch 364/5000
77s 154ms/step - loss:0.6892 - acc:0.8712 - val_loss:0.6787 - val_acc:0.8796
Epoch 365/5000
77s 154ms/step - loss:0.6895 - acc:0.8729 - val_loss:0.6676 - val_acc:0.8837
Epoch 366/5000
77s 154ms/step - loss:0.6955 - acc:0.8705 - val_loss:0.6644 - val_acc:0.8825
Epoch 367/5000
77s 154ms/step - loss:0.6912 - acc:0.8723 - val_loss:0.6712 - val_acc:0.8805
Epoch 368/5000
77s 153ms/step - loss:0.6925 - acc:0.8720 - val_loss:0.6506 - val_acc:0.8871
Epoch 369/5000
77s 154ms/step - loss:0.6904 - acc:0.8724 - val_loss:0.6560 - val_acc:0.8857
Epoch 370/5000
77s 154ms/step - loss:0.6886 - acc:0.8724 - val_loss:0.6637 - val_acc:0.8838
Epoch 371/5000
77s 154ms/step - loss:0.6859 - acc:0.8745 - val_loss:0.6669 - val_acc:0.8853
Epoch 372/5000
77s 154ms/step - loss:0.6888 - acc:0.8731 - val_loss:0.6485 - val_acc:0.8884
Epoch 373/5000
77s 154ms/step - loss:0.6877 - acc:0.8723 - val_loss:0.6571 - val_acc:0.8869
Epoch 374/5000
77s 154ms/step - loss:0.6895 - acc:0.8727 - val_loss:0.6762 - val_acc:0.8811
Epoch 375/5000
77s 153ms/step - loss:0.6924 - acc:0.8694 - val_loss:0.6716 - val_acc:0.8802
Epoch 376/5000
77s 154ms/step - loss:0.6912 - acc:0.8705 - val_loss:0.6669 - val_acc:0.8884
Epoch 377/5000
77s 154ms/step - loss:0.6885 - acc:0.8734 - val_loss:0.6551 - val_acc:0.8858
Epoch 378/5000
77s 154ms/step - loss:0.6916 - acc:0.8689 - val_loss:0.6692 - val_acc:0.8810
Epoch 379/5000
77s 154ms/step - loss:0.6892 - acc:0.8721 - val_loss:0.6846 - val_acc:0.8797
Epoch 380/5000
77s 154ms/step - loss:0.6996 - acc:0.8686 - val_loss:0.6645 - val_acc:0.8851
Epoch 381/5000
77s 154ms/step - loss:0.6925 - acc:0.8734 - val_loss:0.6541 - val_acc:0.8866
Epoch 382/5000
77s 154ms/step - loss:0.6929 - acc:0.8708 - val_loss:0.6599 - val_acc:0.8842
Epoch 383/5000
77s 154ms/step - loss:0.6972 - acc:0.8711 - val_loss:0.6536 - val_acc:0.8859
Epoch 384/5000
77s 154ms/step - loss:0.6874 - acc:0.8734 - val_loss:0.6531 - val_acc:0.8867
Epoch 385/5000
77s 154ms/step - loss:0.6940 - acc:0.8716 - val_loss:0.6656 - val_acc:0.8816
Epoch 386/5000
77s 153ms/step - loss:0.6853 - acc:0.8758 - val_loss:0.6791 - val_acc:0.8779
Epoch 387/5000
77s 154ms/step - loss:0.6880 - acc:0.8747 - val_loss:0.6615 - val_acc:0.8835
Epoch 388/5000
77s 154ms/step - loss:0.6850 - acc:0.8731 - val_loss:0.6602 - val_acc:0.8832
Epoch 389/5000
77s 154ms/step - loss:0.6890 - acc:0.8720 - val_loss:0.6566 - val_acc:0.8842
Epoch 390/5000
77s 154ms/step - loss:0.6863 - acc:0.8738 - val_loss:0.6814 - val_acc:0.8779
Epoch 391/5000
77s 154ms/step - loss:0.6940 - acc:0.8706 - val_loss:0.6519 - val_acc:0.8866
Epoch 392/5000
77s 154ms/step - loss:0.6857 - acc:0.8730 - val_loss:0.6509 - val_acc:0.8885
Epoch 393/5000
77s 154ms/step - loss:0.6915 - acc:0.8706 - val_loss:0.6633 - val_acc:0.8827
Epoch 394/5000
77s 154ms/step - loss:0.6909 - acc:0.8722 - val_loss:0.6619 - val_acc:0.8841
Epoch 395/5000
77s 154ms/step - loss:0.6877 - acc:0.8733 - val_loss:0.6826 - val_acc:0.8774
Epoch 396/5000
77s 154ms/step - loss:0.6941 - acc:0.8717 - val_loss:0.6372 - val_acc:0.8920
Epoch 397/5000
77s 154ms/step - loss:0.6870 - acc:0.8733 - val_loss:0.6681 - val_acc:0.8806
Epoch 398/5000
77s 154ms/step - loss:0.6878 - acc:0.8740 - val_loss:0.6686 - val_acc:0.8797
Epoch 399/5000
77s 154ms/step - loss:0.6923 - acc:0.8724 - val_loss:0.6524 - val_acc:0.8867
Epoch 400/5000
77s 154ms/step - loss:0.6900 - acc:0.8730 - val_loss:0.6754 - val_acc:0.8808
Epoch 401/5000
77s 154ms/step - loss:0.6924 - acc:0.8719 - val_loss:0.6570 - val_acc:0.8819
Epoch 402/5000
77s 153ms/step - loss:0.6906 - acc:0.8721 - val_loss:0.6717 - val_acc:0.8803
Epoch 403/5000
77s 154ms/step - loss:0.6871 - acc:0.8722 - val_loss:0.6586 - val_acc:0.8869
Epoch 404/5000
77s 154ms/step - loss:0.6876 - acc:0.8739 - val_loss:0.6576 - val_acc:0.8846
Epoch 405/5000
77s 154ms/step - loss:0.6886 - acc:0.8718 - val_loss:0.6742 - val_acc:0.8773
Epoch 406/5000
77s 154ms/step - loss:0.6844 - acc:0.8731 - val_loss:0.6549 - val_acc:0.8814
Epoch 407/5000
77s 154ms/step - loss:0.6910 - acc:0.8719 - val_loss:0.6778 - val_acc:0.8798
Epoch 408/5000
77s 154ms/step - loss:0.6917 - acc:0.8711 - val_loss:0.6612 - val_acc:0.8874
Epoch 409/5000
77s 154ms/step - loss:0.6872 - acc:0.8726 - val_loss:0.6490 - val_acc:0.8903
Epoch 410/5000
77s 154ms/step - loss:0.6931 - acc:0.8713 - val_loss:0.6500 - val_acc:0.8890
Epoch 411/5000
77s 154ms/step - loss:0.6852 - acc:0.8740 - val_loss:0.6654 - val_acc:0.8801
Epoch 412/5000
77s 154ms/step - loss:0.6905 - acc:0.8734 - val_loss:0.6788 - val_acc:0.8795
Epoch 413/5000
77s 154ms/step - loss:0.6889 - acc:0.8732 - val_loss:0.6511 - val_acc:0.8855
Epoch 414/5000
77s 154ms/step - loss:0.6884 - acc:0.8733 - val_loss:0.6630 - val_acc:0.8831
Epoch 415/5000
77s 154ms/step - loss:0.6904 - acc:0.8733 - val_loss:0.6667 - val_acc:0.8823
Epoch 416/5000
77s 154ms/step - loss:0.6872 - acc:0.8732 - val_loss:0.6826 - val_acc:0.8790
Epoch 417/5000
77s 154ms/step - loss:0.6893 - acc:0.8715 - val_loss:0.6645 - val_acc:0.8822
Epoch 418/5000
77s 153ms/step - loss:0.6915 - acc:0.8721 - val_loss:0.6428 - val_acc:0.8916
Epoch 419/5000
77s 154ms/step - loss:0.6925 - acc:0.8728 - val_loss:0.6605 - val_acc:0.8870
Epoch 420/5000
77s 154ms/step - loss:0.6916 - acc:0.8714 - val_loss:0.6503 - val_acc:0.8905
Epoch 421/5000
77s 154ms/step - loss:0.6912 - acc:0.8719 - val_loss:0.6260 - val_acc:0.8953
Epoch 422/5000
77s 154ms/step - loss:0.6824 - acc:0.8749 - val_loss:0.6716 - val_acc:0.8800
Epoch 423/5000
77s 154ms/step - loss:0.6857 - acc:0.8756 - val_loss:0.6709 - val_acc:0.8772
Epoch 424/5000
77s 154ms/step - loss:0.6910 - acc:0.8717 - val_loss:0.6628 - val_acc:0.8827
Epoch 425/5000
77s 154ms/step - loss:0.6869 - acc:0.8739 - val_loss:0.6865 - val_acc:0.8751
Epoch 426/5000
77s 154ms/step - loss:0.6904 - acc:0.8738 - val_loss:0.6621 - val_acc:0.8861
Epoch 427/5000
77s 154ms/step - loss:0.6915 - acc:0.8735 - val_loss:0.6622 - val_acc:0.8862
Epoch 428/5000
77s 154ms/step - loss:0.6863 - acc:0.8722 - val_loss:0.6572 - val_acc:0.8851
Epoch 429/5000
77s 154ms/step - loss:0.6877 - acc:0.8722 - val_loss:0.6473 - val_acc:0.8896
Epoch 430/5000
77s 154ms/step - loss:0.6891 - acc:0.8737 - val_loss:0.6699 - val_acc:0.8829
Epoch 431/5000
77s 154ms/step - loss:0.6915 - acc:0.8710 - val_loss:0.6561 - val_acc:0.8834
Epoch 432/5000
77s 154ms/step - loss:0.6849 - acc:0.8739 - val_loss:0.6476 - val_acc:0.8863
Epoch 433/5000
77s 154ms/step - loss:0.6890 - acc:0.8730 - val_loss:0.6679 - val_acc:0.8827
Epoch 434/5000
77s 154ms/step - loss:0.6910 - acc:0.8717 - val_loss:0.6482 - val_acc:0.8864
Epoch 435/5000
77s 154ms/step - loss:0.6866 - acc:0.8736 - val_loss:0.6579 - val_acc:0.8841
Epoch 436/5000
77s 154ms/step - loss:0.6888 - acc:0.8732 - val_loss:0.6615 - val_acc:0.8804
Epoch 437/5000
77s 154ms/step - loss:0.6875 - acc:0.8734 - val_loss:0.6854 - val_acc:0.8791
Epoch 438/5000
77s 154ms/step - loss:0.6917 - acc:0.8719 - val_loss:0.6664 - val_acc:0.8847
Epoch 439/5000
77s 154ms/step - loss:0.6935 - acc:0.8706 - val_loss:0.6469 - val_acc:0.8897
Epoch 440/5000
77s 154ms/step - loss:0.6890 - acc:0.8750 - val_loss:0.6735 - val_acc:0.8830
Epoch 441/5000
77s 154ms/step - loss:0.6907 - acc:0.8719 - val_loss:0.6752 - val_acc:0.8802
Epoch 442/5000
77s 154ms/step - loss:0.6882 - acc:0.8747 - val_loss:0.6486 - val_acc:0.8879
Epoch 443/5000
77s 154ms/step - loss:0.6875 - acc:0.8736 - val_loss:0.6621 - val_acc:0.8826
Epoch 444/5000
77s 154ms/step - loss:0.6865 - acc:0.8732 - val_loss:0.6650 - val_acc:0.8854
Epoch 445/5000
77s 154ms/step - loss:0.6938 - acc:0.8702 - val_loss:0.6406 - val_acc:0.8921
Epoch 446/5000
77s 154ms/step - loss:0.6891 - acc:0.8726 - val_loss:0.6464 - val_acc:0.8937
Epoch 447/5000
77s 154ms/step - loss:0.6890 - acc:0.8725 - val_loss:0.6449 - val_acc:0.8902
Epoch 448/5000
77s 154ms/step - loss:0.6920 - acc:0.8716 - val_loss:0.6620 - val_acc:0.8858
Epoch 449/5000
77s 154ms/step - loss:0.6881 - acc:0.8744 - val_loss:0.6399 - val_acc:0.8926
Epoch 450/5000
77s 154ms/step - loss:0.6872 - acc:0.8735 - val_loss:0.6694 - val_acc:0.8836
Epoch 451/5000
77s 154ms/step - loss:0.6938 - acc:0.8697 - val_loss:0.6440 - val_acc:0.8905
Epoch 452/5000
77s 154ms/step - loss:0.6914 - acc:0.8727 - val_loss:0.6423 - val_acc:0.8856
Epoch 453/5000
77s 154ms/step - loss:0.6845 - acc:0.8746 - val_loss:0.6852 - val_acc:0.8734
Epoch 454/5000
77s 154ms/step - loss:0.6846 - acc:0.8745 - val_loss:0.6488 - val_acc:0.8892
Epoch 455/5000
77s 154ms/step - loss:0.6849 - acc:0.8761 - val_loss:0.6750 - val_acc:0.8782
Epoch 456/5000
77s 154ms/step - loss:0.6879 - acc:0.8728 - val_loss:0.6682 - val_acc:0.8815
Epoch 457/5000
77s 154ms/step - loss:0.6884 - acc:0.8723 - val_loss:0.6584 - val_acc:0.8852
