[This kind can not be ignored] Dynamic ReLU: adaptive parameterized ReLU (parameter record 6)

Posted May 25, 202056 min read

Continued from the previous article:
Dynamic ReLUs:Adaptive Parametric ReLU(parameter record 5)

Adaptive parameterized ReLU is a dynamic ReLU(Dynamic ReLU), submitted to IEEE Transactions on Industrial Electronics on May 3, 2019, accepted on January 24, 2020, on 2020 2 Published on the IEEE's official website on the 13th.

This article continues to adjust the hyperparameters and test the effect of adaptive parametric ReLU on Cifar10. The basic principle is shown in the following figure:
aprelu.png

First of all, from the previous adjustments, it was found that when the learning rate decreased from 0.1 to 0.01 and from 0.01 to 0.001, the loss would be greatly reduced. The learning rate dropped to 0.001 before, so if the learning rate continues to decline, will the loss continue to decline?

Secondly, when adaptive parameterized ReLU is used, the structure of the deep residual network is more complex, more difficult to train, and may require more iterations.

Therefore, this test restores the number of iterations to 1000 epochs, and sets the learning rates of 1-300, 301-600, 601-900, and 901-1000 epochs to 0.1, 0.01, 0.001, and 0.0001, respectively.

At the same time, before the final global mean pooling, if adaptive parameterized ReLU is adopted, it seems that it is not conducive to model training. This is because the adaptive parameterized ReLU uses the sigmoid function. Therefore, the adaptive parameterized ReLU before the global mean pooling is changed to the ordinary ReLU.(For the adaptive parameterized ReLU in the residual module, the increase in training difficulty due to the existence of the identity path should be tolerable)

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 300 epoches
def scheduler(epoch):
    if epoch%300 == 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, activation = 'linear', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(scales)
    scales = BatchNormalization()(scales)
    scales = Activation('relu')(scales)
    scales = Dense(channels, activation = 'linear', kernel_initializer = 'he_normal', kernel_regularizer = l2(1e-4))(scales)
    scales = BatchNormalization()(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()(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()(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, 16, 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()(net)
net = Activation('relu')(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,
    # 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 = 1000,
                    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:

Using TensorFlow backend.
x_train shape:(50000, 32, 32, 3)
50000 train samples
10000 test samples
Epoch 1/1000
90s 179ms/step-loss:2.6847-acc:0.4191-val_loss:2.2382-val_acc:0.5544
Epoch 2/1000
62s 125ms/step-loss:2.1556-acc:0.5605-val_loss:1.8942-val_acc:0.6254
Epoch 3/1000
63s 125ms/step-loss:1.8590-acc:0.6206-val_loss:1.6930-val_acc:0.6629
Epoch 4/1000
62s 125ms/step-loss:1.6407-acc:0.6615-val_loss:1.4932-val_acc:0.6958
Epoch 5/1000
62s 125ms/step-loss:1.4706-acc:0.6923-val_loss:1.3326-val_acc:0.7317
Epoch 6/1000
62s 125ms/step-loss:1.3352-acc:0.7167-val_loss:1.2327-val_acc:0.7465
Epoch 7/1000
62s 125ms/step-loss:1.2271-acc:0.7365-val_loss:1.1326-val_acc:0.7583
Epoch 8/1000
62s 125ms/step-loss:1.1426-acc:0.7512-val_loss:1.0737-val_acc:0.7718
Epoch 9/1000
62s 125ms/step-loss:1.0724-acc:0.7643-val_loss:1.0268-val_acc:0.7720
Epoch 10/1000
62s 125ms/step-loss:1.0256-acc:0.7687-val_loss:0.9672-val_acc:0.7842
Epoch 11/1000
62s 125ms/step-loss:0.9772-acc:0.7766-val_loss:0.9104-val_acc:0.8032
Epoch 12/1000
63s 125ms/step-loss:0.9385-acc:0.7839-val_loss:0.8971-val_acc:0.8017
Epoch 13/1000
62s 125ms/step-loss:0.9109-acc:0.7910-val_loss:0.8675-val_acc:0.8073
Epoch 14/1000
62s 125ms/step-loss:0.8799-acc:0.7961-val_loss:0.8410-val_acc:0.8118
Epoch 15/1000
62s 125ms/step-loss:0.8680-acc:0.7975-val_loss:0.8337-val_acc:0.8106
Epoch 16/1000
62s 125ms/step-loss:0.8426-acc:0.8045-val_loss:0.7960-val_acc:0.8194
Epoch 17/1000
62s 124ms/step-loss:0.8230-acc:0.8088-val_loss:0.8293-val_acc:0.8065
Epoch 18/1000
62s 125ms/step-loss:0.8143-acc:0.8094-val_loss:0.7952-val_acc:0.8215
Epoch 19/1000
62s 125ms/step-loss:0.7971-acc:0.8148-val_loss:0.7876-val_acc:0.8169
Epoch 20/1000
62s 125ms/step-loss:0.7856-acc:0.8204-val_loss:0.7765-val_acc:0.8247
Epoch 21/1000
62s 124ms/step-loss:0.7774-acc:0.8191-val_loss:0.7441-val_acc:0.8361
Epoch 22/1000
62s 125ms/step-loss:0.7718-acc:0.8247-val_loss:0.7552-val_acc:0.8325
Epoch 23/1000
62s 125ms/step-loss:0.7674-acc:0.8272-val_loss:0.7786-val_acc:0.8241
Epoch 24/1000
62s 125ms/step-loss:0.7582-acc:0.8271-val_loss:0.7566-val_acc:0.8282
Epoch 25/1000
62s 125ms/step-loss:0.7448-acc:0.8315-val_loss:0.7507-val_acc:0.8336
Epoch 26/1000
62s 125ms/step-loss:0.7459-acc:0.8336-val_loss:0.7725-val_acc:0.8217
Epoch 27/1000
62s 125ms/step-loss:0.7418-acc:0.8340-val_loss:0.7581-val_acc:0.8335
Epoch 28/1000
62s 124ms/step-loss:0.7335-acc:0.8354-val_loss:0.7402-val_acc:0.8360
Epoch 29/1000
62s 125ms/step-loss:0.7332-acc:0.8372-val_loss:0.7429-val_acc:0.8394
Epoch 30/1000
62s 125ms/step-loss:0.7243-acc:0.8405-val_loss:0.7322-val_acc:0.8393
Epoch 31/1000
62s 124ms/step-loss:0.7227-acc:0.8422-val_loss:0.7098-val_acc:0.8468
Epoch 32/1000
62s 125ms/step-loss:0.7189-acc:0.8392-val_loss:0.7359-val_acc:0.8396
Epoch 33/1000
62s 125ms/step-loss:0.7144-acc:0.8455-val_loss:0.7071-val_acc:0.8442
Epoch 34/1000
62s 125ms/step-loss:0.7111-acc:0.8460-val_loss:0.7401-val_acc:0.8404
Epoch 35/1000
62s 125ms/step-loss:0.7061-acc:0.8480-val_loss:0.7155-val_acc:0.8497
Epoch 36/1000
62s 124ms/step-loss:0.7072-acc:0.8488-val_loss:0.7355-val_acc:0.8430
Epoch 37/1000
62s 125ms/step-loss:0.7077-acc:0.8496-val_loss:0.7167-val_acc:0.8521
Epoch 38/1000
62s 125ms/step-loss:0.6971-acc:0.8518-val_loss:0.7595-val_acc:0.8315
Epoch 39/1000
62s 125ms/step-loss:0.6971-acc:0.8508-val_loss:0.7278-val_acc:0.8423
Epoch 40/1000
62s 125ms/step-loss:0.6923-acc:0.8553-val_loss:0.7252-val_acc:0.8452
Epoch 41/1000
62s 125ms/step-loss:0.6935-acc:0.8538-val_loss:0.7169-val_acc:0.8461
Epoch 42/1000
62s 125ms/step-loss:0.6902-acc:0.8560-val_loss:0.7214-val_acc:0.8500
Epoch 43/1000
62s 125ms/step-loss:0.6874-acc:0.8576-val_loss:0.7078-val_acc:0.8492
Epoch 44/1000