Epoch 458/5000
77s 154ms/step - loss:0.6877 - acc:0.8742 - val_loss:0.6657 - val_acc:0.8841
Epoch 459/5000
77s 154ms/step - loss:0.6946 - acc:0.8708 - val_loss:0.6339 - val_acc:0.8915
Epoch 460/5000
77s 154ms/step - loss:0.6861 - acc:0.8745 - val_loss:0.6607 - val_acc:0.8820
Epoch 461/5000
77s 154ms/step - loss:0.6851 - acc:0.8750 - val_loss:0.6594 - val_acc:0.8849
Epoch 462/5000
77s 154ms/step - loss:0.6900 - acc:0.8724 - val_loss:0.6511 - val_acc:0.8886
Epoch 463/5000
77s 154ms/step - loss:0.6863 - acc:0.8749 - val_loss:0.6682 - val_acc:0.8837
Epoch 464/5000
77s 154ms/step - loss:0.6886 - acc:0.8722 - val_loss:0.6534 - val_acc:0.8865
Epoch 465/5000
77s 154ms/step - loss:0.6808 - acc:0.8763 - val_loss:0.6723 - val_acc:0.8836
Epoch 466/5000
77s 154ms/step - loss:0.6869 - acc:0.8734 - val_loss:0.6576 - val_acc:0.8862
Epoch 467/5000
77s 154ms/step - loss:0.6859 - acc:0.8747 - val_loss:0.6567 - val_acc:0.8881
Epoch 468/5000
77s 154ms/step - loss:0.6849 - acc:0.8736 - val_loss:0.6570 - val_acc:0.8840
Epoch 469/5000
77s 154ms/step - loss:0.6876 - acc:0.8738 - val_loss:0.6499 - val_acc:0.8893
Epoch 470/5000
77s 154ms/step - loss:0.6889 - acc:0.8725 - val_loss:0.6572 - val_acc:0.8873
Epoch 471/5000
77s 154ms/step - loss:0.6887 - acc:0.8721 - val_loss:0.6576 - val_acc:0.8871
Epoch 472/5000
77s 154ms/step - loss:0.6857 - acc:0.8749 - val_loss:0.6491 - val_acc:0.8910
Epoch 473/5000
77s 153ms/step - loss:0.6843 - acc:0.8754 - val_loss:0.6712 - val_acc:0.8797
Epoch 474/5000
77s 154ms/step - loss:0.6875 - acc:0.8729 - val_loss:0.6721 - val_acc:0.8812
Epoch 475/5000
77s 154ms/step - loss:0.6865 - acc:0.8742 - val_loss:0.6723 - val_acc:0.8828
Epoch 476/5000
77s 154ms/step - loss:0.6886 - acc:0.8731 - val_loss:0.6330 - val_acc:0.8934
Epoch 477/5000
77s 153ms/step - loss:0.6854 - acc:0.8752 - val_loss:0.6432 - val_acc:0.8900
Epoch 478/5000
77s 154ms/step - loss:0.6867 - acc:0.8754 - val_loss:0.6474 - val_acc:0.8915
Epoch 479/5000
77s 154ms/step - loss:0.6851 - acc:0.8739 - val_loss:0.6780 - val_acc:0.8816
Epoch 480/5000
77s 154ms/step - loss:0.6851 - acc:0.8755 - val_loss:0.6889 - val_acc:0.8774
Epoch 481/5000
77s 154ms/step - loss:0.6913 - acc:0.8726 - val_loss:0.6380 - val_acc:0.8928
Epoch 482/5000
77s 154ms/step - loss:0.6846 - acc:0.8752 - val_loss:0.6673 - val_acc:0.8811
Epoch 483/5000
77s 154ms/step - loss:0.6879 - acc:0.8748 - val_loss:0.6674 - val_acc:0.8804
Epoch 484/5000
77s 154ms/step - loss:0.6906 - acc:0.8737 - val_loss:0.6809 - val_acc:0.8786
Epoch 485/5000
77s 154ms/step - loss:0.6871 - acc:0.8743 - val_loss:0.6740 - val_acc:0.8789
Epoch 486/5000
77s 154ms/step - loss:0.6876 - acc:0.8747 - val_loss:0.6729 - val_acc:0.8844
Epoch 487/5000
77s 154ms/step - loss:0.6914 - acc:0.8741 - val_loss:0.6650 - val_acc:0.8830
Epoch 488/5000
77s 154ms/step - loss:0.6864 - acc:0.8763 - val_loss:0.6629 - val_acc:0.8827
Epoch 489/5000
77s 154ms/step - loss:0.6844 - acc:0.8747 - val_loss:0.6371 - val_acc:0.8935
Epoch 490/5000
77s 153ms/step - loss:0.6881 - acc:0.8728 - val_loss:0.6862 - val_acc:0.8786
Epoch 491/5000
77s 153ms/step - loss:0.6919 - acc:0.8711 - val_loss:0.6382 - val_acc:0.8922
Epoch 492/5000
77s 154ms/step - loss:0.6858 - acc:0.8767 - val_loss:0.6820 - val_acc:0.8788
Epoch 493/5000
77s 154ms/step - loss:0.6878 - acc:0.8746 - val_loss:0.6815 - val_acc:0.8766
Epoch 494/5000
77s 154ms/step - loss:0.6889 - acc:0.8735 - val_loss:0.6695 - val_acc:0.8835
Epoch 495/5000
77s 154ms/step - loss:0.6822 - acc:0.8754 - val_loss:0.6530 - val_acc:0.8843
Epoch 496/5000
77s 154ms/step - loss:0.6892 - acc:0.8729 - val_loss:0.6570 - val_acc:0.8874
Epoch 497/5000
77s 154ms/step - loss:0.6885 - acc:0.8744 - val_loss:0.6395 - val_acc:0.8922
Epoch 498/5000
77s 154ms/step - loss:0.6862 - acc:0.8745 - val_loss:0.6509 - val_acc:0.8875
Epoch 499/5000
77s 154ms/step - loss:0.6863 - acc:0.8745 - val_loss:0.6554 - val_acc:0.8890
Epoch 500/5000
77s 154ms/step - loss:0.6867 - acc:0.8745 - val_loss:0.6650 - val_acc:0.8839
Epoch 501/5000
77s 154ms/step - loss:0.6805 - acc:0.8767 - val_loss:0.6894 - val_acc:0.8726
Epoch 502/5000
77s 154ms/step - loss:0.6804 - acc:0.8767 - val_loss:0.6739 - val_acc:0.8831
Epoch 503/5000
77s 154ms/step - loss:0.6863 - acc:0.8744 - val_loss:0.6585 - val_acc:0.8856
Epoch 504/5000
77s 154ms/step - loss:0.6836 - acc:0.8748 - val_loss:0.6515 - val_acc:0.8859
Epoch 505/5000
77s 154ms/step - loss:0.6856 - acc:0.8731 - val_loss:0.6709 - val_acc:0.8807
Epoch 506/5000
77s 154ms/step - loss:0.6880 - acc:0.8757 - val_loss:0.6623 - val_acc:0.8843
Epoch 507/5000
77s 154ms/step - loss:0.6860 - acc:0.8743 - val_loss:0.6719 - val_acc:0.8839
Epoch 508/5000
77s 154ms/step - loss:0.6857 - acc:0.8740 - val_loss:0.6653 - val_acc:0.8870
Epoch 509/5000
77s 154ms/step - loss:0.6873 - acc:0.8761 - val_loss:0.6534 - val_acc:0.8910
Epoch 510/5000
77s 154ms/step - loss:0.6865 - acc:0.8751 - val_loss:0.6686 - val_acc:0.8812
Epoch 511/5000
77s 154ms/step - loss:0.6869 - acc:0.8756 - val_loss:0.6690 - val_acc:0.8810
Epoch 512/5000
77s 154ms/step - loss:0.6902 - acc:0.8745 - val_loss:0.6492 - val_acc:0.8916
Epoch 513/5000
77s 154ms/step - loss:0.6870 - acc:0.8737 - val_loss:0.6780 - val_acc:0.8828
Epoch 514/5000
77s 153ms/step - loss:0.6879 - acc:0.8737 - val_loss:0.6663 - val_acc:0.8829
Epoch 515/5000
77s 154ms/step - loss:0.6866 - acc:0.8751 - val_loss:0.6440 - val_acc:0.8907
Epoch 516/5000
77s 153ms/step - loss:0.6885 - acc:0.8742 - val_loss:0.6478 - val_acc:0.8873
Epoch 517/5000
77s 154ms/step - loss:0.6850 - acc:0.8748 - val_loss:0.6541 - val_acc:0.8885
Epoch 518/5000
77s 154ms/step - loss:0.6886 - acc:0.8740 - val_loss:0.6685 - val_acc:0.8788
Epoch 519/5000
77s 154ms/step - loss:0.6906 - acc:0.8721 - val_loss:0.6836 - val_acc:0.8762
Epoch 520/5000
77s 154ms/step - loss:0.6894 - acc:0.8730 - val_loss:0.6596 - val_acc:0.8839
Epoch 521/5000
77s 154ms/step - loss:0.6879 - acc:0.8742 - val_loss:0.6729 - val_acc:0.8801
Epoch 522/5000
77s 154ms/step - loss:0.6874 - acc:0.8755 - val_loss:0.6422 - val_acc:0.8915
Epoch 523/5000
77s 154ms/step - loss:0.6831 - acc:0.8772 - val_loss:0.6386 - val_acc:0.8902
Epoch 524/5000
77s 154ms/step - loss:0.6869 - acc:0.8741 - val_loss:0.6578 - val_acc:0.8890
Epoch 525/5000
77s 154ms/step - loss:0.6882 - acc:0.8734 - val_loss:0.6563 - val_acc:0.8845
Epoch 526/5000
77s 154ms/step - loss:0.6823 - acc:0.8762 - val_loss:0.6540 - val_acc:0.8893
Epoch 527/5000
77s 154ms/step - loss:0.6853 - acc:0.8751 - val_loss:0.6709 - val_acc:0.8814
Epoch 528/5000
77s 154ms/step - loss:0.6831 - acc:0.8774 - val_loss:0.6622 - val_acc:0.8838
Epoch 529/5000
77s 154ms/step - loss:0.6851 - acc:0.8770 - val_loss:0.6478 - val_acc:0.8889
Epoch 530/5000
77s 154ms/step - loss:0.6910 - acc:0.8741 - val_loss:0.6444 - val_acc:0.8884
Epoch 531/5000
77s 154ms/step - loss:0.6854 - acc:0.8759 - val_loss:0.6519 - val_acc:0.8891
Epoch 532/5000
77s 154ms/step - loss:0.6875 - acc:0.8752 - val_loss:0.6509 - val_acc:0.8904
Epoch 533/5000
77s 154ms/step - loss:0.6842 - acc:0.8738 - val_loss:0.6692 - val_acc:0.8837
Epoch 534/5000
77s 154ms/step - loss:0.6834 - acc:0.8764 - val_loss:0.6551 - val_acc:0.8883
Epoch 535/5000
77s 154ms/step - loss:0.6873 - acc:0.8750 - val_loss:0.6708 - val_acc:0.8809
Epoch 536/5000
77s 154ms/step - loss:0.6861 - acc:0.8746 - val_loss:0.6537 - val_acc:0.8897
Epoch 537/5000
77s 154ms/step - loss:0.6815 - acc:0.8771 - val_loss:0.6546 - val_acc:0.8885
Epoch 538/5000
77s 154ms/step - loss:0.6878 - acc:0.8752 - val_loss:0.6486 - val_acc:0.8917
Epoch 539/5000
77s 154ms/step - loss:0.6833 - acc:0.8778 - val_loss:0.6455 - val_acc:0.8915
Epoch 540/5000
77s 154ms/step - loss:0.6849 - acc:0.8758 - val_loss:0.6467 - val_acc:0.8881
Epoch 541/5000
77s 154ms/step - loss:0.6851 - acc:0.8751 - val_loss:0.6578 - val_acc:0.8845
Epoch 542/5000
77s 154ms/step - loss:0.6830 - acc:0.8759 - val_loss:0.6427 - val_acc:0.8890
Epoch 543/5000
77s 154ms/step - loss:0.6867 - acc:0.8750 - val_loss:0.6498 - val_acc:0.8903
Epoch 544/5000
77s 153ms/step - loss:0.6875 - acc:0.8736 - val_loss:0.6620 - val_acc:0.8841
Epoch 545/5000
77s 154ms/step - loss:0.6873 - acc:0.8738 - val_loss:0.6460 - val_acc:0.8906
Epoch 546/5000
77s 153ms/step - loss:0.6855 - acc:0.8769 - val_loss:0.6529 - val_acc:0.8920
Epoch 547/5000
77s 154ms/step - loss:0.6874 - acc:0.8749 - val_loss:0.6537 - val_acc:0.8911
Epoch 548/5000
77s 154ms/step - loss:0.6899 - acc:0.8732 - val_loss:0.6800 - val_acc:0.8805
Epoch 549/5000
77s 154ms/step - loss:0.6891 - acc:0.8760 - val_loss:0.6508 - val_acc:0.8879
Epoch 550/5000
77s 154ms/step - loss:0.6827 - acc:0.8766 - val_loss:0.6610 - val_acc:0.8843
Epoch 551/5000
77s 154ms/step - loss:0.6906 - acc:0.8732 - val_loss:0.6425 - val_acc:0.8926
Epoch 552/5000
77s 153ms/step - loss:0.6815 - acc:0.8767 - val_loss:0.6834 - val_acc:0.8760
Epoch 553/5000
77s 154ms/step - loss:0.6857 - acc:0.8740 - val_loss:0.6426 - val_acc:0.8912
Epoch 554/5000
77s 154ms/step - loss:0.6799 - acc:0.8779 - val_loss:0.6460 - val_acc:0.8883
Epoch 555/5000
77s 154ms/step - loss:0.6837 - acc:0.8749 - val_loss:0.6652 - val_acc:0.8841
Epoch 556/5000
77s 154ms/step - loss:0.6821 - acc:0.8739 - val_loss:0.6418 - val_acc:0.8925
Epoch 557/5000
77s 154ms/step - loss:0.6866 - acc:0.8745 - val_loss:0.6479 - val_acc:0.8929
Epoch 558/5000
77s 154ms/step - loss:0.6873 - acc:0.8743 - val_loss:0.6716 - val_acc:0.8860
Epoch 559/5000
77s 154ms/step - loss:0.6812 - acc:0.8758 - val_loss:0.6542 - val_acc:0.8885
Epoch 560/5000
77s 154ms/step - loss:0.6875 - acc:0.8747 - val_loss:0.6537 - val_acc:0.8907
Epoch 561/5000
77s 154ms/step - loss:0.6864 - acc:0.8770 - val_loss:0.6436 - val_acc:0.8925
Epoch 562/5000
77s 154ms/step - loss:0.6883 - acc:0.8750 - val_loss:0.6498 - val_acc:0.8896
Epoch 563/5000
77s 154ms/step - loss:0.6871 - acc:0.8737 - val_loss:0.6590 - val_acc:0.8880
Epoch 564/5000
77s 154ms/step - loss:0.6820 - acc:0.8765 - val_loss:0.6520 - val_acc:0.8902
Epoch 565/5000
77s 154ms/step - loss:0.6882 - acc:0.8753 - val_loss:0.6522 - val_acc:0.8904
Epoch 566/5000
77s 154ms/step - loss:0.6828 - acc:0.8767 - val_loss:0.6712 - val_acc:0.8854
Epoch 567/5000
77s 153ms/step - loss:0.6862 - acc:0.8742 - val_loss:0.6891 - val_acc:0.8789
Epoch 568/5000
77s 154ms/step - loss:0.6821 - acc:0.8757 - val_loss:0.6508 - val_acc:0.8916
Epoch 569/5000
77s 154ms/step - loss:0.6831 - acc:0.8768 - val_loss:0.6687 - val_acc:0.8826
Epoch 570/5000
77s 154ms/step - loss:0.6897 - acc:0.8738 - val_loss:0.6624 - val_acc:0.8880
Epoch 571/5000
77s 153ms/step - loss:0.6916 - acc:0.8730 - val_loss:0.6588 - val_acc:0.8866
Epoch 572/5000
77s 154ms/step - loss:0.6834 - acc:0.8762 - val_loss:0.6897 - val_acc:0.8768
Epoch 573/5000
77s 154ms/step - loss:0.6827 - acc:0.8787 - val_loss:0.6428 - val_acc:0.8931
Epoch 574/5000
77s 154ms/step - loss:0.6891 - acc:0.8751 - val_loss:0.6741 - val_acc:0.8827
Epoch 575/5000
77s 154ms/step - loss:0.6855 - acc:0.8752 - val_loss:0.6770 - val_acc:0.8799
Epoch 576/5000
77s 154ms/step - loss:0.6821 - acc:0.8770 - val_loss:0.6548 - val_acc:0.8877
Epoch 577/5000
77s 154ms/step - loss:0.6868 - acc:0.8756 - val_loss:0.6592 - val_acc:0.8907
Epoch 578/5000
77s 153ms/step - loss:0.6837 - acc:0.8762 - val_loss:0.6952 - val_acc:0.8734
Epoch 579/5000
77s 154ms/step - loss:0.6907 - acc:0.8747 - val_loss:0.6539 - val_acc:0.8858
Epoch 580/5000
77s 153ms/step - loss:0.6859 - acc:0.8766 - val_loss:0.6604 - val_acc:0.8856
Epoch 581/5000
77s 154ms/step - loss:0.6792 - acc:0.8772 - val_loss:0.6459 - val_acc:0.8907
Epoch 582/5000
77s 154ms/step - loss:0.6826 - acc:0.8766 - val_loss:0.6629 - val_acc:0.8886
Epoch 583/5000
77s 154ms/step - loss:0.6865 - acc:0.8748 - val_loss:0.6689 - val_acc:0.8842
Epoch 584/5000
77s 154ms/step - loss:0.6823 - acc:0.8767 - val_loss:0.6514 - val_acc:0.8908
Epoch 585/5000
77s 154ms/step - loss:0.6822 - acc:0.8770 - val_loss:0.6637 - val_acc:0.8838
Epoch 586/5000
77s 154ms/step - loss:0.6823 - acc:0.8775 - val_loss:0.6616 - val_acc:0.8854
Epoch 587/5000
77s 154ms/step - loss:0.6843 - acc:0.8760 - val_loss:0.6617 - val_acc:0.8833
Epoch 588/5000
77s 154ms/step - loss:0.6865 - acc:0.8756 - val_loss:0.6399 - val_acc:0.8939
Epoch 589/5000
77s 154ms/step - loss:0.6828 - acc:0.8775 - val_loss:0.6497 - val_acc:0.8886
Epoch 590/5000
77s 154ms/step - loss:0.6848 - acc:0.8754 - val_loss:0.6451 - val_acc:0.8922
Epoch 591/5000
77s 154ms/step - loss:0.6892 - acc:0.8751 - val_loss:0.6585 - val_acc:0.8875
Epoch 592/5000
77s 154ms/step - loss:0.6856 - acc:0.8765 - val_loss:0.6616 - val_acc:0.8853
Epoch 593/5000
77s 154ms/step - loss:0.6842 - acc:0.8755 - val_loss:0.6380 - val_acc:0.8936
Epoch 594/5000
77s 154ms/step - loss:0.6850 - acc:0.8766 - val_loss:0.6702 - val_acc:0.8830
Epoch 595/5000
77s 154ms/step - loss:0.6842 - acc:0.8752 - val_loss:0.6391 - val_acc:0.8935
Epoch 596/5000
77s 154ms/step - loss:0.6832 - acc:0.8759 - val_loss:0.6665 - val_acc:0.8857
Epoch 597/5000
77s 154ms/step - loss:0.6822 - acc:0.8764 - val_loss:0.6539 - val_acc:0.8870
Epoch 598/5000
77s 154ms/step - loss:0.6842 - acc:0.8767 - val_loss:0.6744 - val_acc:0.8814
Epoch 599/5000
77s 153ms/step - loss:0.6876 - acc:0.8749 - val_loss:0.6829 - val_acc:0.8813
Epoch 600/5000
77s 154ms/step - loss:0.6835 - acc:0.8768 - val_loss:0.6625 - val_acc:0.8873
Epoch 601/5000
77s 153ms/step - loss:0.6840 - acc:0.8774 - val_loss:0.6809 - val_acc:0.8794
Epoch 602/5000
77s 154ms/step - loss:0.6846 - acc:0.8764 - val_loss:0.6467 - val_acc:0.8893
Epoch 603/5000
77s 154ms/step - loss:0.6808 - acc:0.8759 - val_loss:0.6447 - val_acc:0.8912
Epoch 604/5000
77s 154ms/step - loss:0.6831 - acc:0.8756 - val_loss:0.6614 - val_acc:0.8851
Epoch 605/5000
77s 154ms/step - loss:0.6844 - acc:0.8761 - val_loss:0.6354 - val_acc:0.8979
Epoch 606/5000
77s 154ms/step - loss:0.6824 - acc:0.8773 - val_loss:0.6695 - val_acc:0.8832
Epoch 607/5000
77s 154ms/step - loss:0.6899 - acc:0.8751 - val_loss:0.6583 - val_acc:0.8843
Epoch 608/5000
77s 154ms/step - loss:0.6804 - acc:0.8779 - val_loss:0.6470 - val_acc:0.8909
Epoch 609/5000
77s 154ms/step - loss:0.6865 - acc:0.8755 - val_loss:0.6763 - val_acc:0.8801
Epoch 610/5000
77s 154ms/step - loss:0.6839 - acc:0.8756 - val_loss:0.6519 - val_acc:0.8881
Epoch 611/5000
77s 154ms/step - loss:0.6853 - acc:0.8756 - val_loss:0.6613 - val_acc:0.8857
Epoch 612/5000
77s 154ms/step - loss:0.6806 - acc:0.8773 - val_loss:0.6511 - val_acc:0.8934
Epoch 613/5000
77s 154ms/step - loss:0.6856 - acc:0.8760 - val_loss:0.6386 - val_acc:0.8942
Epoch 614/5000
77s 154ms/step - loss:0.6830 - acc:0.8759 - val_loss:0.6596 - val_acc:0.8844
Epoch 615/5000
77s 154ms/step - loss:0.6812 - acc:0.8776 - val_loss:0.6517 - val_acc:0.8885
Epoch 616/5000
77s 154ms/step - loss:0.6776 - acc:0.8775 - val_loss:0.6609 - val_acc:0.8885
Epoch 617/5000
77s 154ms/step - loss:0.6873 - acc:0.8750 - val_loss:0.6522 - val_acc:0.8857
Epoch 618/5000
77s 154ms/step - loss:0.6830 - acc:0.8770 - val_loss:0.6656 - val_acc:0.8847
Epoch 619/5000
77s 154ms/step - loss:0.6813 - acc:0.8759 - val_loss:0.6539 - val_acc:0.8874
Epoch 620/5000
77s 154ms/step - loss:0.6870 - acc:0.8750 - val_loss:0.6632 - val_acc:0.8852
Epoch 621/5000
77s 154ms/step - loss:0.6853 - acc:0.8757 - val_loss:0.6495 - val_acc:0.8894
Epoch 622/5000
77s 154ms/step - loss:0.6811 - acc:0.8757 - val_loss:0.6762 - val_acc:0.8799
Epoch 623/5000
77s 154ms/step - loss:0.6810 - acc:0.8759 - val_loss:0.6653 - val_acc:0.8860
Epoch 624/5000
77s 154ms/step - loss:0.6814 - acc:0.8765 - val_loss:0.6669 - val_acc:0.8845
Epoch 625/5000
77s 154ms/step - loss:0.6867 - acc:0.8760 - val_loss:0.6505 - val_acc:0.8888
Epoch 626/5000
77s 154ms/step - loss:0.6809 - acc:0.8780 - val_loss:0.6794 - val_acc:0.8811
Epoch 627/5000
77s 154ms/step - loss:0.6793 - acc:0.8779 - val_loss:0.6671 - val_acc:0.8862
Epoch 628/5000
77s 153ms/step - loss:0.6836 - acc:0.8756 - val_loss:0.6555 - val_acc:0.8853
Epoch 629/5000
77s 154ms/step - loss:0.6873 - acc:0.8748 - val_loss:0.6482 - val_acc:0.8880
Epoch 630/5000
77s 154ms/step - loss:0.6838 - acc:0.8769 - val_loss:0.6464 - val_acc:0.8900
Epoch 631/5000
77s 154ms/step - loss:0.6812 - acc:0.8774 - val_loss:0.6706 - val_acc:0.8830
Epoch 632/5000
77s 154ms/step - loss:0.6827 - acc:0.8767 - val_loss:0.6543 - val_acc:0.8902
Epoch 633/5000
77s 154ms/step - loss:0.6812 - acc:0.8762 - val_loss:0.6733 - val_acc:0.8829
Epoch 634/5000
77s 154ms/step - loss:0.6862 - acc:0.8747 - val_loss:0.6691 - val_acc:0.8824
Epoch 635/5000
77s 153ms/step - loss:0.6814 - acc:0.8781 - val_loss:0.6578 - val_acc:0.8855
Epoch 636/5000
77s 154ms/step - loss:0.6767 - acc:0.8784 - val_loss:0.6637 - val_acc:0.8846
Epoch 637/5000
77s 154ms/step - loss:0.6806 - acc:0.8763 - val_loss:0.6529 - val_acc:0.8884
Epoch 638/5000
77s 154ms/step - loss:0.6837 - acc:0.8766 - val_loss:0.6346 - val_acc:0.8939
Epoch 639/5000
77s 154ms/step - loss:0.6836 - acc:0.8746 - val_loss:0.6439 - val_acc:0.8929
Epoch 640/5000
77s 153ms/step - loss:0.6777 - acc:0.8765 - val_loss:0.6639 - val_acc:0.8832
Epoch 641/5000
77s 154ms/step - loss:0.6824 - acc:0.8764 - val_loss:0.6721 - val_acc:0.8819
Epoch 642/5000
77s 154ms/step - loss:0.6856 - acc:0.8757 - val_loss:0.6614 - val_acc:0.8842
Epoch 643/5000
77s 154ms/step - loss:0.6832 - acc:0.8766 - val_loss:0.6578 - val_acc:0.8866
Epoch 644/5000
77s 154ms/step - loss:0.6805 - acc:0.8765 - val_loss:0.6534 - val_acc:0.8888
Epoch 645/5000