62s 125ms/step-loss:0.6869-acc:0.8585-val_loss:0.7122-val_acc:0.8526
Epoch 45/1000
62s 124ms/step-loss:0.6830-acc:0.8587-val_loss:0.7509-val_acc:0.8411
Epoch 46/1000
62s 124ms/step-loss:0.6867-acc:0.8583-val_loss:0.7015-val_acc:0.8555
Epoch 47/1000
62s 124ms/step-loss:0.6795-acc:0.8614-val_loss:0.7051-val_acc:0.8529
Epoch 48/1000
62s 125ms/step-loss:0.6790-acc:0.8597-val_loss:0.7037-val_acc:0.8524
Epoch 49/1000
62s 125ms/step-loss:0.6790-acc:0.8612-val_loss:0.7121-val_acc:0.8526
Epoch 50/1000
62s 125ms/step-loss:0.6713-acc:0.8638-val_loss:0.7031-val_acc:0.8556
Epoch 51/1000
62s 125ms/step-loss:0.6655-acc:0.8658-val_loss:0.6827-val_acc:0.8617
Epoch 52/1000
62s 124ms/step-loss:0.6725-acc:0.8649-val_loss:0.7000-val_acc:0.8566
Epoch 53/1000
62s 125ms/step-loss:0.6669-acc:0.8677-val_loss:0.7089-val_acc:0.8599
Epoch 54/1000
62s 125ms/step-loss:0.6654-acc:0.8652-val_loss:0.6769-val_acc:0.8662
Epoch 55/1000
62s 125ms/step-loss:0.6674-acc:0.8668-val_loss:0.7016-val_acc:0.8570
Epoch 56/1000
62s 124ms/step-loss:0.6670-acc:0.8670-val_loss:0.6838-val_acc:0.8647
Epoch 57/1000
62s 125ms/step-loss:0.6667-acc:0.8672-val_loss:0.7112-val_acc:0.8595
Epoch 58/1000
62s 125ms/step-loss:0.6629-acc:0.8688-val_loss:0.7012-val_acc:0.8587
Epoch 59/1000
62s 125ms/step-loss:0.6649-acc:0.8678-val_loss:0.6854-val_acc:0.8656
Epoch 60/1000
62s 125ms/step-loss:0.6592-acc:0.8699-val_loss:0.6989-val_acc:0.8614
Epoch 61/1000
62s 125ms/step-loss:0.6591-acc:0.8696-val_loss:0.6978-val_acc:0.8603
Epoch 62/1000
62s 124ms/step-loss:0.6589-acc:0.8711-val_loss:0.6866-val_acc:0.8626
Epoch 63/1000
62s 124ms/step-loss:0.6516-acc:0.8736-val_loss:0.6845-val_acc:0.8612
Epoch 64/1000
62s 125ms/step-loss:0.6520-acc:0.8743-val_loss:0.7003-val_acc:0.8597
Epoch 65/1000
62s 125ms/step-loss:0.6544-acc:0.8736-val_loss:0.6992-val_acc:0.8593
Epoch 66/1000
62s 125ms/step-loss:0.6529-acc:0.8735-val_loss:0.6723-val_acc:0.8708
Epoch 67/1000
62s 125ms/step-loss:0.6534-acc:0.8740-val_loss:0.6958-val_acc:0.8610
Epoch 68/1000
62s 124ms/step-loss:0.6468-acc:0.8737-val_loss:0.6829-val_acc:0.8640
Epoch 69/1000
62s 125ms/step-loss:0.6463-acc:0.8760-val_loss:0.7142-val_acc:0.8552
Epoch 70/1000
62s 125ms/step-loss:0.6461-acc:0.8764-val_loss:0.6814-val_acc:0.8661
Epoch 71/1000
62s 125ms/step-loss:0.6459-acc:0.8764-val_loss:0.6884-val_acc:0.8656
Epoch 72/1000
62s 125ms/step-loss:0.6430-acc:0.8768-val_loss:0.6644-val_acc:0.8760
Epoch 73/1000
62s 125ms/step-loss:0.6406-acc:0.8774-val_loss:0.6803-val_acc:0.8710
Epoch 74/1000
62s 125ms/step-loss:0.6395-acc:0.8781-val_loss:0.6845-val_acc:0.8665
Epoch 75/1000
62s 125ms/step-loss:0.6413-acc:0.8773-val_loss:0.7124-val_acc:0.8560
Epoch 76/1000
62s 125ms/step-loss:0.6383-acc:0.8804-val_loss:0.7164-val_acc:0.8554
Epoch 77/1000
62s 125ms/step-loss:0.6385-acc:0.8806-val_loss:0.6843-val_acc:0.8661
Epoch 78/1000
62s 124ms/step-loss:0.6349-acc:0.8830-val_loss:0.7035-val_acc:0.8599
Epoch 79/1000
62s 124ms/step-loss:0.6330-acc:0.8818-val_loss:0.6983-val_acc:0.8591
Epoch 80/1000
62s 125ms/step-loss:0.6348-acc:0.8810-val_loss:0.6886-val_acc:0.8626
Epoch 81/1000
62s 125ms/step-loss:0.6323-acc:0.8817-val_loss:0.6763-val_acc:0.8680
Epoch 82/1000
62s 125ms/step-loss:0.6320-acc:0.8825-val_loss:0.6560-val_acc:0.8758
Epoch 83/1000
62s 125ms/step-loss:0.6327-acc:0.8820-val_loss:0.6592-val_acc:0.8779
Epoch 84/1000
62s 124ms/step-loss:0.6296-acc:0.8813-val_loss:0.6822-val_acc:0.8690
Epoch 85/1000
62s 125ms/step-loss:0.6310-acc:0.8810-val_loss:0.6825-val_acc:0.8703
Epoch 86/1000
62s 125ms/step-loss:0.6331-acc:0.8832-val_loss:0.6891-val_acc:0.8665
Epoch 87/1000
62s 125ms/step-loss:0.6330-acc:0.8818-val_loss:0.6806-val_acc:0.8704
Epoch 88/1000
62s 125ms/step-loss:0.6274-acc:0.8841-val_loss:0.6832-val_acc:0.8681
Epoch 89/1000
62s 125ms/step-loss:0.6313-acc:0.8821-val_loss:0.6796-val_acc:0.8694
Epoch 90/1000
62s 125ms/step-loss:0.6258-acc:0.8854-val_loss:0.6600-val_acc:0.8772
Epoch 91/1000
62s 125ms/step-loss:0.6270-acc:0.8841-val_loss:0.6670-val_acc:0.8758
Epoch 92/1000
62s 125ms/step-loss:0.6281-acc:0.8824-val_loss:0.6881-val_acc:0.8710
Epoch 93/1000
62s 124ms/step-loss:0.6265-acc:0.8847-val_loss:0.6886-val_acc:0.8698
Epoch 94/1000
62s 125ms/step-loss:0.6214-acc:0.8871-val_loss:0.6896-val_acc:0.8640
Epoch 95/1000
62s 125ms/step-loss:0.6241-acc:0.8860-val_loss:0.6674-val_acc:0.8721
Epoch 96/1000
62s 125ms/step-loss:0.6252-acc:0.8844-val_loss:0.6571-val_acc:0.8791
Epoch 97/1000
62s 125ms/step-loss:0.6227-acc:0.8856-val_loss:0.6486-val_acc:0.8797
Epoch 98/1000
62s 125ms/step-loss:0.6178-acc:0.8866-val_loss:0.6849-val_acc:0.8717
Epoch 99/1000
62s 125ms/step-loss:0.6162-acc:0.8881-val_loss:0.6726-val_acc:0.8709
Epoch 100/1000
62s 124ms/step-loss:0.6209-acc:0.8861-val_loss:0.6682-val_acc:0.8732
Epoch 101/1000
62s 125ms/step-loss:0.6190-acc:0.8883-val_loss:0.6810-val_acc:0.8723
Epoch 102/1000
62s 125ms/step-loss:0.6181-acc:0.8872-val_loss:0.6678-val_acc:0.8745
Epoch 103/1000
63s 125ms/step-loss:0.6163-acc:0.8883-val_loss:0.6870-val_acc:0.8704
Epoch 104/1000
62s 125ms/step-loss:0.6105-acc:0.8910-val_loss:0.6576-val_acc:0.8775
Epoch 105/1000
62s 125ms/step-loss:0.6120-acc:0.8902-val_loss:0.6571-val_acc:0.8800
Epoch 106/1000
62s 125ms/step-loss:0.6146-acc:0.8882-val_loss:0.6560-val_acc:0.8772
Epoch 107/1000
62s 125ms/step-loss:0.6186-acc:0.8870-val_loss:0.6773-val_acc:0.8720
Epoch 108/1000
62s 125ms/step-loss:0.6189-acc:0.8879-val_loss:0.6503-val_acc:0.8846
Epoch 109/1000
62s 125ms/step-loss:0.6110-acc:0.8896-val_loss:0.6625-val_acc:0.8782
Epoch 110/1000
62s 125ms/step-loss:0.6185-acc:0.8862-val_loss:0.6735-val_acc:0.8712
Epoch 111/1000
62s 125ms/step-loss:0.6101-acc:0.8900-val_loss:0.6510-val_acc:0.8809
Epoch 112/1000
62s 125ms/step-loss:0.6132-acc:0.8897-val_loss:0.6817-val_acc:0.8703
Epoch 113/1000
62s 125ms/step-loss:0.6049-acc:0.8941-val_loss:0.6524-val_acc:0.8776
Epoch 114/1000
62s 125ms/step-loss:0.6129-acc:0.8884-val_loss:0.6532-val_acc:0.8778
Epoch 115/1000
62s 125ms/step-loss:0.6077-acc:0.8906-val_loss:0.6650-val_acc:0.8771
Epoch 116/1000
62s 124ms/step-loss:0.6079-acc:0.8915-val_loss:0.6643-val_acc:0.8759
Epoch 117/1000
62s 125ms/step-loss:0.6102-acc:0.8903-val_loss:0.6661-val_acc:0.8757
Epoch 118/1000
62s 124ms/step-loss:0.6103-acc:0.8909-val_loss:0.6641-val_acc:0.8748
Epoch 119/1000
62s 125ms/step-loss:0.6081-acc:0.8908-val_loss:0.6744-val_acc:0.8718
Epoch 120/1000
62s 125ms/step-loss:0.6060-acc:0.8931-val_loss:0.6355-val_acc:0.8881
Epoch 121/1000