77s 154ms/step - loss:0.6833 - acc:0.8755 - val_loss:0.6613 - val_acc:0.8855
Epoch 646/5000
77s 154ms/step - loss:0.6778 - acc:0.8777 - val_loss:0.6597 - val_acc:0.8863
Epoch 647/5000
77s 154ms/step - loss:0.6833 - acc:0.8756 - val_loss:0.6577 - val_acc:0.8888
Epoch 648/5000
77s 154ms/step - loss:0.6886 - acc:0.8762 - val_loss:0.6539 - val_acc:0.8885
Epoch 649/5000
77s 154ms/step - loss:0.6829 - acc:0.8768 - val_loss:0.6575 - val_acc:0.8875
Epoch 650/5000
77s 154ms/step - loss:0.6892 - acc:0.8735 - val_loss:0.6865 - val_acc:0.8777
Epoch 651/5000
77s 154ms/step - loss:0.6776 - acc:0.8790 - val_loss:0.6533 - val_acc:0.8857
Epoch 652/5000
77s 154ms/step - loss:0.6860 - acc:0.8752 - val_loss:0.6643 - val_acc:0.8880
Epoch 653/5000
77s 154ms/step - loss:0.6848 - acc:0.8749 - val_loss:0.6565 - val_acc:0.8882
Epoch 654/5000
77s 154ms/step - loss:0.6811 - acc:0.8774 - val_loss:0.6638 - val_acc:0.8852
Epoch 655/5000
77s 154ms/step - loss:0.6781 - acc:0.8780 - val_loss:0.6566 - val_acc:0.8894
Epoch 656/5000
77s 154ms/step - loss:0.6818 - acc:0.8764 - val_loss:0.6804 - val_acc:0.8822
Epoch 657/5000
77s 154ms/step - loss:0.6834 - acc:0.8766 - val_loss:0.6487 - val_acc:0.8894
Epoch 658/5000
77s 154ms/step - loss:0.6867 - acc:0.8747 - val_loss:0.6576 - val_acc:0.8872
Epoch 659/5000
77s 154ms/step - loss:0.6823 - acc:0.8772 - val_loss:0.6532 - val_acc:0.8875
Epoch 660/5000
77s 154ms/step - loss:0.6814 - acc:0.8769 - val_loss:0.6576 - val_acc:0.8865
Epoch 661/5000
77s 154ms/step - loss:0.6831 - acc:0.8776 - val_loss:0.6648 - val_acc:0.8811
Epoch 662/5000
77s 154ms/step - loss:0.6822 - acc:0.8758 - val_loss:0.6648 - val_acc:0.8863
Epoch 663/5000
77s 154ms/step - loss:0.6912 - acc:0.8741 - val_loss:0.6724 - val_acc:0.8799
Epoch 664/5000
77s 154ms/step - loss:0.6821 - acc:0.8753 - val_loss:0.6441 - val_acc:0.8906
Epoch 665/5000
77s 154ms/step - loss:0.6847 - acc:0.8755 - val_loss:0.6666 - val_acc:0.8847
Epoch 666/5000
77s 154ms/step - loss:0.6803 - acc:0.8782 - val_loss:0.6387 - val_acc:0.8931
Epoch 667/5000
77s 154ms/step - loss:0.6838 - acc:0.8767 - val_loss:0.6705 - val_acc:0.8837
Epoch 668/5000
77s 154ms/step - loss:0.6882 - acc:0.8747 - val_loss:0.6715 - val_acc:0.8845
Epoch 669/5000
77s 154ms/step - loss:0.6791 - acc:0.8779 - val_loss:0.6596 - val_acc:0.8866
Epoch 670/5000
77s 154ms/step - loss:0.6838 - acc:0.8769 - val_loss:0.6623 - val_acc:0.8865
Epoch 671/5000
77s 154ms/step - loss:0.6776 - acc:0.8773 - val_loss:0.6627 - val_acc:0.8866
Epoch 672/5000
77s 154ms/step - loss:0.6815 - acc:0.8779 - val_loss:0.6596 - val_acc:0.8901
Epoch 673/5000
77s 154ms/step - loss:0.6819 - acc:0.8766 - val_loss:0.6718 - val_acc:0.8856
Epoch 674/5000
77s 154ms/step - loss:0.6836 - acc:0.8764 - val_loss:0.6477 - val_acc:0.8911
Epoch 675/5000
77s 154ms/step - loss:0.6816 - acc:0.8783 - val_loss:0.6656 - val_acc:0.8874
Epoch 676/5000
77s 154ms/step - loss:0.6835 - acc:0.8786 - val_loss:0.6672 - val_acc:0.8852
Epoch 677/5000
77s 154ms/step - loss:0.6821 - acc:0.8768 - val_loss:0.6772 - val_acc:0.8818
Epoch 678/5000
77s 154ms/step - loss:0.6828 - acc:0.8784 - val_loss:0.6708 - val_acc:0.8828
Epoch 679/5000
77s 153ms/step - loss:0.6812 - acc:0.8779 - val_loss:0.6756 - val_acc:0.8799
Epoch 680/5000
77s 154ms/step - loss:0.6825 - acc:0.8766 - val_loss:0.6512 - val_acc:0.8882
Epoch 681/5000
77s 153ms/step - loss:0.6803 - acc:0.8769 - val_loss:0.6505 - val_acc:0.8896
Epoch 682/5000
77s 154ms/step - loss:0.6829 - acc:0.8768 - val_loss:0.6531 - val_acc:0.8841
Epoch 683/5000
77s 154ms/step - loss:0.6834 - acc:0.8759 - val_loss:0.6509 - val_acc:0.8884
Epoch 684/5000
77s 154ms/step - loss:0.6832 - acc:0.8780 - val_loss:0.6385 - val_acc:0.8940
Epoch 685/5000
77s 154ms/step - loss:0.6821 - acc:0.8769 - val_loss:0.6699 - val_acc:0.8840
Epoch 686/5000
77s 154ms/step - loss:0.6790 - acc:0.8785 - val_loss:0.6789 - val_acc:0.8772
Epoch 687/5000
77s 154ms/step - loss:0.6809 - acc:0.8766 - val_loss:0.6421 - val_acc:0.8935
Epoch 688/5000
77s 153ms/step - loss:0.6797 - acc:0.8783 - val_loss:0.6627 - val_acc:0.8870
Epoch 689/5000
77s 154ms/step - loss:0.6870 - acc:0.8772 - val_loss:0.6521 - val_acc:0.8903
Epoch 690/5000
77s 154ms/step - loss:0.6787 - acc:0.8784 - val_loss:0.6540 - val_acc:0.8898
Epoch 691/5000
77s 154ms/step - loss:0.6826 - acc:0.8769 - val_loss:0.6506 - val_acc:0.8897
Epoch 692/5000
77s 153ms/step - loss:0.6843 - acc:0.8767 - val_loss:0.6663 - val_acc:0.8815
Epoch 693/5000
77s 154ms/step - loss:0.6844 - acc:0.8769 - val_loss:0.6549 - val_acc:0.8897
Epoch 694/5000
77s 154ms/step - loss:0.6817 - acc:0.8774 - val_loss:0.6547 - val_acc:0.8894
Epoch 695/5000
77s 153ms/step - loss:0.6850 - acc:0.8753 - val_loss:0.6532 - val_acc:0.8897
Epoch 696/5000
77s 154ms/step - loss:0.6781 - acc:0.8787 - val_loss:0.6379 - val_acc:0.8958
Epoch 697/5000
77s 154ms/step - loss:0.6797 - acc:0.8784 - val_loss:0.6609 - val_acc:0.8869
Epoch 698/5000
77s 154ms/step - loss:0.6886 - acc:0.8741 - val_loss:0.6434 - val_acc:0.8932
Epoch 699/5000
77s 154ms/step - loss:0.6795 - acc:0.8790 - val_loss:0.6545 - val_acc:0.8889
Epoch 700/5000
77s 154ms/step - loss:0.6818 - acc:0.8773 - val_loss:0.6663 - val_acc:0.8834
Epoch 701/5000
77s 154ms/step - loss:0.6857 - acc:0.8775 - val_loss:0.6370 - val_acc:0.8934
Epoch 702/5000
77s 154ms/step - loss:0.6821 - acc:0.8775 - val_loss:0.6452 - val_acc:0.8928
Epoch 703/5000
77s 154ms/step - loss:0.6810 - acc:0.8767 - val_loss:0.6575 - val_acc:0.8869
Epoch 704/5000
77s 154ms/step - loss:0.6809 - acc:0.8789 - val_loss:0.6608 - val_acc:0.8849
Epoch 705/5000
77s 153ms/step - loss:0.6819 - acc:0.8765 - val_loss:0.6537 - val_acc:0.8892
Epoch 706/5000
77s 154ms/step - loss:0.6882 - acc:0.8763 - val_loss:0.6601 - val_acc:0.8859
Epoch 707/5000
77s 154ms/step - loss:0.6836 - acc:0.8762 - val_loss:0.6612 - val_acc:0.8854
Epoch 708/5000
77s 154ms/step - loss:0.6821 - acc:0.8771 - val_loss:0.6675 - val_acc:0.8843
Epoch 709/5000
77s 154ms/step - loss:0.6875 - acc:0.8745 - val_loss:0.6473 - val_acc:0.8926
Epoch 710/5000
77s 154ms/step - loss:0.6820 - acc:0.8781 - val_loss:0.6590 - val_acc:0.8875
Epoch 711/5000
77s 154ms/step - loss:0.6790 - acc:0.8798 - val_loss:0.6470 - val_acc:0.8877
Epoch 712/5000
77s 154ms/step - loss:0.6789 - acc:0.8774 - val_loss:0.6745 - val_acc:0.8832
Epoch 713/5000
77s 154ms/step - loss:0.6833 - acc:0.8761 - val_loss:0.6637 - val_acc:0.8839
Epoch 714/5000
77s 154ms/step - loss:0.6774 - acc:0.8790 - val_loss:0.6672 - val_acc:0.8818
Epoch 715/5000
77s 154ms/step - loss:0.6808 - acc:0.8781 - val_loss:0.6399 - val_acc:0.8952
Epoch 716/5000
77s 154ms/step - loss:0.6845 - acc:0.8766 - val_loss:0.6635 - val_acc:0.8836
Epoch 717/5000
77s 154ms/step - loss:0.6810 - acc:0.8782 - val_loss:0.6382 - val_acc:0.8934
Epoch 718/5000
77s 154ms/step - loss:0.6801 - acc:0.8783 - val_loss:0.6439 - val_acc:0.8950
Epoch 719/5000
77s 154ms/step - loss:0.6800 - acc:0.8797 - val_loss:0.6493 - val_acc:0.8909
Epoch 720/5000
77s 154ms/step - loss:0.6856 - acc:0.8763 - val_loss:0.6469 - val_acc:0.8922
Epoch 721/5000
77s 154ms/step - loss:0.6836 - acc:0.8763 - val_loss:0.6656 - val_acc:0.8876
Epoch 722/5000
77s 153ms/step - loss:0.6830 - acc:0.8782 - val_loss:0.6732 - val_acc:0.8826
Epoch 723/5000
77s 154ms/step - loss:0.6845 - acc:0.8765 - val_loss:0.6785 - val_acc:0.8832
Epoch 724/5000
77s 154ms/step - loss:0.6820 - acc:0.8767 - val_loss:0.6567 - val_acc:0.8892
Epoch 725/5000
77s 154ms/step - loss:0.6851 - acc:0.8769 - val_loss:0.6530 - val_acc:0.8895
Epoch 726/5000
77s 154ms/step - loss:0.6806 - acc:0.8784 - val_loss:0.6473 - val_acc:0.8929
Epoch 727/5000
77s 153ms/step - loss:0.6786 - acc:0.8796 - val_loss:0.6540 - val_acc:0.8894
Epoch 728/5000
77s 154ms/step - loss:0.6790 - acc:0.8780 - val_loss:0.6413 - val_acc:0.8925
Epoch 729/5000
77s 154ms/step - loss:0.6811 - acc:0.8781 - val_loss:0.6519 - val_acc:0.8885
Epoch 730/5000
77s 154ms/step - loss:0.6837 - acc:0.8769 - val_loss:0.6731 - val_acc:0.8800
Epoch 731/5000
77s 154ms/step - loss:0.6895 - acc:0.8746 - val_loss:0.6662 - val_acc:0.8863
Epoch 732/5000
77s 154ms/step - loss:0.6798 - acc:0.8784 - val_loss:0.6768 - val_acc:0.8820
Epoch 733/5000
77s 154ms/step - loss:0.6816 - acc:0.8793 - val_loss:0.6514 - val_acc:0.8919
Epoch 734/5000
77s 154ms/step - loss:0.6867 - acc:0.8767 - val_loss:0.6460 - val_acc:0.8928
Epoch 735/5000
77s 154ms/step - loss:0.6802 - acc:0.8799 - val_loss:0.6523 - val_acc:0.8875
Epoch 736/5000
77s 153ms/step - loss:0.6807 - acc:0.8794 - val_loss:0.6487 - val_acc:0.8873
Epoch 737/5000
77s 153ms/step - loss:0.6811 - acc:0.8774 - val_loss:0.6670 - val_acc:0.8856
Epoch 738/5000
77s 154ms/step - loss:0.6821 - acc:0.8763 - val_loss:0.6545 - val_acc:0.8863