62s 125ms/step-loss:0.6063-acc:0.8925-val_loss:0.6630-val_acc:0.8768
Epoch 122/1000
62s 125ms/step-loss:0.6101-acc:0.8901-val_loss:0.6482-val_acc:0.8799
Epoch 123/1000
62s 125ms/step-loss:0.6037-acc:0.8923-val_loss:0.6467-val_acc:0.8786
Epoch 124/1000
62s 124ms/step-loss:0.6016-acc:0.8942-val_loss:0.6487-val_acc:0.8788
Epoch 125/1000
62s 125ms/step-loss:0.6089-acc:0.8915-val_loss:0.6812-val_acc:0.8683
Epoch 126/1000
62s 125ms/step-loss:0.6042-acc:0.8943-val_loss:0.6480-val_acc:0.8830
Epoch 127/1000
62s 125ms/step-loss:0.6008-acc:0.8938-val_loss:0.6765-val_acc:0.8762
Epoch 128/1000
62s 125ms/step-loss:0.6023-acc:0.8940-val_loss:0.6676-val_acc:0.8755
Epoch 129/1000
62s 125ms/step-loss:0.6046-acc:0.8925-val_loss:0.6589-val_acc:0.8750
Epoch 130/1000
62s 125ms/step-loss:0.6008-acc:0.8949-val_loss:0.6580-val_acc:0.8805
Epoch 131/1000
62s 125ms/step-loss:0.6008-acc:0.8947-val_loss:0.6546-val_acc:0.8825
Epoch 132/1000
62s 125ms/step-loss:0.6009-acc:0.8946-val_loss:0.6434-val_acc:0.8833
Epoch 133/1000
62s 125ms/step-loss:0.6019-acc:0.8937-val_loss:0.6498-val_acc:0.8828
Epoch 134/1000
62s 125ms/step-loss:0.5977-acc:0.8942-val_loss:0.6527-val_acc:0.8796
Epoch 135/1000
62s 125ms/step-loss:0.6013-acc:0.8941-val_loss:0.6239-val_acc:0.8875
Epoch 136/1000
62s 125ms/step-loss:0.5946-acc:0.8964-val_loss:0.6379-val_acc:0.8843
Epoch 137/1000
62s 125ms/step-loss:0.5959-acc:0.8945-val_loss:0.6549-val_acc:0.8792
Epoch 138/1000
62s 125ms/step-loss:0.5975-acc:0.8946-val_loss:0.6546-val_acc:0.8814
Epoch 139/1000
62s 125ms/step-loss:0.5954-acc:0.8958-val_loss:0.6686-val_acc:0.8734
Epoch 140/1000
62s 125ms/step-loss:0.5963-acc:0.8959-val_loss:0.6363-val_acc:0.8845
Epoch 141/1000
62s 125ms/step-loss:0.5959-acc:0.8947-val_loss:0.6745-val_acc:0.8745
Epoch 142/1000
62s 124ms/step-loss:0.5988-acc:0.8934-val_loss:0.6512-val_acc:0.8818
Epoch 143/1000
62s 125ms/step-loss:0.5940-acc:0.8977-val_loss:0.6644-val_acc:0.8784
Epoch 144/1000
62s 125ms/step-loss:0.5928-acc:0.8974-val_loss:0.6601-val_acc:0.8758
Epoch 145/1000
62s 124ms/step-loss:0.6008-acc:0.8951-val_loss:0.6376-val_acc:0.8871
Epoch 146/1000
62s 125ms/step-loss:0.5949-acc:0.8962-val_loss:0.6469-val_acc:0.8855
Epoch 147/1000
62s 125ms/step-loss:0.5922-acc:0.8969-val_loss:0.6538-val_acc:0.8787
Epoch 148/1000
62s 125ms/step-loss:0.5964-acc:0.8968-val_loss:0.6406-val_acc:0.8842
Epoch 149/1000
62s 124ms/step-loss:0.5937-acc:0.8974-val_loss:0.6441-val_acc:0.8832
Epoch 150/1000
62s 125ms/step-loss:0.5988-acc:0.8955-val_loss:0.6565-val_acc:0.8786
Epoch 151/1000
62s 125ms/step-loss:0.5906-acc:0.8978-val_loss:0.6429-val_acc:0.8822
Epoch 152/1000
62s 125ms/step-loss:0.5928-acc:0.8969-val_loss:0.6567-val_acc:0.8777
Epoch 153/1000
62s 125ms/step-loss:0.5906-acc:0.8974-val_loss:0.6490-val_acc:0.8854
Epoch 154/1000
62s 125ms/step-loss:0.5916-acc:0.8977-val_loss:0.6577-val_acc:0.8789
Epoch 155/1000
62s 125ms/step-loss:0.5898-acc:0.8990-val_loss:0.6776-val_acc:0.8713
Epoch 156/1000
62s 125ms/step-loss:0.5947-acc:0.8975-val_loss:0.6373-val_acc:0.8840
Epoch 157/1000
62s 125ms/step-loss:0.5936-acc:0.8966-val_loss:0.6297-val_acc:0.8873
Epoch 158/1000
62s 125ms/step-loss:0.5873-acc:0.8995-val_loss:0.6499-val_acc:0.8765
Epoch 159/1000
62s 125ms/step-loss:0.5845-acc:0.8995-val_loss:0.6369-val_acc:0.8839
Epoch 160/1000
62s 125ms/step-loss:0.5928-acc:0.8961-val_loss:0.6585-val_acc:0.8782
Epoch 161/1000
62s 125ms/step-loss:0.5877-acc:0.8970-val_loss:0.6343-val_acc:0.8836
Epoch 162/1000
62s 125ms/step-loss:0.5868-acc:0.9000-val_loss:0.6437-val_acc:0.8803
Epoch 163/1000
62s 125ms/step-loss:0.5902-acc:0.8980-val_loss:0.6356-val_acc:0.8863
Epoch 164/1000
62s 125ms/step-loss:0.5832-acc:0.9012-val_loss:0.6400-val_acc:0.8874
Epoch 165/1000
62s 125ms/step-loss:0.5892-acc:0.8984-val_loss:0.6582-val_acc:0.8766
Epoch 166/1000
62s 124ms/step-loss:0.5867-acc:0.9009-val_loss:0.6727-val_acc:0.8725
Epoch 167/1000
62s 125ms/step-loss:0.5857-acc:0.9007-val_loss:0.6682-val_acc:0.8746
Epoch 168/1000
62s 125ms/step-loss:0.5886-acc:0.8999-val_loss:0.6429-val_acc:0.8844
Epoch 169/1000
62s 125ms/step-loss:0.5855-acc:0.8996-val_loss:0.6534-val_acc:0.8780
Epoch 170/1000
62s 125ms/step-loss:0.5877-acc:0.8997-val_loss:0.6453-val_acc:0.8814
Epoch 171/1000
62s 125ms/step-loss:0.5852-acc:0.8978-val_loss:0.6388-val_acc:0.8846
Epoch 172/1000
62s 125ms/step-loss:0.5878-acc:0.8986-val_loss:0.6310-val_acc:0.8883
Epoch 173/1000
62s 125ms/step-loss:0.5862-acc:0.9018-val_loss:0.6279-val_acc:0.8885
Epoch 174/1000
62s 125ms/step-loss:0.5867-acc:0.8993-val_loss:0.6682-val_acc:0.8762
Epoch 175/1000
62s 125ms/step-loss:0.5859-acc:0.8995-val_loss:0.6573-val_acc:0.8798
Epoch 176/1000
62s 125ms/step-loss:0.5828-acc:0.9017-val_loss:0.6472-val_acc:0.8835
Epoch 177/1000
62s 125ms/step-loss:0.5819-acc:0.9010-val_loss:0.6735-val_acc:0.8753
Epoch 178/1000
62s 125ms/step-loss:0.5875-acc:0.8993-val_loss:0.6420-val_acc:0.8860
Epoch 179/1000
62s 125ms/step-loss:0.5840-acc:0.9000-val_loss:0.6490-val_acc:0.8809
Epoch 180/1000
62s 125ms/step-loss:0.5796-acc:0.9035-val_loss:0.6586-val_acc:0.8760
Epoch 181/1000
62s 125ms/step-loss:0.5811-acc:0.9031-val_loss:0.6387-val_acc:0.8864
Epoch 182/1000
62s 125ms/step-loss:0.5811-acc:0.9015-val_loss:0.6334-val_acc:0.8890
Epoch 183/1000
62s 125ms/step-loss:0.5835-acc:0.9017-val_loss:0.6471-val_acc:0.8775
Epoch 184/1000
62s 124ms/step-loss:0.5801-acc:0.9015-val_loss:0.6620-val_acc:0.8785
Epoch 185/1000
62s 125ms/step-loss:0.5770-acc:0.9023-val_loss:0.6412-val_acc:0.8842
Epoch 186/1000
62s 125ms/step-loss:0.5768-acc:0.9024-val_loss:0.6341-val_acc:0.8828
Epoch 187/1000
62s 124ms/step-loss:0.5817-acc:0.9006-val_loss:0.6304-val_acc:0.8896
Epoch 188/1000
62s 125ms/step-loss:0.5835-acc:0.9008-val_loss:0.6491-val_acc:0.8820
Epoch 189/1000
62s 125ms/step-loss:0.5863-acc:0.8995-val_loss:0.6389-val_acc:0.8825
Epoch 190/1000
62s 125ms/step-loss:0.5832-acc:0.9016-val_loss:0.6362-val_acc:0.8833
Epoch 191/1000
62s 125ms/step-loss:0.5798-acc:0.9022-val_loss:0.6460-val_acc:0.8804
Epoch 192/1000
62s 125ms/step-loss:0.5801-acc:0.9007-val_loss:0.6358-val_acc:0.8869
Epoch 193/1000
62s 125ms/step-loss:0.5807-acc:0.9016-val_loss:0.6472-val_acc:0.8820
Epoch 194/1000
62s 125ms/step-loss:0.5774-acc:0.9024-val_loss:0.6542-val_acc:0.8825
Epoch 195/1000
62s 125ms/step-loss:0.5758-acc:0.9034-val_loss:0.6429-val_acc:0.8832
Epoch 196/1000
62s 125ms/step-loss:0.5784-acc:0.9020-val_loss:0.6505-val_acc:0.8826
Epoch 197/1000
62s 125ms/step-loss:0.5830-acc:0.9010-val_loss:0.6669-val_acc:0.8741