Epoch 739/5000
77s 154ms/step - loss:0.6877 - acc:0.8743 - val_loss:0.6712 - val_acc:0.8833
Epoch 740/5000
77s 154ms/step - loss:0.6763 - acc:0.8809 - val_loss:0.6697 - val_acc:0.8837
Epoch 741/5000
77s 154ms/step - loss:0.6873 - acc:0.8766 - val_loss:0.6560 - val_acc:0.8911
Epoch 742/5000
77s 154ms/step - loss:0.6803 - acc:0.8771 - val_loss:0.6483 - val_acc:0.8907
Epoch 743/5000
77s 153ms/step - loss:0.6794 - acc:0.8782 - val_loss:0.6755 - val_acc:0.8816
Epoch 744/5000
77s 154ms/step - loss:0.6835 - acc:0.8758 - val_loss:0.6565 - val_acc:0.8884
Epoch 745/5000
77s 154ms/step - loss:0.6842 - acc:0.8782 - val_loss:0.6857 - val_acc:0.8824
Epoch 746/5000
77s 154ms/step - loss:0.6768 - acc:0.8800 - val_loss:0.6802 - val_acc:0.8786
Epoch 747/5000
77s 154ms/step - loss:0.6825 - acc:0.8771 - val_loss:0.6430 - val_acc:0.8961
Epoch 748/5000
77s 154ms/step - loss:0.6787 - acc:0.8800 - val_loss:0.6699 - val_acc:0.8807
Epoch 749/5000
77s 154ms/step - loss:0.6822 - acc:0.8767 - val_loss:0.6622 - val_acc:0.8885
Epoch 750/5000
77s 153ms/step - loss:0.6758 - acc:0.8808 - val_loss:0.6511 - val_acc:0.8901
Epoch 751/5000
77s 154ms/step - loss:0.6827 - acc:0.8769 - val_loss:0.6777 - val_acc:0.8799
Epoch 752/5000
77s 154ms/step - loss:0.6855 - acc:0.8775 - val_loss:0.6472 - val_acc:0.8924
Epoch 753/5000
77s 153ms/step - loss:0.6783 - acc:0.8784 - val_loss:0.6535 - val_acc:0.8919
Epoch 754/5000
77s 154ms/step - loss:0.6796 - acc:0.8792 - val_loss:0.6624 - val_acc:0.8861
Epoch 755/5000
77s 153ms/step - loss:0.6798 - acc:0.8788 - val_loss:0.6661 - val_acc:0.8880
Epoch 756/5000
77s 154ms/step - loss:0.6814 - acc:0.8766 - val_loss:0.6466 - val_acc:0.8930
Epoch 757/5000
77s 154ms/step - loss:0.6808 - acc:0.8775 - val_loss:0.6528 - val_acc:0.8890
Epoch 758/5000
77s 154ms/step - loss:0.6818 - acc:0.8782 - val_loss:0.6547 - val_acc:0.8883
Epoch 759/5000
77s 154ms/step - loss:0.6806 - acc:0.8788 - val_loss:0.6509 - val_acc:0.8889
Epoch 760/5000
77s 154ms/step - loss:0.6782 - acc:0.8786 - val_loss:0.6486 - val_acc:0.8865
Epoch 761/5000
77s 154ms/step - loss:0.6808 - acc:0.8785 - val_loss:0.6484 - val_acc:0.8888
Epoch 762/5000
77s 154ms/step - loss:0.6802 - acc:0.8775 - val_loss:0.6838 - val_acc:0.8819
Epoch 763/5000
77s 154ms/step - loss:0.6797 - acc:0.8776 - val_loss:0.6411 - val_acc:0.8942
Epoch 764/5000
77s 154ms/step - loss:0.6811 - acc:0.8762 - val_loss:0.6767 - val_acc:0.8821
Epoch 765/5000
77s 154ms/step - loss:0.6790 - acc:0.8778 - val_loss:0.6430 - val_acc:0.8942
Epoch 766/5000
77s 154ms/step - loss:0.6819 - acc:0.8780 - val_loss:0.6648 - val_acc:0.8846
Epoch 767/5000
77s 154ms/step - loss:0.6843 - acc:0.8786 - val_loss:0.6458 - val_acc:0.8936
...
Epoch 1491/5000
77s 154ms/step - loss:0.6771 - acc:0.8807 - val_loss:0.6669 - val_acc:0.8886
Epoch 1492/5000
77s 154ms/step - loss:0.6735 - acc:0.8827 - val_loss:0.6475 - val_acc:0.8920
Epoch 1493/5000
77s 154ms/step - loss:0.6773 - acc:0.8814 - val_loss:0.6660 - val_acc:0.8891
Epoch 1494/5000
77s 154ms/step - loss:0.6807 - acc:0.8792 - val_loss:0.6478 - val_acc:0.8925
Epoch 1495/5000
77s 154ms/step - loss:0.6784 - acc:0.8819 - val_loss:0.6947 - val_acc:0.8754
Epoch 1496/5000
77s 154ms/step - loss:0.6815 - acc:0.8802 - val_loss:0.6643 - val_acc:0.8882
Epoch 1497/5000
77s 154ms/step - loss:0.6844 - acc:0.8787 - val_loss:0.6254 - val_acc:0.9019
Epoch 1498/5000
77s 154ms/step - loss:0.6783 - acc:0.8815 - val_loss:0.6634 - val_acc:0.8876
Epoch 1499/5000
77s 154ms/step - loss:0.6787 - acc:0.8800 - val_loss:0.6708 - val_acc:0.8862
Epoch 1500/5000
77s 154ms/step - loss:0.6815 - acc:0.8810 - val_loss:0.6554 - val_acc:0.8919
Epoch 1501/5000
lr changed to 0.010000000149011612
77s 154ms/step - loss:0.5717 - acc:0.9188 - val_loss:0.5618 - val_acc:0.9242
Epoch 1502/5000
77s 154ms/step - loss:0.5116 - acc:0.9373 - val_loss:0.5485 - val_acc:0.9261
Epoch 1503/5000
77s 154ms/step - loss:0.4922 - acc:0.9420 - val_loss:0.5352 - val_acc:0.9278
Epoch 1504/5000
77s 154ms/step - loss:0.4747 - acc:0.9466 - val_loss:0.5291 - val_acc:0.9268
Epoch 1505/5000
77s 154ms/step - loss:0.4657 - acc:0.9481 - val_loss:0.5215 - val_acc:0.9288
Epoch 1506/5000
77s 154ms/step - loss:0.4528 - acc:0.9497 - val_loss:0.5122 - val_acc:0.9292
Epoch 1507/5000
77s 154ms/step - loss:0.4453 - acc:0.9513 - val_loss:0.5116 - val_acc:0.9304
Epoch 1508/5000
77s 154ms/step - loss:0.4360 - acc:0.9530 - val_loss:0.5029 - val_acc:0.9325
Epoch 1509/5000
77s 154ms/step - loss:0.4239 - acc:0.9547 - val_loss:0.5028 - val_acc:0.9297
Epoch 1510/5000
77s 154ms/step - loss:0.4195 - acc:0.9549 - val_loss:0.4906 - val_acc:0.9322
Epoch 1511/5000
77s 154ms/step - loss:0.4109 - acc:0.9565 - val_loss:0.4917 - val_acc:0.9308
Epoch 1512/5000
77s 154ms/step - loss:0.4071 - acc:0.9561 - val_loss:0.4811 - val_acc:0.9324
Epoch 1513/5000
77s 154ms/step - loss:0.3979 - acc:0.9580 - val_loss:0.4752 - val_acc:0.9348
Epoch 1514/5000
77s 154ms/step - loss:0.3896 - acc:0.9590 - val_loss:0.4839 - val_acc:0.9303
Epoch 1515/5000
77s 154ms/step - loss:0.3846 - acc:0.9599 - val_loss:0.4811 - val_acc:0.9307
Epoch 1516/5000
77s 153ms/step - loss:0.3815 - acc:0.9592 - val_loss:0.4753 - val_acc:0.9317
Epoch 1517/5000
77s 154ms/step - loss:0.3730 - acc:0.9610 - val_loss:0.4688 - val_acc:0.9302
Epoch 1518/5000
77s 154ms/step - loss:0.3661 - acc:0.9624 - val_loss:0.4653 - val_acc:0.9324
Epoch 1519/5000
77s 154ms/step - loss:0.3621 - acc:0.9618 - val_loss:0.4602 - val_acc:0.9334
Epoch 1520/5000
77s 154ms/step - loss:0.3581 - acc:0.9636 - val_loss:0.4604 - val_acc:0.9310
Epoch 1521/5000
77s 154ms/step - loss:0.3542 - acc:0.9622 - val_loss:0.4598 - val_acc:0.9299
Epoch 1522/5000
77s 154ms/step - loss:0.3498 - acc:0.9632 - val_loss:0.4564 - val_acc:0.9307
Epoch 1523/5000
77s 153ms/step - loss:0.3445 - acc:0.9631 - val_loss:0.4461 - val_acc:0.9310
Epoch 1524/5000
77s 154ms/step - loss:0.3386 - acc:0.9641 - val_loss:0.4460 - val_acc:0.9319
Epoch 1525/5000
77s 154ms/step - loss:0.3348 - acc:0.9636 - val_loss:0.4432 - val_acc:0.9323
Epoch 1526/5000
77s 154ms/step - loss:0.3320 - acc:0.9652 - val_loss:0.4571 - val_acc:0.9249
Epoch 1527/5000
77s 154ms/step - loss:0.3278 - acc:0.9650 - val_loss:0.4385 - val_acc:0.9324
Epoch 1528/5000
77s 154ms/step - loss:0.3279 - acc:0.9639 - val_loss:0.4325 - val_acc:0.9330
Epoch 1529/5000
77s 154ms/step - loss:0.3228 - acc:0.9647 - val_loss:0.4303 - val_acc:0.9326
Epoch 1530/5000
77s 154ms/step - loss:0.3179 - acc:0.9658 - val_loss:0.4323 - val_acc:0.9314
Epoch 1531/5000
77s 154ms/step - loss:0.3145 - acc:0.9658 - val_loss:0.4339 - val_acc:0.9307
Epoch 1532/5000
77s 154ms/step - loss:0.3142 - acc:0.9658 - val_loss:0.4335 - val_acc:0.9287
Epoch 1533/5000
77s 154ms/step - loss:0.3100 - acc:0.9661 - val_loss:0.4267 - val_acc:0.9305
Epoch 1534/5000
77s 154ms/step - loss:0.3067 - acc:0.9660 - val_loss:0.4233 - val_acc:0.9339
Epoch 1535/5000
77s 154ms/step - loss:0.3067 - acc:0.9651 - val_loss:0.4267 - val_acc:0.9280
Epoch 1536/5000
77s 154ms/step - loss:0.3007 - acc:0.9660 - val_loss:0.4275 - val_acc:0.9288
Epoch 1537/5000
77s 154ms/step - loss:0.3011 - acc:0.9663 - val_loss:0.4170 - val_acc:0.9306
Epoch 1538/5000
77s 154ms/step - loss:0.2959 - acc:0.9666 - val_loss:0.4172 - val_acc:0.9331
Epoch 1539/5000
77s 154ms/step - loss:0.2929 - acc:0.9671 - val_loss:0.4187 - val_acc:0.9317
Epoch 1540/5000
77s 154ms/step - loss:0.2908 - acc:0.9676 - val_loss:0.4157 - val_acc:0.9299
Epoch 1541/5000
77s 154ms/step - loss:0.2892 - acc:0.9670 - val_loss:0.4234 - val_acc:0.9252
Epoch 1542/5000
77s 154ms/step - loss:0.2905 - acc:0.9659 - val_loss:0.4111 - val_acc:0.9299
Epoch 1543/5000
77s 154ms/step - loss:0.2855 - acc:0.9674 - val_loss:0.4094 - val_acc:0.9291
Epoch 1544/5000
77s 154ms/step - loss:0.2842 - acc:0.9673 - val_loss:0.4163 - val_acc:0.9286
Epoch 1545/5000
77s 154ms/step - loss:0.2817 - acc:0.9670 - val_loss:0.4068 - val_acc:0.9331
Epoch 1546/5000
77s 154ms/step - loss:0.2843 - acc:0.9661 - val_loss:0.4202 - val_acc:0.9255
Epoch 1547/5000
77s 154ms/step - loss:0.2851 - acc:0.9649 - val_loss:0.4121 - val_acc:0.9295
Epoch 1548/5000
77s 154ms/step - loss:0.2782 - acc:0.9665 - val_loss:0.4117 - val_acc:0.9308
Epoch 1549/5000
77s 154ms/step - loss:0.2766 - acc:0.9671 - val_loss:0.4029 - val_acc:0.9302
Epoch 1550/5000
77s 154ms/step - loss:0.2736 - acc:0.9679 - val_loss:0.4064 - val_acc:0.9299
Epoch 1551/5000
77s 154ms/step - loss:0.2745 - acc:0.9663 - val_loss:0.3985 - val_acc:0.9300
Epoch 1552/5000
77s 154ms/step - loss:0.2745 - acc:0.9661 - val_loss:0.4098 - val_acc:0.9250
Epoch 1553/5000
77s 154ms/step - loss:0.2717 - acc:0.9662 - val_loss:0.4028 - val_acc:0.9292
Epoch 1554/5000
77s 154ms/step - loss:0.2730 - acc:0.9657 - val_loss:0.4019 - val_acc:0.9276
Epoch 1555/5000
77s 154ms/step - loss:0.2751 - acc:0.9645 - val_loss:0.3969 - val_acc:0.9287
Epoch 1556/5000
77s 154ms/step - loss:0.2708 - acc:0.9657 - val_loss:0.4027 - val_acc:0.9271
Epoch 1557/5000
77s 154ms/step - loss:0.2670 - acc:0.9669 - val_loss:0.4042 - val_acc:0.9275
Epoch 1558/5000
77s 154ms/step - loss:0.2662 - acc:0.9669 - val_loss:0.4038 - val_acc:0.9258
Epoch 1559/5000
77s 154ms/step - loss:0.2653 - acc:0.9661 - val_loss:0.4098 - val_acc:0.9251
Epoch 1560/5000
77s 154ms/step - loss:0.2664 - acc:0.9657 - val_loss:0.3950 - val_acc:0.9269
Epoch 1561/5000
77s 154ms/step - loss:0.2614 - acc:0.9675 - val_loss:0.4088 - val_acc:0.9232
Epoch 1562/5000
77s 153ms/step - loss:0.2619 - acc:0.9669 - val_loss:0.4005 - val_acc:0.9274
Epoch 1563/5000
77s 154ms/step - loss:0.2619 - acc:0.9666 - val_loss:0.4021 - val_acc:0.9257
Epoch 1564/5000
77s 154ms/step - loss:0.2606 - acc:0.9669 - val_loss:0.3961 - val_acc:0.9282
Epoch 1565/5000
77s 154ms/step - loss:0.2597 - acc:0.9664 - val_loss:0.4045 - val_acc:0.9229
Epoch 1566/5000
77s 154ms/step - loss:0.2620 - acc:0.9650 - val_loss:0.3903 - val_acc:0.9284
Epoch 1567/5000
77s 154ms/step - loss:0.2634 - acc:0.9654 - val_loss:0.3865 - val_acc:0.9297
Epoch 1568/5000
77s 154ms/step - loss:0.2564 - acc:0.9668 - val_loss:0.3962 - val_acc:0.9276
Epoch 1569/5000
77s 154ms/step - loss:0.2559 - acc:0.9662 - val_loss:0.4041 - val_acc:0.9266
Epoch 1570/5000
77s 153ms/step - loss:0.2581 - acc:0.9656 - val_loss:0.4054 - val_acc:0.9238
Epoch 1571/5000
77s 154ms/step - loss:0.2569 - acc:0.9659 - val_loss:0.3901 - val_acc:0.9273
Epoch 1572/5000
77s 154ms/step - loss:0.2618 - acc:0.9639 - val_loss:0.3958 - val_acc:0.9262
Epoch 1573/5000
77s 154ms/step - loss:0.2550 - acc:0.9667 - val_loss:0.3916 - val_acc:0.9262
Epoch 1574/5000
77s 154ms/step - loss:0.2564 - acc:0.9659 - val_loss:0.3992 - val_acc:0.9261
Epoch 1575/5000
77s 154ms/step - loss:0.2591 - acc:0.9641 - val_loss:0.3978 - val_acc:0.9257
Epoch 1576/5000
77s 154ms/step - loss:0.2535 - acc:0.9654 - val_loss:0.3850 - val_acc:0.9286
Epoch 1577/5000
77s 154ms/step - loss:0.2527 - acc:0.9656 - val_loss:0.3918 - val_acc:0.9251
Epoch 1578/5000
77s 154ms/step - loss:0.2522 - acc:0.9673 - val_loss:0.3841 - val_acc:0.9280
Epoch 1579/5000
77s 154ms/step - loss:0.2573 - acc:0.9644 - val_loss:0.3839 - val_acc:0.9285
Epoch 1580/5000
77s 153ms/step - loss:0.2524 - acc:0.9664 - val_loss:0.3796 - val_acc:0.9299
Epoch 1581/5000
77s 154ms/step - loss:0.2532 - acc:0.9648 - val_loss:0.3851 - val_acc:0.9284
Epoch 1582/5000
77s 154ms/step - loss:0.2485 - acc:0.9678 - val_loss:0.3811 - val_acc:0.9280
Epoch 1583/5000
77s 154ms/step - loss:0.2525 - acc:0.9657 - val_loss:0.3967 - val_acc:0.9230
Epoch 1584/5000
77s 154ms/step - loss:0.2519 - acc:0.9658 - val_loss:0.3781 - val_acc:0.9285
Epoch 1585/5000
77s 154ms/step - loss:0.2516 - acc:0.9656 - val_loss:0.3820 - val_acc:0.9263
Epoch 1586/5000
77s 154ms/step - loss:0.2551 - acc:0.9645 - val_loss:0.3922 - val_acc:0.9266
Epoch 1587/5000
77s 154ms/step - loss:0.2503 - acc:0.9650 - val_loss:0.3849 - val_acc:0.9250
Epoch 1588/5000
77s 153ms/step - loss:0.2543 - acc:0.9640 - val_loss:0.3732 - val_acc:0.9298
Epoch 1589/5000
77s 154ms/step - loss:0.2514 - acc:0.9654 - val_loss:0.3804 - val_acc:0.9302
Epoch 1590/5000
77s 154ms/step - loss:0.2528 - acc:0.9651 - val_loss:0.3872 - val_acc:0.9252
Epoch 1591/5000
77s 154ms/step - loss:0.2501 - acc:0.9657 - val_loss:0.3836 - val_acc:0.9272
Epoch 1592/5000
77s 154ms/step - loss:0.2508 - acc:0.9652 - val_loss:0.4037 - val_acc:0.9209
Epoch 1593/5000
77s 154ms/step - loss:0.2498 - acc:0.9651 - val_loss:0.3844 - val_acc:0.9262
Epoch 1594/5000
77s 154ms/step - loss:0.2532 - acc:0.9637 - val_loss:0.3932 - val_acc:0.9251
Epoch 1595/5000
77s 154ms/step - loss:0.2453 - acc:0.9673 - val_loss:0.3754 - val_acc:0.9283
Epoch 1596/5000
77s 154ms/step - loss:0.2484 - acc:0.9652 - val_loss:0.3797 - val_acc:0.9283
Epoch 1597/5000
77s 153ms/step - loss:0.2418 - acc:0.9672 - val_loss:0.3826 - val_acc:0.9272
Epoch 1598/5000
77s 154ms/step - loss:0.2513 - acc:0.9640 - val_loss:0.3885 - val_acc:0.9248
Epoch 1599/5000
77s 154ms/step - loss:0.2538 - acc:0.9636 - val_loss:0.3797 - val_acc:0.9250
Epoch 1600/5000
77s 154ms/step - loss:0.2552 - acc:0.9623 - val_loss:0.3814 - val_acc:0.9288
...
Epoch 2930/5000
77s 154ms/step - loss:0.2255 - acc:0.9725 - val_loss:0.4132 - val_acc:0.9188
Epoch 2931/5000
77s 154ms/step - loss:0.2247 - acc:0.9720 - val_loss:0.4201 - val_acc:0.9200
Epoch 2932/5000
77s 154ms/step - loss:0.2271 - acc:0.9725 - val_loss:0.4074 - val_acc:0.9228
Epoch 2933/5000
77s 154ms/step - loss:0.2280 - acc:0.9711 - val_loss:0.4094 - val_acc:0.9220
Epoch 2934/5000
77s 154ms/step - loss:0.2290 - acc:0.9709 - val_loss:0.4011 - val_acc:0.9232
Epoch 2935/5000
77s 154ms/step - loss:0.2266 - acc:0.9717 - val_loss:0.4038 - val_acc:0.9212
Epoch 2936/5000
77s 154ms/step - loss:0.2253 - acc:0.9726 - val_loss:0.4277 - val_acc:0.9151
Epoch 2937/5000
77s 154ms/step - loss:0.2256 - acc:0.9728 - val_loss:0.4134 - val_acc:0.9203
Epoch 2938/5000
77s 154ms/step - loss:0.2254 - acc:0.9726 - val_loss:0.4020 - val_acc:0.9260
Epoch 2939/5000
77s 154ms/step - loss:0.2264 - acc:0.9724 - val_loss:0.4004 - val_acc:0.9227
Epoch 2940/5000
77s 154ms/step - loss:0.2249 - acc:0.9721 - val_loss:0.4046 - val_acc:0.9197
Epoch 2941/5000
77s 154ms/step - loss:0.2242 - acc:0.9728 - val_loss:0.4049 - val_acc:0.9197
Epoch 2942/5000
77s 154ms/step - loss:0.2252 - acc:0.9722 - val_loss:0.4010 - val_acc:0.9244
Epoch 2943/5000
77s 154ms/step - loss:0.2289 - acc:0.9713 - val_loss:0.4085 - val_acc:0.9193
Epoch 2944/5000
77s 154ms/step - loss:0.2258 - acc:0.9724 - val_loss:0.4128 - val_acc:0.9214
Epoch 2945/5000
77s 154ms/step - loss:0.2286 - acc:0.9707 - val_loss:0.4222 - val_acc:0.9145
Epoch 2946/5000
77s 154ms/step - loss:0.2256 - acc:0.9726 - val_loss:0.4081 - val_acc:0.9215
Epoch 2947/5000
77s 154ms/step - loss:0.2228 - acc:0.9733 - val_loss:0.4001 - val_acc:0.9236
Epoch 2948/5000
77s 154ms/step - loss:0.2260 - acc:0.9722 - val_loss:0.3945 - val_acc:0.9239
Epoch 2949/5000
77s 154ms/step - loss:0.2226 - acc:0.9732 - val_loss:0.4005 - val_acc:0.9223
Epoch 2950/5000
77s 154ms/step - loss:0.2280 - acc:0.9710 - val_loss:0.3977 - val_acc:0.9220
Epoch 2951/5000
77s 154ms/step - loss:0.2277 - acc:0.9707 - val_loss:0.3953 - val_acc:0.9245
Epoch 2952/5000
77s 154ms/step - loss:0.2270 - acc:0.9715 - val_loss:0.3916 - val_acc:0.9249
Epoch 2953/5000
77s 154ms/step - loss:0.2251 - acc:0.9724 - val_loss:0.4020 - val_acc:0.9232
Epoch 2954/5000
77s 154ms/step - loss:0.2277 - acc:0.9714 - val_loss:0.3946 - val_acc:0.9222
Epoch 2955/5000
77s 154ms/step - loss:0.2282 - acc:0.9719 - val_loss:0.3926 - val_acc:0.9239
Epoch 2956/5000
77s 154ms/step - loss:0.2209 - acc:0.9742 - val_loss:0.3995 - val_acc:0.9219
Epoch 2957/5000
77s 154ms/step - loss:0.2250 - acc:0.9729 - val_loss:0.4095 - val_acc:0.9195
Epoch 2958/5000
77s 154ms/step - loss:0.2200 - acc:0.9744 - val_loss:0.4053 - val_acc:0.9213
Epoch 2959/5000
77s 154ms/step - loss:0.2259 - acc:0.9725 - val_loss:0.3938 - val_acc:0.9243
Epoch 2960/5000
77s 154ms/step - loss:0.2225 - acc:0.9733 - val_loss:0.4226 - val_acc:0.9149
Epoch 2961/5000
77s 154ms/step - loss:0.2228 - acc:0.9733 - val_loss:0.4012 - val_acc:0.9231
Epoch 2962/5000
77s 154ms/step - loss:0.2266 - acc:0.9722 - val_loss:0.3923 - val_acc:0.9220
Epoch 2963/5000
77s 154ms/step - loss:0.2257 - acc:0.9720 - val_loss:0.4094 - val_acc:0.9207
Epoch 2964/5000
77s 154ms/step - loss:0.2232 - acc:0.9719 - val_loss:0.4030 - val_acc:0.9195
Epoch 2965/5000
77s 154ms/step - loss:0.2257 - acc:0.9726 - val_loss:0.4015 - val_acc:0.9208
Epoch 2966/5000
77s 154ms/step - loss:0.2260 - acc:0.9720 - val_loss:0.3923 - val_acc:0.9252
Epoch 2967/5000
77s 154ms/step - loss:0.2298 - acc:0.9702 - val_loss:0.4055 - val_acc:0.9212
Epoch 2968/5000
77s 154ms/step - loss:0.2341 - acc:0.9689 - val_loss:0.3956 - val_acc:0.9204
Epoch 2969/5000
78s 155ms/step - loss:0.2216 - acc:0.9743 - val_loss:0.4065 - val_acc:0.9227
Epoch 2970/5000
78s 155ms/step - loss:0.2271 - acc:0.9713 - val_loss:0.4127 - val_acc:0.9191
Epoch 2971/5000
77s 155ms/step - loss:0.2275 - acc:0.9716 - val_loss:0.3983 - val_acc:0.9206
Epoch 2972/5000
78s 155ms/step - loss:0.2237 - acc:0.9723 - val_loss:0.3819 - val_acc:0.9278
Epoch 2973/5000
78s 155ms/step - loss:0.2237 - acc:0.9740 - val_loss:0.3824 - val_acc:0.9241
Epoch 2974/5000
78s 155ms/step - loss:0.2282 - acc:0.9711 - val_loss:0.4099 - val_acc:0.9220
Epoch 2975/5000
77s 155ms/step - loss:0.2226 - acc:0.9730 - val_loss:0.3993 - val_acc:0.9249