Epoch 198/1000
62s 125ms/step-loss:0.5769-acc:0.9026-val_loss:0.6474-val_acc:0.8814
Epoch 199/1000
62s 125ms/step-loss:0.5772-acc:0.9031-val_loss:0.6297-val_acc:0.8862
Epoch 200/1000
62s 125ms/step-loss:0.5780-acc:0.9023-val_loss:0.6459-val_acc:0.8843
Epoch 201/1000
62s 125ms/step-loss:0.5816-acc:0.9016-val_loss:0.6652-val_acc:0.8745
Epoch 202/1000
62s 125ms/step-loss:0.5764-acc:0.9032-val_loss:0.6306-val_acc:0.8869
Epoch 203/1000
62s 125ms/step-loss:0.5759-acc:0.9038-val_loss:0.6328-val_acc:0.8881
Epoch 204/1000
63s 125ms/step-loss:0.5766-acc:0.9031-val_loss:0.6786-val_acc:0.8753
Epoch 205/1000
62s 125ms/step-loss:0.5756-acc:0.9035-val_loss:0.6442-val_acc:0.8841
Epoch 206/1000
62s 125ms/step-loss:0.5788-acc:0.9020-val_loss:0.6505-val_acc:0.8813
Epoch 207/1000
62s 125ms/step-loss:0.5797-acc:0.9019-val_loss:0.6414-val_acc:0.8839
Epoch 208/1000
62s 125ms/step-loss:0.5755-acc:0.9050-val_loss:0.6436-val_acc:0.8870
Epoch 209/1000
62s 125ms/step-loss:0.5782-acc:0.9013-val_loss:0.6619-val_acc:0.8765
Epoch 210/1000
62s 125ms/step-loss:0.5786-acc:0.9009-val_loss:0.6482-val_acc:0.8798
Epoch 211/1000
62s 125ms/step-loss:0.5727-acc:0.9039-val_loss:0.6324-val_acc:0.8879
Epoch 212/1000
62s 125ms/step-loss:0.5801-acc:0.9024-val_loss:0.6353-val_acc:0.8846
Epoch 213/1000
62s 124ms/step-loss:0.5747-acc:0.9046-val_loss:0.6388-val_acc:0.8827
Epoch 214/1000
62s 125ms/step-loss:0.5728-acc:0.9043-val_loss:0.6470-val_acc:0.8822
Epoch 215/1000
62s 125ms/step-loss:0.5747-acc:0.9045-val_loss:0.6394-val_acc:0.8889
Epoch 216/1000
62s 125ms/step-loss:0.5734-acc:0.9041-val_loss:0.6465-val_acc:0.8853
Epoch 217/1000
62s 125ms/step-loss:0.5696-acc:0.9072-val_loss:0.6500-val_acc:0.8838
Epoch 218/1000
62s 124ms/step-loss:0.5727-acc:0.9055-val_loss:0.6214-val_acc:0.8929
Epoch 219/1000
62s 125ms/step-loss:0.5737-acc:0.9048-val_loss:0.6288-val_acc:0.8885
Epoch 220/1000
62s 125ms/step-loss:0.5734-acc:0.9039-val_loss:0.6399-val_acc:0.8863
Epoch 221/1000
62s 124ms/step-loss:0.5740-acc:0.9047-val_loss:0.6256-val_acc:0.8906
Epoch 222/1000
62s 125ms/step-loss:0.5714-acc:0.9054-val_loss:0.6390-val_acc:0.8812
Epoch 223/1000
62s 125ms/step-loss:0.5795-acc:0.9017-val_loss:0.6447-val_acc:0.8851
Epoch 224/1000
62s 125ms/step-loss:0.5687-acc:0.9062-val_loss:0.6262-val_acc:0.8902
Epoch 225/1000
62s 125ms/step-loss:0.5713-acc:0.9034-val_loss:0.6379-val_acc:0.8857
Epoch 226/1000
62s 125ms/step-loss:0.5735-acc:0.9047-val_loss:0.6319-val_acc:0.8888
Epoch 227/1000
62s 125ms/step-loss:0.5749-acc:0.9044-val_loss:0.6353-val_acc:0.8870
Epoch 228/1000
62s 125ms/step-loss:0.5699-acc:0.9056-val_loss:0.6265-val_acc:0.8927
Epoch 229/1000
62s 125ms/step-loss:0.5718-acc:0.9048-val_loss:0.6291-val_acc:0.8865
Epoch 230/1000
62s 125ms/step-loss:0.5678-acc:0.9060-val_loss:0.6318-val_acc:0.8873
Epoch 231/1000
62s 125ms/step-loss:0.5699-acc:0.9060-val_loss:0.6378-val_acc:0.8859
Epoch 232/1000
62s 125ms/step-loss:0.5694-acc:0.9054-val_loss:0.6263-val_acc:0.8896
Epoch 233/1000
62s 125ms/step-loss:0.5748-acc:0.9040-val_loss:0.6202-val_acc:0.8964
Epoch 234/1000
62s 125ms/step-loss:0.5693-acc:0.9070-val_loss:0.6358-val_acc:0.8882
Epoch 235/1000
62s 125ms/step-loss:0.5712-acc:0.9040-val_loss:0.6529-val_acc:0.8811
Epoch 236/1000
62s 125ms/step-loss:0.5663-acc:0.9060-val_loss:0.6340-val_acc:0.8873
Epoch 237/1000
62s 124ms/step-loss:0.5717-acc:0.9047-val_loss:0.6391-val_acc:0.8869
Epoch 238/1000
62s 125ms/step-loss:0.5692-acc:0.9060-val_loss:0.6419-val_acc:0.8849
Epoch 239/1000
62s 125ms/step-loss:0.5732-acc:0.9059-val_loss:0.6274-val_acc:0.8862
Epoch 240/1000
62s 125ms/step-loss:0.5735-acc:0.9036-val_loss:0.6352-val_acc:0.8881
Epoch 241/1000
62s 125ms/step-loss:0.5672-acc:0.9064-val_loss:0.6263-val_acc:0.8871
Epoch 242/1000
62s 125ms/step-loss:0.5734-acc:0.9050-val_loss:0.6380-val_acc:0.8868
Epoch 243/1000
62s 125ms/step-loss:0.5693-acc:0.9061-val_loss:0.6313-val_acc:0.8865
Epoch 244/1000
62s 124ms/step-loss:0.5663-acc:0.9068-val_loss:0.6544-val_acc:0.8811
Epoch 245/1000
62s 125ms/step-loss:0.5697-acc:0.9066-val_loss:0.6647-val_acc:0.8791
Epoch 246/1000
62s 124ms/step-loss:0.5749-acc:0.9026-val_loss:0.6451-val_acc:0.8802
Epoch 247/1000
62s 125ms/step-loss:0.5712-acc:0.9053-val_loss:0.6448-val_acc:0.8837
Epoch 248/1000
62s 125ms/step-loss:0.5739-acc:0.9061-val_loss:0.6252-val_acc:0.8923
Epoch 249/1000
62s 125ms/step-loss:0.5716-acc:0.9051-val_loss:0.6571-val_acc:0.8809
Epoch 250/1000
62s 125ms/step-loss:0.5703-acc:0.9062-val_loss:0.6289-val_acc:0.8879
Epoch 251/1000
62s 125ms/step-loss:0.5689-acc:0.9055-val_loss:0.6302-val_acc:0.8898
Epoch 252/1000
62s 124ms/step-loss:0.5650-acc:0.9066-val_loss:0.6394-val_acc:0.8863
Epoch 253/1000
62s 124ms/step-loss:0.5688-acc:0.9067-val_loss:0.6249-val_acc:0.8884
Epoch 254/1000
62s 125ms/step-loss:0.5681-acc:0.9062-val_loss:0.6199-val_acc:0.8918
Epoch 255/1000
62s 125ms/step-loss:0.5661-acc:0.9079-val_loss:0.6540-val_acc:0.8822
Epoch 256/1000
62s 125ms/step-loss:0.5697-acc:0.9055-val_loss:0.6553-val_acc:0.8796
Epoch 257/1000
62s 125ms/step-loss:0.5672-acc:0.9067-val_loss:0.6183-val_acc:0.8944
Epoch 258/1000
62s 125ms/step-loss:0.5632-acc:0.9088-val_loss:0.6358-val_acc:0.8896
Epoch 259/1000
62s 125ms/step-loss:0.5679-acc:0.9063-val_loss:0.6347-val_acc:0.8866
Epoch 260/1000
62s 124ms/step-loss:0.5638-acc:0.9071-val_loss:0.6528-val_acc:0.8803
Epoch 261/1000
62s 124ms/step-loss:0.5723-acc:0.9055-val_loss:0.6438-val_acc:0.8848
Epoch 262/1000
62s 125ms/step-loss:0.5671-acc:0.9073-val_loss:0.6208-val_acc:0.8894
Epoch 263/1000
62s 125ms/step-loss:0.5677-acc:0.9057-val_loss:0.6412-val_acc:0.8846
Epoch 264/1000
62s 124ms/step-loss:0.5684-acc:0.9074-val_loss:0.6129-val_acc:0.8942
Epoch 265/1000
62s 125ms/step-loss:0.5701-acc:0.9072-val_loss:0.6283-val_acc:0.8881
Epoch 266/1000
62s 125ms/step-loss:0.5671-acc:0.9073-val_loss:0.6324-val_acc:0.8862
Epoch 267/1000
62s 125ms/step-loss:0.5630-acc:0.9078-val_loss:0.6319-val_acc:0.8862
Epoch 268/1000
62s 125ms/step-loss:0.5625-acc:0.9078-val_loss:0.6415-val_acc:0.8786
Epoch 269/1000
62s 125ms/step-loss:0.5605-acc:0.9084-val_loss:0.6366-val_acc:0.8871
Epoch 270/1000
62s 125ms/step-loss:0.5639-acc:0.9076-val_loss:0.6345-val_acc:0.8890
Epoch 271/1000
62s 124ms/step-loss:0.5692-acc:0.9052-val_loss:0.6379-val_acc:0.8817
Epoch 272/1000
62s 125ms/step-loss:0.5650-acc:0.9071-val_loss:0.6334-val_acc:0.8867
Epoch 273/1000
62s 125ms/step-loss:0.5651-acc:0.9082-val_loss:0.6315-val_acc:0.8869