Epoch 2976/5000
77s 155ms/step - loss:0.2274 - acc:0.9716 - val_loss:0.3942 - val_acc:0.9241
Epoch 2977/5000
78s 155ms/step - loss:0.2303 - acc:0.9703 - val_loss:0.3946 - val_acc:0.9228
Epoch 2978/5000
78s 155ms/step - loss:0.2236 - acc:0.9729 - val_loss:0.4192 - val_acc:0.9195
Epoch 2979/5000
77s 155ms/step - loss:0.2303 - acc:0.9711 - val_loss:0.4105 - val_acc:0.9204
Epoch 2980/5000
77s 155ms/step - loss:0.2281 - acc:0.9708 - val_loss:0.4206 - val_acc:0.9166
Epoch 2981/5000
78s 155ms/step - loss:0.2293 - acc:0.9714 - val_loss:0.3983 - val_acc:0.9233
Epoch 2982/5000
77s 155ms/step - loss:0.2212 - acc:0.9744 - val_loss:0.4093 - val_acc:0.9220
Epoch 2983/5000
78s 155ms/step - loss:0.2282 - acc:0.9713 - val_loss:0.3909 - val_acc:0.9266
Epoch 2984/5000
78s 155ms/step - loss:0.2220 - acc:0.9738 - val_loss:0.4007 - val_acc:0.9222
Epoch 2985/5000
77s 155ms/step - loss:0.2246 - acc:0.9728 - val_loss:0.4016 - val_acc:0.9231
Epoch 2986/5000
78s 155ms/step - loss:0.2263 - acc:0.9714 - val_loss:0.3954 - val_acc:0.9229
Epoch 2987/5000
77s 155ms/step - loss:0.2253 - acc:0.9724 - val_loss:0.3986 - val_acc:0.9254
Epoch 2988/5000
77s 155ms/step - loss:0.2278 - acc:0.9718 - val_loss:0.3938 - val_acc:0.9237
Epoch 2989/5000
77s 155ms/step - loss:0.2291 - acc:0.9715 - val_loss:0.4007 - val_acc:0.9208
Epoch 2990/5000
78s 155ms/step - loss:0.2288 - acc:0.9708 - val_loss:0.3921 - val_acc:0.9235
Epoch 2991/5000
77s 155ms/step - loss:0.2186 - acc:0.9752 - val_loss:0.4077 - val_acc:0.9234
Epoch 2992/5000
78s 155ms/step - loss:0.2271 - acc:0.9711 - val_loss:0.3884 - val_acc:0.9262
Epoch 2993/5000
78s 155ms/step - loss:0.2236 - acc:0.9722 - val_loss:0.3975 - val_acc:0.9241
Epoch 2994/5000
77s 155ms/step - loss:0.2231 - acc:0.9732 - val_loss:0.3987 - val_acc:0.9255
Epoch 2995/5000
77s 155ms/step - loss:0.2234 - acc:0.9729 - val_loss:0.4180 - val_acc:0.9175
Epoch 2996/5000
77s 155ms/step - loss:0.2252 - acc:0.9726 - val_loss:0.4069 - val_acc:0.9222
Epoch 2997/5000
78s 155ms/step - loss:0.2273 - acc:0.9727 - val_loss:0.3979 - val_acc:0.9229
Epoch 2998/5000
77s 155ms/step - loss:0.2260 - acc:0.9722 - val_loss:0.4036 - val_acc:0.9208
Epoch 2999/5000
78s 155ms/step - loss:0.2254 - acc:0.9721 - val_loss:0.3880 - val_acc:0.9252
Epoch 3000/5000
78s 155ms/step - loss:0.2262 - acc:0.9725 - val_loss:0.4040 - val_acc:0.9217
Epoch 3001/5000
lr changed to 0.0009999999776482583
78s 155ms/step - loss:0.2012 - acc:0.9814 - val_loss:0.3627 - val_acc:0.9343
Epoch 3002/5000
78s 155ms/step - loss:0.1846 - acc:0.9875 - val_loss:0.3587 - val_acc:0.9344
Epoch 3003/5000
78s 155ms/step - loss:0.1793 - acc:0.9893 - val_loss:0.3559 - val_acc:0.9357
Epoch 3004/5000
78s 155ms/step - loss:0.1770 - acc:0.9901 - val_loss:0.3559 - val_acc:0.9361
Epoch 3005/5000
78s 155ms/step - loss:0.1752 - acc:0.9909 - val_loss:0.3563 - val_acc:0.9363
Epoch 3006/5000
78s 155ms/step - loss:0.1730 - acc:0.9916 - val_loss:0.3536 - val_acc:0.9366
Epoch 3007/5000
78s 155ms/step - loss:0.1744 - acc:0.9905 - val_loss:0.3543 - val_acc:0.9388
Epoch 3008/5000
78s 155ms/step - loss:0.1692 - acc:0.9927 - val_loss:0.3553 - val_acc:0.9374
Epoch 3009/5000
78s 155ms/step - loss:0.1693 - acc:0.9925 - val_loss:0.3557 - val_acc:0.9370
Epoch 3010/5000
78s 155ms/step - loss:0.1688 - acc:0.9926 - val_loss:0.3541 - val_acc:0.9389
Epoch 3011/5000
78s 155ms/step - loss:0.1664 - acc:0.9934 - val_loss:0.3545 - val_acc:0.9384
Epoch 3012/5000
78s 155ms/step - loss:0.1671 - acc:0.9931 - val_loss:0.3572 - val_acc:0.9387
Epoch 3013/5000
78s 155ms/step - loss:0.1644 - acc:0.9940 - val_loss:0.3561 - val_acc:0.9387
Epoch 3014/5000
77s 155ms/step - loss:0.1646 - acc:0.9937 - val_loss:0.3563 - val_acc:0.9388
Epoch 3015/5000
78s 155ms/step - loss:0.1644 - acc:0.9936 - val_loss:0.3564 - val_acc:0.9379
Epoch 3016/5000
78s 155ms/step - loss:0.1632 - acc:0.9939 - val_loss:0.3542 - val_acc:0.9376
Epoch 3017/5000
78s 155ms/step - loss:0.1622 - acc:0.9941 - val_loss:0.3562 - val_acc:0.9380
Epoch 3018/5000
78s 155ms/step - loss:0.1619 - acc:0.9943 - val_loss:0.3545 - val_acc:0.9385
Epoch 3019/5000
77s 155ms/step - loss:0.1609 - acc:0.9947 - val_loss:0.3553 - val_acc:0.9393
Epoch 3020/5000
78s 155ms/step - loss:0.1607 - acc:0.9945 - val_loss:0.3575 - val_acc:0.9373
...
Epoch 4492/5000
77s 154ms/step - loss:0.0646 - acc:0.9953 - val_loss:0.3020 - val_acc:0.9352
Epoch 4493/5000
77s 153ms/step - loss:0.0649 - acc:0.9947 - val_loss:0.3092 - val_acc:0.9344
Epoch 4494/5000
77s 154ms/step - loss:0.0642 - acc:0.9952 - val_loss:0.2993 - val_acc:0.9351
Epoch 4495/5000
77s 154ms/step - loss:0.0645 - acc:0.9949 - val_loss:0.2898 - val_acc:0.9371
Epoch 4496/5000
77s 154ms/step - loss:0.0652 - acc:0.9952 - val_loss:0.3040 - val_acc:0.9364
Epoch 4497/5000
77s 154ms/step - loss:0.0646 - acc:0.9949 - val_loss:0.3002 - val_acc:0.9357
Epoch 4498/5000
77s 153ms/step - loss:0.0655 - acc:0.9947 - val_loss:0.2957 - val_acc:0.9385
Epoch 4499/5000
77s 153ms/step - loss:0.0648 - acc:0.9947 - val_loss:0.2993 - val_acc:0.9371
Epoch 4500/5000
77s 153ms/step - loss:0.0657 - acc:0.9944 - val_loss:0.3034 - val_acc:0.9349
Epoch 4501/5000
lr changed to 9.999999310821295e-05
77s 154ms/step - loss:0.0631 - acc:0.9958 - val_loss:0.2941 - val_acc:0.9384
Epoch 4502/5000
77s 154ms/step - loss:0.0606 - acc:0.9963 - val_loss:0.2887 - val_acc:0.9393
Epoch 4503/5000
77s 154ms/step - loss:0.0585 - acc:0.9971 - val_loss:0.2866 - val_acc:0.9398
Epoch 4504/5000
77s 154ms/step - loss:0.0579 - acc:0.9974 - val_loss:0.2861 - val_acc:0.9408
Epoch 4505/5000
77s 153ms/step - loss:0.0568 - acc:0.9976 - val_loss:0.2838 - val_acc:0.9415
Epoch 4506/5000
77s 154ms/step - loss:0.0579 - acc:0.9975 - val_loss:0.2825 - val_acc:0.9419
Epoch 4507/5000
77s 154ms/step - loss:0.0567 - acc:0.9977 - val_loss:0.2818 - val_acc:0.9417
Epoch 4508/5000
77s 154ms/step - loss:0.0570 - acc:0.9977 - val_loss:0.2814 - val_acc:0.9416
Epoch 4509/5000
77s 154ms/step - loss:0.0557 - acc:0.9982 - val_loss:0.2794 - val_acc:0.9421
Epoch 4510/5000
77s 154ms/step - loss:0.0555 - acc:0.9982 - val_loss:0.2793 - val_acc:0.9428
Epoch 4511/5000
77s 153ms/step - loss:0.0565 - acc:0.9979 - val_loss:0.2789 - val_acc:0.9418
Epoch 4512/5000
77s 154ms/step - loss:0.0555 - acc:0.9981 - val_loss:0.2806 - val_acc:0.9408
Epoch 4513/5000
77s 153ms/step - loss:0.0561 - acc:0.9977 - val_loss:0.2801 - val_acc:0.9417
Epoch 4514/5000
77s 153ms/step - loss:0.0552 - acc:0.9983 - val_loss:0.2791 - val_acc:0.9415
Epoch 4515/5000
77s 154ms/step - loss:0.0550 - acc:0.9985 - val_loss:0.2796 - val_acc:0.9423
Epoch 4516/5000
77s 153ms/step - loss:0.0547 - acc:0.9982 - val_loss:0.2817 - val_acc:0.9416
Epoch 4517/5000
77s 153ms/step - loss:0.0559 - acc:0.9980 - val_loss:0.2821 - val_acc:0.9423
Epoch 4518/5000
77s 154ms/step - loss:0.0548 - acc:0.9985 - val_loss:0.2807 - val_acc:0.9430
Epoch 4519/5000
77s 154ms/step - loss:0.0545 - acc:0.9986 - val_loss:0.2801 - val_acc:0.9433
Epoch 4520/5000
77s 154ms/step - loss:0.0550 - acc:0.9980 - val_loss:0.2814 - val_acc:0.9422
Epoch 4521/5000
77s 154ms/step - loss:0.0554 - acc:0.9981 - val_loss:0.2811 - val_acc:0.9422
Epoch 4522/5000
77s 154ms/step - loss:0.0545 - acc:0.9984 - val_loss:0.2792 - val_acc:0.9432
Epoch 4523/5000
77s 154ms/step - loss:0.0541 - acc:0.9986 - val_loss:0.2798 - val_acc:0.9421
Epoch 4524/5000
77s 154ms/step - loss:0.0543 - acc:0.9985 - val_loss:0.2789 - val_acc:0.9435
Epoch 4525/5000
77s 154ms/step - loss:0.0543 - acc:0.9986 - val_loss:0.2788 - val_acc:0.9428
Epoch 4526/5000
77s 154ms/step - loss:0.0547 - acc:0.9984 - val_loss:0.2786 - val_acc:0.9429
Epoch 4527/5000
77s 154ms/step - loss:0.0541 - acc:0.9985 - val_loss:0.2791 - val_acc:0.9425
Epoch 4528/5000
77s 155ms/step - loss:0.0539 - acc:0.9986 - val_loss:0.2797 - val_acc:0.9427
Epoch 4529/5000
78s 156ms/step - loss:0.0553 - acc:0.9980 - val_loss:0.2777 - val_acc:0.9432
Epoch 4530/5000
78s 155ms/step - loss:0.0542 - acc:0.9985 - val_loss:0.2787 - val_acc:0.9422
Epoch 4531/5000
77s 155ms/step - loss:0.0548 - acc:0.9982 - val_loss:0.2792 - val_acc:0.9427
Epoch 4532/5000
77s 155ms/step - loss:0.0547 - acc:0.9983 - val_loss:0.2791 - val_acc:0.9425
Epoch 4533/5000
78s 155ms/step - loss:0.0539 - acc:0.9986 - val_loss:0.2811 - val_acc:0.9423
Epoch 4534/5000
78s 155ms/step - loss:0.0536 - acc:0.9985 - val_loss:0.2808 - val_acc:0.9422
Epoch 4535/5000
78s 155ms/step - loss:0.0542 - acc:0.9984 - val_loss:0.2802 - val_acc:0.9426
Epoch 4536/5000
78s 155ms/step - loss:0.0535 - acc:0.9988 - val_loss:0.2804 - val_acc:0.9422
Epoch 4537/5000
77s 155ms/step - loss:0.0536 - acc:0.9987 - val_loss:0.2790 - val_acc:0.9425
Epoch 4538/5000
78s 155ms/step - loss:0.0539 - acc:0.9986 - val_loss:0.2798 - val_acc:0.9433