Epoch 274/1000
62s 125ms/step-loss:0.5631-acc:0.9092-val_loss:0.6232-val_acc:0.8899
Epoch 275/1000
62s 125ms/step-loss:0.5642-acc:0.9086-val_loss:0.6296-val_acc:0.8907
Epoch 276/1000
62s 124ms/step-loss:0.5663-acc:0.9076-val_loss:0.6068-val_acc:0.8949
Epoch 277/1000
62s 125ms/step-loss:0.5685-acc:0.9057-val_loss:0.6036-val_acc:0.8994
Epoch 278/1000
62s 125ms/step-loss:0.5659-acc:0.9087-val_loss:0.6275-val_acc:0.8889
Epoch 279/1000
62s 124ms/step-loss:0.5677-acc:0.9065-val_loss:0.6267-val_acc:0.8872
Epoch 280/1000
62s 124ms/step-loss:0.5694-acc:0.9060-val_loss:0.6318-val_acc:0.8881
Epoch 281/1000
62s 125ms/step-loss:0.5601-acc:0.9100-val_loss:0.6203-val_acc:0.8932
Epoch 282/1000
62s 125ms/step-loss:0.5631-acc:0.9071-val_loss:0.6395-val_acc:0.8856
Epoch 283/1000
62s 125ms/step-loss:0.5646-acc:0.9088-val_loss:0.6373-val_acc:0.8895
Epoch 284/1000
62s 124ms/step-loss:0.5605-acc:0.9083-val_loss:0.6456-val_acc:0.8836
Epoch 285/1000
62s 124ms/step-loss:0.5618-acc:0.9094-val_loss:0.6225-val_acc:0.8900
Epoch 286/1000
62s 124ms/step-loss:0.5683-acc:0.9061-val_loss:0.6444-val_acc:0.8853
Epoch 287/1000
62s 124ms/step-loss:0.5661-acc:0.9075-val_loss:0.6479-val_acc:0.8834
Epoch 288/1000
62s 125ms/step-loss:0.5622-acc:0.9099-val_loss:0.6137-val_acc:0.8955
Epoch 289/1000
62s 125ms/step-loss:0.5630-acc:0.9075-val_loss:0.6212-val_acc:0.8944
Epoch 290/1000
62s 125ms/step-loss:0.5621-acc:0.9084-val_loss:0.6434-val_acc:0.8861
Epoch 291/1000
62s 125ms/step-loss:0.5656-acc:0.9087-val_loss:0.6248-val_acc:0.8911
Epoch 292/1000
62s 124ms/step-loss:0.5625-acc:0.9085-val_loss:0.6322-val_acc:0.8902
Epoch 293/1000
62s 125ms/step-loss:0.5637-acc:0.9094-val_loss:0.6321-val_acc:0.8867
Epoch 294/1000
62s 125ms/step-loss:0.5668-acc:0.9070-val_loss:0.6236-val_acc:0.8887
Epoch 295/1000
62s 125ms/step-loss:0.5622-acc:0.9091-val_loss:0.6359-val_acc:0.8880
Epoch 296/1000
62s 125ms/step-loss:0.5614-acc:0.9094-val_loss:0.6290-val_acc:0.8901
Epoch 297/1000
62s 125ms/step-loss:0.5610-acc:0.9092-val_loss:0.6358-val_acc:0.8905
Epoch 298/1000
62s 125ms/step-loss:0.5584-acc:0.9103-val_loss:0.6199-val_acc:0.8935
Epoch 299/1000
62s 125ms/step-loss:0.5660-acc:0.9069-val_loss:0.6153-val_acc:0.8957
Epoch 300/1000
62s 124ms/step-loss:0.5578-acc:0.9106-val_loss:0.6273-val_acc:0.8939
Epoch 301/1000
lr changed to 0.010000000149011612
62s 124ms/step-loss:0.4654-acc:0.9431-val_loss:0.5402-val_acc:0.9195
Epoch 302/1000
63s 125ms/step-loss:0.4160-acc:0.9576-val_loss:0.5281-val_acc:0.9208
Epoch 303/1000
63s 125ms/step-loss:0.3942-acc:0.9640-val_loss:0.5227-val_acc:0.9234
Epoch 304/1000
62s 125ms/step-loss:0.3791-acc:0.9677-val_loss:0.5185-val_acc:0.9257
Epoch 305/1000
62s 125ms/step-loss:0.3685-acc:0.9689-val_loss:0.5151-val_acc:0.9273
Epoch 306/1000
62s 125ms/step-loss:0.3548-acc:0.9717-val_loss:0.5098-val_acc:0.9268
Epoch 307/1000
62s 125ms/step-loss:0.3455-acc:0.9737-val_loss:0.5064-val_acc:0.9260
Epoch 308/1000
62s 124ms/step-loss:0.3382-acc:0.9758-val_loss:0.5038-val_acc:0.9268
Epoch 309/1000
62s 125ms/step-loss:0.3281-acc:0.9766-val_loss:0.5063-val_acc:0.9248
Epoch 310/1000
62s 125ms/step-loss:0.3208-acc:0.9779-val_loss:0.5018-val_acc:0.9242
Epoch 311/1000
62s 125ms/step-loss:0.3133-acc:0.9792-val_loss:0.5024-val_acc:0.9248
Epoch 312/1000
62s 125ms/step-loss:0.3078-acc:0.9790-val_loss:0.4962-val_acc:0.9250
Epoch 313/1000
63s 125ms/step-loss:0.2999-acc:0.9810-val_loss:0.5008-val_acc:0.9234
Epoch 314/1000
62s 125ms/step-loss:0.2930-acc:0.9817-val_loss:0.4988-val_acc:0.9227
Epoch 315/1000
62s 125ms/step-loss:0.2868-acc:0.9824-val_loss:0.4896-val_acc:0.9221
Epoch 316/1000
62s 125ms/step-loss:0.2815-acc:0.9827-val_loss:0.4896-val_acc:0.9255
Epoch 317/1000
62s 125ms/step-loss:0.2752-acc:0.9834-val_loss:0.4882-val_acc:0.9233
Epoch 318/1000
62s 125ms/step-loss:0.2719-acc:0.9836-val_loss:0.4935-val_acc:0.9225
Epoch 319/1000
62s 125ms/step-loss:0.2659-acc:0.9839-val_loss:0.4843-val_acc:0.9230
Epoch 320/1000
62s 125ms/step - loss:0.2607 - acc:0.9845 - val_loss:0.4881 - val_acc:0.9221
Epoch 321/1000
62s 125ms/step - loss:0.2561 - acc:0.9850 - val_loss:0.4871 - val_acc:0.9200
Epoch 322/1000
62s 125ms/step - loss:0.2543 - acc:0.9846 - val_loss:0.4793 - val_acc:0.9227
Epoch 323/1000
62s 125ms/step - loss:0.2500 - acc:0.9852 - val_loss:0.4661 - val_acc:0.9221
Epoch 324/1000
62s 125ms/step - loss:0.2459 - acc:0.9851 - val_loss:0.4621 - val_acc:0.9260
Epoch 325/1000
62s 125ms/step - loss:0.2410 - acc:0.9855 - val_loss:0.4690 - val_acc:0.9236
Epoch 326/1000
62s 125ms/step - loss:0.2352 - acc:0.9866 - val_loss:0.4689 - val_acc:0.9227
Epoch 327/1000
62s 125ms/step - loss:0.2334 - acc:0.9860 - val_loss:0.4711 - val_acc:0.9205
Epoch 328/1000
62s 125ms/step - loss:0.2296 - acc:0.9863 - val_loss:0.4718 - val_acc:0.9231
Epoch 329/1000
62s 125ms/step - loss:0.2259 - acc:0.9869 - val_loss:0.4648 - val_acc:0.9212
Epoch 330/1000
62s 125ms/step - loss:0.2211 - acc:0.9875 - val_loss:0.4697 - val_acc:0.9229
Epoch 331/1000
62s 125ms/step - loss:0.2228 - acc:0.9861 - val_loss:0.4697 - val_acc:0.9200
Epoch 332/1000
62s 124ms/step - loss:0.2175 - acc:0.9862 - val_loss:0.4546 - val_acc:0.9224
Epoch 333/1000
62s 125ms/step - loss:0.2143 - acc:0.9872 - val_loss:0.4580 - val_acc:0.9229
Epoch 334/1000
62s 124ms/step - loss:0.2107 - acc:0.9878 - val_loss:0.4492 - val_acc:0.9197
Epoch 335/1000
62s 125ms/step - loss:0.2080 - acc:0.9875 - val_loss:0.4626 - val_acc:0.9184
Epoch 336/1000
62s 125ms/step - loss:0.2066 - acc:0.9870 - val_loss:0.4614 - val_acc:0.9180
Epoch 337/1000
62s 125ms/step - loss:0.2045 - acc:0.9871 - val_loss:0.4447 - val_acc:0.9210
Epoch 338/1000
62s 125ms/step - loss:0.2001 - acc:0.9874 - val_loss:0.4554 - val_acc:0.9207
Epoch 339/1000
62s 125ms/step - loss:0.1991 - acc:0.9877 - val_loss:0.4527 - val_acc:0.9206
Epoch 340/1000
62s 125ms/step - loss:0.1958 - acc:0.9878 - val_loss:0.4630 - val_acc:0.9157
Epoch 341/1000
62s 125ms/step - loss:0.1957 - acc:0.9868 - val_loss:0.4447 - val_acc:0.9225
Epoch 342/1000
62s 125ms/step - loss:0.1939 - acc:0.9870 - val_loss:0.4558 - val_acc:0.9160
Epoch 343/1000
63s 125ms/step - loss:0.1921 - acc:0.9866 - val_loss:0.4451 - val_acc:0.9195
Epoch 344/1000
62s 125ms/step - loss:0.1929 - acc:0.9860 - val_loss:0.4431 - val_acc:0.9213
Epoch 345/1000
62s 125ms/step - loss:0.1889 - acc:0.9864 - val_loss:0.4386 - val_acc:0.9213
Epoch 346/1000
62s 125ms/step - loss:0.1865 - acc:0.9869 - val_loss:0.4504 - val_acc:0.9167
Epoch 347/1000
62s 125ms/step - loss:0.1847 - acc:0.9870 - val_loss:0.4285 - val_acc:0.9196
Epoch 348/1000
62s 125ms/step - loss:0.1836 - acc:0.9865 - val_loss:0.4252 - val_acc:0.9220
Epoch 349/1000
62s 124ms/step - loss:0.1827 - acc:0.9864 - val_loss:0.4364 - val_acc:0.9205
Epoch 350/1000
62s 125ms/step - loss:0.1800 - acc:0.9870 - val_loss:0.4379 - val_acc:0.9214
Epoch 351/1000
62s 125ms/step - loss:0.1793 - acc:0.9869 - val_loss:0.4343 - val_acc:0.9193
Epoch 352/1000
62s 125ms/step - loss:0.1768 - acc:0.9873 - val_loss:0.4342 - val_acc:0.9216
Epoch 353/1000
62s 125ms/step - loss:0.1784 - acc:0.9855 - val_loss:0.4390 - val_acc:0.9192
Epoch 354/1000
63s 125ms/step - loss:0.1763 - acc:0.9860 - val_loss:0.4257 - val_acc:0.9197
Epoch 355/1000
62s 125ms/step - loss:0.1724 - acc:0.9867 - val_loss:0.4276 - val_acc:0.9191
Epoch 356/1000
62s 124ms/step - loss:0.1727 - acc:0.9867 - val_loss:0.4395 - val_acc:0.9202
Epoch 357/1000
62s 124ms/step - loss:0.1710 - acc:0.9860 - val_loss:0.4386 - val_acc:0.9174
Epoch 358/1000
62s 125ms/step - loss:0.1722 - acc:0.9852 - val_loss:0.4284 - val_acc:0.9179
Epoch 359/1000
62s 125ms/step - loss:0.1691 - acc:0.9870 - val_loss:0.4245 - val_acc:0.9213
Epoch 360/1000
62s 125ms/step - loss:0.1687 - acc:0.9859 - val_loss:0.4181 - val_acc:0.9153
Epoch 361/1000
62s 125ms/step - loss:0.1684 - acc:0.9861 - val_loss:0.4114 - val_acc:0.9186
Epoch 362/1000
62s 125ms/step - loss:0.1650 - acc:0.9867 - val_loss:0.4036 - val_acc:0.9195
Epoch 363/1000
62s 125ms/step - loss:0.1690 - acc:0.9853 - val_loss:0.4161 - val_acc:0.9183
Epoch 364/1000
62s 125ms/step - loss:0.1651 - acc:0.9859 - val_loss:0.4265 - val_acc:0.9159
Epoch 365/1000
62s 124ms/step - loss:0.1666 - acc:0.9853 - val_loss:0.4090 - val_acc:0.9208
Epoch 366/1000
62s 124ms/step - loss:0.1650 - acc:0.9854 - val_loss:0.4077 - val_acc:0.9237
Epoch 367/1000
62s 124ms/step - loss:0.1656 - acc:0.9850 - val_loss:0.4051 - val_acc:0.9215
Epoch 368/1000
62s 124ms/step - loss:0.1616 - acc:0.9860 - val_loss:0.4279 - val_acc:0.9154
Epoch 369/1000
62s 124ms/step - loss:0.1657 - acc:0.9844 - val_loss:0.4328 - val_acc:0.9136
Epoch 370/1000
62s 124ms/step - loss:0.1624 - acc:0.9851 - val_loss:0.4312 - val_acc:0.9144
Epoch 371/1000
62s 124ms/step - loss:0.1648 - acc:0.9842 - val_loss:0.4086 - val_acc:0.9181
Epoch 372/1000
62s 124ms/step - loss:0.1615 - acc:0.9853 - val_loss:0.4178 - val_acc:0.9195
Epoch 373/1000
62s 123ms/step - loss:0.1620 - acc:0.9846 - val_loss:0.3955 - val_acc:0.9195
Epoch 374/1000
62s 123ms/step - loss:0.1602 - acc:0.9853 - val_loss:0.4074 - val_acc:0.9197
Epoch 375/1000
62s 124ms/step - loss:0.1612 - acc:0.9842 - val_loss:0.4081 - val_acc:0.9187
Epoch 376/1000
62s 124ms/step - loss:0.1611 - acc:0.9845 - val_loss:0.4138 - val_acc:0.9174
Epoch 377/1000
62s 124ms/step - loss:0.1603 - acc:0.9840 - val_loss:0.4135 - val_acc:0.9168
Epoch 378/1000
62s 124ms/step - loss:0.1597 - acc:0.9840 - val_loss:0.4254 - val_acc:0.9158
Epoch 379/1000
62s 123ms/step - loss:0.1610 - acc:0.9845 - val_loss:0.4306 - val_acc:0.9155
Epoch 380/1000
62s 124ms/step - loss:0.1590 - acc:0.9842 - val_loss:0.4183 - val_acc:0.9137
Epoch 381/1000
62s 124ms/step - loss:0.1600 - acc:0.9835 - val_loss:0.4124 - val_acc:0.9180
Epoch 382/1000
62s 123ms/step - loss:0.1574 - acc:0.9840 - val_loss:0.4224 - val_acc:0.9173
Epoch 383/1000
62s 124ms/step - loss:0.1564 - acc:0.9850 - val_loss:0.4164 - val_acc:0.9182
Epoch 384/1000
62s 124ms/step - loss:0.1535 - acc:0.9855 - val_loss:0.4009 - val_acc:0.9218
Epoch 385/1000
62s 124ms/step - loss:0.1577 - acc:0.9830 - val_loss:0.4206 - val_acc:0.9150
Epoch 386/1000
62s 125ms/step - loss:0.1576 - acc:0.9838 - val_loss:0.4181 - val_acc:0.9158
Epoch 387/1000
62s 125ms/step - loss:0.1567 - acc:0.9843 - val_loss:0.4205 - val_acc:0.9139
Epoch 388/1000
62s 124ms/step - loss:0.1548 - acc:0.9845 - val_loss:0.4168 - val_acc:0.9160
Epoch 389/1000
62s 124ms/step - loss:0.1570 - acc:0.9832 - val_loss:0.4166 - val_acc:0.9178
Epoch 390/1000
62s 124ms/step - loss:0.1557 - acc:0.9842 - val_loss:0.4142 - val_acc:0.9159
Epoch 391/1000
62s 125ms/step - loss:0.1592 - acc:0.9826 - val_loss:0.4110 - val_acc:0.9186
Epoch 392/1000
62s 125ms/step - loss:0.1577 - acc:0.9832 - val_loss:0.4116 - val_acc:0.9180
Epoch 393/1000
62s 125ms/step - loss:0.1570 - acc:0.9838 - val_loss:0.4033 - val_acc:0.9168
Epoch 394/1000
62s 124ms/step - loss:0.1564 - acc:0.9838 - val_loss:0.4234 - val_acc:0.9134
Epoch 395/1000
62s 125ms/step - loss:0.1587 - acc:0.9825 - val_loss:0.3980 - val_acc:0.9216
Epoch 396/1000
62s 124ms/step - loss:0.1562 - acc:0.9833 - val_loss:0.4011 - val_acc:0.9188
Epoch 397/1000
62s 124ms/step - loss:0.1553 - acc:0.9838 - val_loss:0.4025 - val_acc:0.9161
Epoch 398/1000
62s 124ms/step - loss:0.1531 - acc:0.9845 - val_loss:0.3951 - val_acc:0.9195
Epoch 399/1000
62s 124ms/step - loss:0.1521 - acc:0.9848 - val_loss:0.4025 - val_acc:0.9188
Epoch 400/1000
62s 125ms/step - loss:0.1554 - acc:0.9833 - val_loss:0.4085 - val_acc:0.9161
Epoch 401/1000
62s 125ms/step - loss:0.1542 - acc:0.9841 - val_loss:0.4103 - val_acc:0.9202
Epoch 402/1000
62s 125ms/step - loss:0.1528 - acc:0.9844 - val_loss:0.4119 - val_acc:0.9168
Epoch 403/1000
62s 125ms/step - loss:0.1566 - acc:0.9825 - val_loss:0.4014 - val_acc:0.9186
Epoch 404/1000
62s 125ms/step - loss:0.1523 - acc:0.9843 - val_loss:0.4243 - val_acc:0.9147
Epoch 405/1000
62s 124ms/step - loss:0.1520 - acc:0.9850 - val_loss:0.4182 - val_acc:0.9159
Epoch 406/1000
62s 124ms/step - loss:0.1521 - acc:0.9835 - val_loss:0.4021 - val_acc:0.9178
Epoch 407/1000
62s 125ms/step - loss:0.1566 - acc:0.9823 - val_loss:0.4143 - val_acc:0.9150
Epoch 408/1000
62s 124ms/step - loss:0.1520 - acc:0.9846 - val_loss:0.3987 - val_acc:0.9200
Epoch 409/1000
62s 125ms/step - loss:0.1538 - acc:0.9837 - val_loss:0.4051 - val_acc:0.9160
Epoch 410/1000
62s 124ms/step - loss:0.1541 - acc:0.9824 - val_loss:0.4159 - val_acc:0.9133
Epoch 411/1000
62s 124ms/step - loss:0.1540 - acc:0.9834 - val_loss:0.4171 - val_acc:0.9119
Epoch 412/1000
62s 123ms/step - loss:0.1523 - acc:0.9843 - val_loss:0.4103 - val_acc:0.9154
Epoch 413/1000
62s 124ms/step - loss:0.1502 - acc:0.9845 - val_loss:0.4164 - val_acc:0.9148
Epoch 414/1000
62s 125ms/step - loss:0.1585 - acc:0.9811 - val_loss:0.4115 - val_acc:0.9166
Epoch 415/1000
62s 125ms/step - loss:0.1508 - acc:0.9844 - val_loss:0.4210 - val_acc:0.9119
Epoch 416/1000
62s 125ms/step - loss:0.1531 - acc:0.9835 - val_loss:0.4125 - val_acc:0.9169