Epoch 4539/5000
78s 155ms/step - loss:0.0540 - acc:0.9985 - val_loss:0.2786 - val_acc:0.9436
Epoch 4540/5000
78s 155ms/step - loss:0.0540 - acc:0.9985 - val_loss:0.2788 - val_acc:0.9433
Epoch 4541/5000
77s 155ms/step - loss:0.0543 - acc:0.9985 - val_loss:0.2774 - val_acc:0.9424
Epoch 4542/5000
77s 155ms/step - loss:0.0536 - acc:0.9987 - val_loss:0.2771 - val_acc:0.9431
Epoch 4543/5000
77s 155ms/step - loss:0.0536 - acc:0.9984 - val_loss:0.2785 - val_acc:0.9427
Epoch 4544/5000
77s 155ms/step - loss:0.0539 - acc:0.9984 - val_loss:0.2806 - val_acc:0.9428
Epoch 4545/5000
78s 155ms/step - loss:0.0537 - acc:0.9985 - val_loss:0.2803 - val_acc:0.9428
Epoch 4546/5000
77s 155ms/step - loss:0.0527 - acc:0.9991 - val_loss:0.2806 - val_acc:0.9434
Epoch 4547/5000
77s 155ms/step - loss:0.0534 - acc:0.9987 - val_loss:0.2808 - val_acc:0.9427
Epoch 4548/5000
77s 155ms/step - loss:0.0537 - acc:0.9985 - val_loss:0.2799 - val_acc:0.9427
Epoch 4549/5000
77s 155ms/step - loss:0.0538 - acc:0.9984 - val_loss:0.2814 - val_acc:0.9424
Epoch 4550/5000
77s 155ms/step - loss:0.0537 - acc:0.9987 - val_loss:0.2806 - val_acc:0.9434
Epoch 4551/5000
77s 155ms/step - loss:0.0532 - acc:0.9988 - val_loss:0.2804 - val_acc:0.9435
Epoch 4552/5000
78s 155ms/step - loss:0.0534 - acc:0.9989 - val_loss:0.2813 - val_acc:0.9424
Epoch 4553/5000
78s 155ms/step - loss:0.0531 - acc:0.9988 - val_loss:0.2812 - val_acc:0.9411
Epoch 4554/5000
78s 155ms/step - loss:0.0535 - acc:0.9986 - val_loss:0.2807 - val_acc:0.9419
Epoch 4555/5000
77s 155ms/step - loss:0.0529 - acc:0.9989 - val_loss:0.2800 - val_acc:0.9428
Epoch 4556/5000
77s 155ms/step - loss:0.0533 - acc:0.9985 - val_loss:0.2802 - val_acc:0.9425
Epoch 4557/5000
78s 155ms/step - loss:0.0534 - acc:0.9987 - val_loss:0.2819 - val_acc:0.9422
Epoch 4558/5000
78s 155ms/step - loss:0.0536 - acc:0.9985 - val_loss:0.2806 - val_acc:0.9434
Epoch 4559/5000
77s 155ms/step - loss:0.0540 - acc:0.9985 - val_loss:0.2812 - val_acc:0.9432
Epoch 4560/5000
78s 155ms/step - loss:0.0532 - acc:0.9988 - val_loss:0.2813 - val_acc:0.9441
Epoch 4561/5000
77s 155ms/step - loss:0.0527 - acc:0.9988 - val_loss:0.2817 - val_acc:0.9442
Epoch 4562/5000
77s 155ms/step - loss:0.0527 - acc:0.9990 - val_loss:0.2805 - val_acc:0.9444
Epoch 4563/5000
77s 155ms/step - loss:0.0528 - acc:0.9989 - val_loss:0.2810 - val_acc:0.9445
Epoch 4564/5000
77s 155ms/step - loss:0.0525 - acc:0.9990 - val_loss:0.2790 - val_acc:0.9443
Epoch 4565/5000
78s 155ms/step - loss:0.0529 - acc:0.9986 - val_loss:0.2793 - val_acc:0.9430
Epoch 4566/5000
78s 155ms/step - loss:0.0530 - acc:0.9989 - val_loss:0.2784 - val_acc:0.9439
Epoch 4567/5000
78s 155ms/step - loss:0.0535 - acc:0.9986 - val_loss:0.2802 - val_acc:0.9435
Epoch 4568/5000
77s 155ms/step - loss:0.0525 - acc:0.9989 - val_loss:0.2805 - val_acc:0.9437
Epoch 4569/5000
77s 155ms/step - loss:0.0527 - acc:0.9988 - val_loss:0.2807 - val_acc:0.9438
Epoch 4570/5000
77s 155ms/step - loss:0.0527 - acc:0.9989 - val_loss:0.2813 - val_acc:0.9431
Epoch 4571/5000
77s 155ms/step - loss:0.0528 - acc:0.9990 - val_loss:0.2822 - val_acc:0.9427
Epoch 4572/5000
77s 155ms/step - loss:0.0531 - acc:0.9989 - val_loss:0.2822 - val_acc:0.9424
Epoch 4573/5000
77s 155ms/step - loss:0.0520 - acc:0.9992 - val_loss:0.2835 - val_acc:0.9431
Epoch 4574/5000
78s 155ms/step - loss:0.0530 - acc:0.9988 - val_loss:0.2815 - val_acc:0.9439
Epoch 4575/5000
77s 155ms/step - loss:0.0530 - acc:0.9988 - val_loss:0.2827 - val_acc:0.9435
Epoch 4576/5000
77s 155ms/step - loss:0.0528 - acc:0.9987 - val_loss:0.2822 - val_acc:0.9445
Epoch 4577/5000
77s 155ms/step - loss:0.0529 - acc:0.9988 - val_loss:0.2817 - val_acc:0.9433
Epoch 4578/5000
77s 155ms/step - loss:0.0530 - acc:0.9988 - val_loss:0.2821 - val_acc:0.9426
Epoch 4579/5000
77s 155ms/step - loss:0.0526 - acc:0.9989 - val_loss:0.2822 - val_acc:0.9432
Epoch 4580/5000
77s 155ms/step - loss:0.0529 - acc:0.9988 - val_loss:0.2840 - val_acc:0.9429
Epoch 4581/5000
77s 155ms/step - loss:0.0534 - acc:0.9984 - val_loss:0.2832 - val_acc:0.9430
Epoch 4582/5000
77s 155ms/step - loss:0.0527 - acc:0.9989 - val_loss:0.2832 - val_acc:0.9437
Epoch 4583/5000
78s 155ms/step - loss:0.0523 - acc:0.9991 - val_loss:0.2831 - val_acc:0.9428
Epoch 4584/5000
77s 155ms/step - loss:0.0527 - acc:0.9987 - val_loss:0.2835 - val_acc:0.9426
Epoch 4585/5000
77s 155ms/step - loss:0.0529 - acc:0.9988 - val_loss:0.2833 - val_acc:0.9432
...
Epoch 4958/5000
77s 154ms/step - loss:0.0484 - acc:0.9992 - val_loss:0.2819 - val_acc:0.9435
Epoch 4959/5000
77s 154ms/step - loss:0.0485 - acc:0.9992 - val_loss:0.2826 - val_acc:0.9437
Epoch 4960/5000
77s 154ms/step - loss:0.0482 - acc:0.9994 - val_loss:0.2830 - val_acc:0.9423
Epoch 4961/5000
77s 154ms/step - loss:0.0485 - acc:0.9992 - val_loss:0.2827 - val_acc:0.9436
Epoch 4962/5000
77s 154ms/step - loss:0.0487 - acc:0.9990 - val_loss:0.2831 - val_acc:0.9434
Epoch 4963/5000
77s 154ms/step - loss:0.0481 - acc:0.9993 - val_loss:0.2835 - val_acc:0.9440
Epoch 4964/5000
77s 154ms/step - loss:0.0488 - acc:0.9991 - val_loss:0.2843 - val_acc:0.9433
Epoch 4965/5000
77s 154ms/step - loss:0.0486 - acc:0.9992 - val_loss:0.2821 - val_acc:0.9434
Epoch 4966/5000
77s 153ms/step - loss:0.0487 - acc:0.9992 - val_loss:0.2824 - val_acc:0.9440
Epoch 4967/5000
77s 154ms/step - loss:0.0482 - acc:0.9992 - val_loss:0.2817 - val_acc:0.9449
Epoch 4968/5000
77s 154ms/step - loss:0.0485 - acc:0.9992 - val_loss:0.2830 - val_acc:0.9449
Epoch 4969/5000
77s 154ms/step - loss:0.0492 - acc:0.9990 - val_loss:0.2856 - val_acc:0.9439
Epoch 4970/5000
77s 154ms/step - loss:0.0484 - acc:0.9991 - val_loss:0.2860 - val_acc:0.9429
Epoch 4971/5000
77s 153ms/step - loss:0.0486 - acc:0.9991 - val_loss:0.2864 - val_acc:0.9429
Epoch 4972/5000
77s 154ms/step - loss:0.0483 - acc:0.9994 - val_loss:0.2878 - val_acc:0.9422
Epoch 4973/5000
77s 154ms/step - loss:0.0485 - acc:0.9991 - val_loss:0.2874 - val_acc:0.9423
Epoch 4974/5000
77s 154ms/step - loss:0.0490 - acc:0.9991 - val_loss:0.2848 - val_acc:0.9439
Epoch 4975/5000
77s 154ms/step - loss:0.0484 - acc:0.9993 - val_loss:0.2867 - val_acc:0.9438
Epoch 4976/5000
77s 154ms/step - loss:0.0480 - acc:0.9993 - val_loss:0.2857 - val_acc:0.9439
Epoch 4977/5000
77s 154ms/step - loss:0.0483 - acc:0.9992 - val_loss:0.2848 - val_acc:0.9436
Epoch 4978/5000
77s 154ms/step - loss:0.0483 - acc:0.9992 - val_loss:0.2860 - val_acc:0.9440
Epoch 4979/5000
77s 154ms/step - loss:0.0481 - acc:0.9993 - val_loss:0.2872 - val_acc:0.9433
Epoch 4980/5000
77s 154ms/step - loss:0.0482 - acc:0.9993 - val_loss:0.2867 - val_acc:0.9436
Epoch 4981/5000
77s 154ms/step - loss:0.0480 - acc:0.9994 - val_loss:0.2871 - val_acc:0.9431
Epoch 4982/5000
77s 154ms/step - loss:0.0477 - acc:0.9995 - val_loss:0.2867 - val_acc:0.9431
Epoch 4983/5000
77s 154ms/step - loss:0.0485 - acc:0.9992 - val_loss:0.2864 - val_acc:0.9423
Epoch 4984/5000
77s 153ms/step - loss:0.0480 - acc:0.9994 - val_loss:0.2852 - val_acc:0.9437
Epoch 4985/5000
77s 154ms/step - loss:0.0479 - acc:0.9994 - val_loss:0.2846 - val_acc:0.9437
Epoch 4986/5000
77s 154ms/step - loss:0.0488 - acc:0.9990 - val_loss:0.2852 - val_acc:0.9433
Epoch 4987/5000
77s 154ms/step - loss:0.0484 - acc:0.9990 - val_loss:0.2831 - val_acc:0.9443
Epoch 4988/5000
77s 154ms/step - loss:0.0484 - acc:0.9993 - val_loss:0.2850 - val_acc:0.9440
Epoch 4989/5000
77s 154ms/step - loss:0.0484 - acc:0.9991 - val_loss:0.2871 - val_acc:0.9431
Epoch 4990/5000
77s 154ms/step - loss:0.0479 - acc:0.9993 - val_loss:0.2863 - val_acc:0.9433
Epoch 4991/5000
77s 153ms/step - loss:0.0483 - acc:0.9993 - val_loss:0.2868 - val_acc:0.9434
Epoch 4992/5000
77s 154ms/step - loss:0.0482 - acc:0.9992 - val_loss:0.2847 - val_acc:0.9431
Epoch 4993/5000
77s 154ms/step - loss:0.0485 - acc:0.9992 - val_loss:0.2853 - val_acc:0.9417
Epoch 4994/5000
77s 154ms/step - loss:0.0481 - acc:0.9994 - val_loss:0.2835 - val_acc:0.9422
Epoch 4995/5000
77s 154ms/step - loss:0.0481 - acc:0.9994 - val_loss:0.2836 - val_acc:0.9432
Epoch 4996/5000
77s 153ms/step - loss:0.0483 - acc:0.9991 - val_loss:0.2852 - val_acc:0.9427
Epoch 4997/5000
77s 154ms/step - loss:0.0481 - acc:0.9994 - val_loss:0.2855 - val_acc:0.9427
Epoch 4998/5000
77s 154ms/step - loss:0.0481 - acc:0.9993 - val_loss:0.2839 - val_acc:0.9430
Epoch 4999/5000
77s 154ms/step - loss:0.0478 - acc:0.9994 - val_loss:0.2855 - val_acc:0.9424
Epoch 5000/5000
77s 154ms/step - loss:0.0480 - acc:0.9993 - val_loss:0.2855 - val_acc:0.9428
Train loss:0.04765264599025249
Train accuracy:0.9993600006103516
Test loss:0.2855186524987221
Test accuracy:0.9428000026941299

       94%  

      5000 epoch   epoch   loss         

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...