Epoch 417/1000
62s 125ms/step - loss:0.1502 - acc:0.9838 - val_loss:0.4174 - val_acc:0.9139
Epoch 418/1000
62s 125ms/step - loss:0.1477 - acc:0.9853 - val_loss:0.4091 - val_acc:0.9173
Epoch 419/1000
62s 125ms/step - loss:0.1529 - acc:0.9831 - val_loss:0.4144 - val_acc:0.9151
Epoch 420/1000
62s 124ms/step - loss:0.1546 - acc:0.9824 - val_loss:0.3990 - val_acc:0.9175
Epoch 421/1000
62s 125ms/step - loss:0.1502 - acc:0.9843 - val_loss:0.3900 - val_acc:0.9187
Epoch 422/1000
62s 125ms/step - loss:0.1500 - acc:0.9843 - val_loss:0.4025 - val_acc:0.9168
Epoch 423/1000
62s 125ms/step - loss:0.1551 - acc:0.9824 - val_loss:0.4141 - val_acc:0.9173
Epoch 424/1000
62s 125ms/step - loss:0.1507 - acc:0.9841 - val_loss:0.4181 - val_acc:0.9132
Epoch 425/1000
62s 125ms/step - loss:0.1517 - acc:0.9835 - val_loss:0.4149 - val_acc:0.9178
Epoch 426/1000
62s 125ms/step - loss:0.1533 - acc:0.9830 - val_loss:0.4080 - val_acc:0.9159
Epoch 427/1000
62s 125ms/step - loss:0.1500 - acc:0.9840 - val_loss:0.4227 - val_acc:0.9111
Epoch 428/1000
62s 125ms/step - loss:0.1515 - acc:0.9840 - val_loss:0.4033 - val_acc:0.9161
Epoch 429/1000
62s 125ms/step - loss:0.1487 - acc:0.9846 - val_loss:0.4152 - val_acc:0.9151
Epoch 430/1000
62s 124ms/step - loss:0.1504 - acc:0.9838 - val_loss:0.4093 - val_acc:0.9144
Epoch 431/1000
62s 125ms/step - loss:0.1479 - acc:0.9849 - val_loss:0.3920 - val_acc:0.9185
Epoch 432/1000
62s 125ms/step - loss:0.1486 - acc:0.9847 - val_loss:0.4119 - val_acc:0.9136
Epoch 433/1000
62s 124ms/step - loss:0.1518 - acc:0.9839 - val_loss:0.4071 - val_acc:0.9161
Epoch 434/1000
62s 125ms/step - loss:0.1526 - acc:0.9830 - val_loss:0.4031 - val_acc:0.9162
Epoch 435/1000
62s 125ms/step - loss:0.1519 - acc:0.9835 - val_loss:0.3861 - val_acc:0.9210
Epoch 436/1000
62s 125ms/step - loss:0.1487 - acc:0.9845 - val_loss:0.4099 - val_acc:0.9184
Epoch 437/1000
62s 124ms/step - loss:0.1531 - acc:0.9823 - val_loss:0.4020 - val_acc:0.9205
Epoch 438/1000
62s 125ms/step - loss:0.1519 - acc:0.9833 - val_loss:0.4032 - val_acc:0.9179
Epoch 439/1000
62s 125ms/step - loss:0.1523 - acc:0.9832 - val_loss:0.3972 - val_acc:0.9171
Epoch 440/1000
62s 124ms/step - loss:0.1512 - acc:0.9840 - val_loss:0.3920 - val_acc:0.9195
Epoch 441/1000
62s 125ms/step - loss:0.1503 - acc:0.9835 - val_loss:0.4231 - val_acc:0.9130
Epoch 442/1000
62s 125ms/step - loss:0.1464 - acc:0.9849 - val_loss:0.4230 - val_acc:0.9133
Epoch 443/1000
62s 125ms/step - loss:0.1509 - acc:0.9837 - val_loss:0.4154 - val_acc:0.9127
Epoch 444/1000
62s 124ms/step - loss:0.1488 - acc:0.9846 - val_loss:0.4284 - val_acc:0.9120
Epoch 445/1000
62s 124ms/step - loss:0.1468 - acc:0.9853 - val_loss:0.4246 - val_acc:0.9143
Epoch 446/1000
62s 125ms/step - loss:0.1499 - acc:0.9839 - val_loss:0.4191 - val_acc:0.9150
Epoch 447/1000
62s 124ms/step - loss:0.1494 - acc:0.9841 - val_loss:0.4146 - val_acc:0.9183
Epoch 448/1000
62s 125ms/step - loss:0.1527 - acc:0.9829 - val_loss:0.4059 - val_acc:0.9157
Epoch 449/1000
62s 125ms/step - loss:0.1491 - acc:0.9845 - val_loss:0.4126 - val_acc:0.9151
Epoch 450/1000
62s 125ms/step - loss:0.1494 - acc:0.9842 - val_loss:0.4150 - val_acc:0.9152
Epoch 451/1000
62s 124ms/step - loss:0.1521 - acc:0.9838 - val_loss:0.3997 - val_acc:0.9176
Epoch 452/1000
62s 124ms/step - loss:0.1518 - acc:0.9834 - val_loss:0.4082 - val_acc:0.9126
Epoch 453/1000
62s 124ms/step - loss:0.1514 - acc:0.9835 - val_loss:0.4053 - val_acc:0.9177
Epoch 454/1000
62s 124ms/step - loss:0.1506 - acc:0.9836 - val_loss:0.4148 - val_acc:0.9166
Epoch 455/1000
62s 125ms/step - loss:0.1493 - acc:0.9845 - val_loss:0.3997 - val_acc:0.9207
Epoch 456/1000
62s 124ms/step - loss:0.1486 - acc:0.9842 - val_loss:0.4132 - val_acc:0.9148
Epoch 457/1000
62s 125ms/step - loss:0.1479 - acc:0.9856 - val_loss:0.3984 - val_acc:0.9181
Epoch 458/1000
62s 125ms/step - loss:0.1515 - acc:0.9826 - val_loss:0.4026 - val_acc:0.9162
Epoch 459/1000
62s 125ms/step - loss:0.1515 - acc:0.9838 - val_loss:0.4098 - val_acc:0.9137
Epoch 460/1000
62s 124ms/step - loss:0.1513 - acc:0.9828 - val_loss:0.4047 - val_acc:0.9180
Epoch 461/1000
62s 125ms/step - loss:0.1466 - acc:0.9855 - val_loss:0.3965 - val_acc:0.9193
Epoch 462/1000
62s 124ms/step - loss:0.1518 - acc:0.9835 - val_loss:0.4046 - val_acc:0.9151
Epoch 463/1000
62s 124ms/step - loss:0.1506 - acc:0.9839 - val_loss:0.4084 - val_acc:0.9140
Epoch 464/1000
62s 125ms/step - loss:0.1503 - acc:0.9840 - val_loss:0.4086 - val_acc:0.9145
Epoch 465/1000
62s 125ms/step - loss:0.1523 - acc:0.9837 - val_loss:0.3983 - val_acc:0.9184
Epoch 466/1000
62s 125ms/step - loss:0.1493 - acc:0.9839 - val_loss:0.3957 - val_acc:0.9187
Epoch 467/1000
62s 124ms/step - loss:0.1492 - acc:0.9840 - val_loss:0.4008 - val_acc:0.9212
Epoch 468/1000
62s 124ms/step - loss:0.1474 - acc:0.9851 - val_loss:0.4152 - val_acc:0.9135
Epoch 469/1000
62s 124ms/step - loss:0.1466 - acc:0.9851 - val_loss:0.4033 - val_acc:0.9179
Epoch 470/1000
62s 124ms/step - loss:0.1471 - acc:0.9856 - val_loss:0.3983 - val_acc:0.9182
Epoch 471/1000
62s 124ms/step - loss:0.1473 - acc:0.9846 - val_loss:0.4316 - val_acc:0.9089
Epoch 472/1000
62s 124ms/step - loss:0.1539 - acc:0.9828 - val_loss:0.3924 - val_acc:0.9199
Epoch 473/1000
62s 125ms/step - loss:0.1483 - acc:0.9847 - val_loss:0.3929 - val_acc:0.9197
Epoch 474/1000
62s 124ms/step - loss:0.1465 - acc:0.9856 - val_loss:0.4017 - val_acc:0.9178
Epoch 475/1000
62s 124ms/step - loss:0.1541 - acc:0.9831 - val_loss:0.4030 - val_acc:0.9145
Epoch 476/1000
62s 124ms/step - loss:0.1472 - acc:0.9853 - val_loss:0.4143 - val_acc:0.9160
Epoch 477/1000
62s 124ms/step - loss:0.1498 - acc:0.9842 - val_loss:0.4277 - val_acc:0.9121
Epoch 478/1000
62s 124ms/step - loss:0.1473 - acc:0.9851 - val_loss:0.4091 - val_acc:0.9135
Epoch 479/1000
62s 124ms/step - loss:0.1513 - acc:0.9838 - val_loss:0.4148 - val_acc:0.9163
Epoch 480/1000
62s 124ms/step - loss:0.1487 - acc:0.9844 - val_loss:0.4073 - val_acc:0.9137
Epoch 481/1000
62s 124ms/step - loss:0.1446 - acc:0.9862 - val_loss:0.4056 - val_acc:0.9184
Epoch 482/1000
62s 125ms/step - loss:0.1469 - acc:0.9847 - val_loss:0.4189 - val_acc:0.9152
Epoch 483/1000
62s 125ms/step - loss:0.1447 - acc:0.9855 - val_loss:0.4097 - val_acc:0.9169
Epoch 484/1000
62s 125ms/step - loss:0.1490 - acc:0.9849 - val_loss:0.3920 - val_acc:0.9207
Epoch 485/1000
62s 125ms/step - loss:0.1466 - acc:0.9853 - val_loss:0.4131 - val_acc:0.9162
Epoch 486/1000
62s 124ms/step - loss:0.1461 - acc:0.9854 - val_loss:0.4065 - val_acc:0.9142
Epoch 487/1000
62s 125ms/step - loss:0.1479 - acc:0.9849 - val_loss:0.4088 - val_acc:0.9159
Epoch 488/1000
62s 124ms/step - loss:0.1481 - acc:0.9842 - val_loss:0.4170 - val_acc:0.9150
Epoch 489/1000
62s 125ms/step - loss:0.1480 - acc:0.9843 - val_loss:0.4196 - val_acc:0.9114
Epoch 490/1000
62s 124ms/step - loss:0.1471 - acc:0.9854 - val_loss:0.4182 - val_acc:0.9145
Epoch 491/1000
62s 124ms/step - loss:0.1457 - acc:0.9859 - val_loss:0.4128 - val_acc:0.9173
Epoch 492/1000
62s 124ms/step - loss:0.1491 - acc:0.9833 - val_loss:0.4115 - val_acc:0.9145
Epoch 493/1000
62s 125ms/step - loss:0.1483 - acc:0.9845 - val_loss:0.4246 - val_acc:0.9138
Epoch 494/1000
62s 124ms/step - loss:0.1510 - acc:0.9837 - val_loss:0.4197 - val_acc:0.9140
Epoch 495/1000
62s 125ms/step - loss:0.1441 - acc:0.9863 - val_loss:0.4147 - val_acc:0.9143
Epoch 496/1000
62s 125ms/step - loss:0.1445 - acc:0.9862 - val_loss:0.4187 - val_acc:0.9116
Epoch 497/1000
62s 124ms/step - loss:0.1469 - acc:0.9854 - val_loss:0.4090 - val_acc:0.9181
Epoch 498/1000
62s 125ms/step - loss:0.1505 - acc:0.9837 - val_loss:0.3973 - val_acc:0.9184
Epoch 499/1000
62s 125ms/step - loss:0.1479 - acc:0.9847 - val_loss:0.4087 - val_acc:0.9166
Epoch 500/1000
62s 124ms/step - loss:0.1477 - acc:0.9848 - val_loss:0.4203 - val_acc:0.9136
Epoch 501/1000
62s 124ms/step - loss:0.1492 - acc:0.9845 - val_loss:0.4222 - val_acc:0.9131
Epoch 502/1000
62s 125ms/step - loss:0.1470 - acc:0.9850 - val_loss:0.4172 - val_acc:0.9138
Epoch 503/1000
62s 124ms/step - loss:0.1497 - acc:0.9839 - val_loss:0.4288 - val_acc:0.9133
Epoch 504/1000
62s 125ms/step - loss:0.1488 - acc:0.9844 - val_loss:0.4096 - val_acc:0.9167
Epoch 505/1000
62s 125ms/step - loss:0.1467 - acc:0.9854 - val_loss:0.4186 - val_acc:0.9139
Epoch 506/1000
62s 124ms/step - loss:0.1456 - acc:0.9856 - val_loss:0.4107 - val_acc:0.9167
Epoch 507/1000
62s 125ms/step - loss:0.1488 - acc:0.9847 - val_loss:0.4200 - val_acc:0.9152
Epoch 508/1000
62s 124ms/step - loss:0.1480 - acc:0.9842 - val_loss:0.4129 - val_acc:0.9133
Epoch 509/1000
62s 125ms/step - loss:0.1497 - acc:0.9838 - val_loss:0.4048 - val_acc:0.9136
Epoch 510/1000
62s 124ms/step - loss:0.1509 - acc:0.9840 - val_loss:0.3958 - val_acc:0.9167
Epoch 511/1000
62s 125ms/step - loss:0.1478 - acc:0.9850 - val_loss:0.4136 - val_acc:0.9157
Epoch 512/1000
62s 125ms/step - loss:0.1435 - acc:0.9863 - val_loss:0.4051 - val_acc:0.9185
Epoch 513/1000
62s 125ms/step - loss:0.1458 - acc:0.9856 - val_loss:0.4088 - val_acc:0.9154
Epoch 514/1000
62s 125ms/step - loss:0.1483 - acc:0.9851 - val_loss:0.4187 - val_acc:0.9142
Epoch 515/1000
62s 125ms/step - loss:0.1463 - acc:0.9853 - val_loss:0.4347 - val_acc:0.9096
Epoch 516/1000
62s 125ms/step - loss:0.1467 - acc:0.9856 - val_loss:0.4235 - val_acc:0.9148
Epoch 517/1000
62s 123ms/step - loss:0.1452 - acc:0.9854 - val_loss:0.4250 - val_acc:0.9135
Epoch 518/1000
62s 123ms/step - loss:0.1499 - acc:0.9844 - val_loss:0.4048 - val_acc:0.9174
Epoch 519/1000
62s 123ms/step - loss:0.1482 - acc:0.9843 - val_loss:0.4159 - val_acc:0.9140
Epoch 520/1000
62s 123ms/step - loss:0.1483 - acc:0.9841 - val_loss:0.4160 - val_acc:0.9153
Epoch 521/1000
62s 123ms/step - loss:0.1464 - acc:0.9858 - val_loss:0.4009 - val_acc:0.9165
Epoch 522/1000
62s 123ms/step - loss:0.1454 - acc:0.9852 - val_loss:0.4126 - val_acc:0.9164
Epoch 523/1000
62s 123ms/step - loss:0.1435 - acc:0.9866 - val_loss:0.4130 - val_acc:0.9201
Epoch 524/1000
62s 124ms/step - loss:0.1478 - acc:0.9848 - val_loss:0.4095 - val_acc:0.9172
Epoch 525/1000
62s 125ms/step - loss:0.1511 - acc:0.9837 - val_loss:0.4036 - val_acc:0.9179
Epoch 526/1000
62s 125ms/step - loss:0.1491 - acc:0.9842 - val_loss:0.4036 - val_acc:0.9173
Epoch 527/1000
62s 125ms/step - loss:0.1433 - acc:0.9865 - val_loss:0.4225 - val_acc:0.9123
Epoch 528/1000
62s 125ms/step - loss:0.1453 - acc:0.9854 - val_loss:0.4156 - val_acc:0.9156
Epoch 529/1000
62s 125ms/step - loss:0.1462 - acc:0.9856 - val_loss:0.4154 - val_acc:0.9143
Epoch 530/1000
62s 125ms/step - loss:0.1500 - acc:0.9840 - val_loss:0.4176 - val_acc:0.9120
Epoch 531/1000
62s 125ms/step - loss:0.1489 - acc:0.9845 - val_loss:0.4087 - val_acc:0.9158
Epoch 532/1000
62s 125ms/step - loss:0.1480 - acc:0.9849 - val_loss:0.4042 - val_acc:0.9154
Epoch 533/1000
62s 124ms/step - loss:0.1483 - acc:0.9850 - val_loss:0.4191 - val_acc:0.9155
Epoch 534/1000
62s 125ms/step - loss:0.1432 - acc:0.9865 - val_loss:0.4054 - val_acc:0.9173
Epoch 535/1000
62s 125ms/step - loss:0.1471 - acc:0.9854 - val_loss:0.4200 - val_acc:0.9133
Epoch 536/1000
62s 125ms/step - loss:0.1518 - acc:0.9835 - val_loss:0.4052 - val_acc:0.9160
Epoch 537/1000
62s 125ms/step - loss:0.1442 - acc:0.9860 - val_loss:0.4331 - val_acc:0.9126
Epoch 538/1000
62s 124ms/step - loss:0.1466 - acc:0.9848 - val_loss:0.4207 - val_acc:0.9173
Epoch 539/1000
62s 125ms/step - loss:0.1469 - acc:0.9851 - val_loss:0.4202 - val_acc:0.9109
Epoch 540/1000
62s 124ms/step - loss:0.1496 - acc:0.9838 - val_loss:0.4297 - val_acc:0.9126
Epoch 541/1000
62s 124ms/step - loss:0.1453 - acc:0.9863 - val_loss:0.4219 - val_acc:0.9139
Epoch 542/1000
62s 125ms/step - loss:0.1469 - acc:0.9854 - val_loss:0.4203 - val_acc:0.9137
Epoch 543/1000
62s 124ms/step - loss:0.1471 - acc:0.9852 - val_loss:0.4216 - val_acc:0.9152
Epoch 544/1000
62s 125ms/step - loss:0.1514 - acc:0.9840 - val_loss:0.4178 - val_acc:0.9138
Epoch 545/1000
62s 125ms/step - loss:0.1459 - acc:0.9853 - val_loss:0.4266 - val_acc:0.9126
Epoch 546/1000
62s 125ms/step - loss:0.1480 - acc:0.9845 - val_loss:0.4147 - val_acc:0.9176
Epoch 547/1000
62s 125ms/step - loss:0.1464 - acc:0.9856 - val_loss:0.4306 - val_acc:0.9130
Epoch 548/1000
62s 124ms/step - loss:0.1490 - acc:0.9840 - val_loss:0.4259 - val_acc:0.9143
Epoch 549/1000
62s 124ms/step - loss:0.1485 - acc:0.9847 - val_loss:0.4349 - val_acc:0.9109
Epoch 550/1000
62s 124ms/step - loss:0.1487 - acc:0.9844 - val_loss:0.3984 - val_acc:0.9189
Epoch 551/1000
62s 125ms/step - loss:0.1489 - acc:0.9850 - val_loss:0.4091 - val_acc:0.9185
Epoch 552/1000
62s 124ms/step - loss:0.1486 - acc:0.9845 - val_loss:0.4143 - val_acc:0.9138
Epoch 553/1000
62s 125ms/step - loss:0.1453 - acc:0.9859 - val_loss:0.4008 - val_acc:0.9154
Epoch 554/1000
62s 124ms/step - loss:0.1445 - acc:0.9864 - val_loss:0.4308 - val_acc:0.9134
Epoch 555/1000
62s 125ms/step - loss:0.1484 - acc:0.9844 - val_loss:0.4206 - val_acc:0.9143
Epoch 556/1000
62s 124ms/step - loss:0.1455 - acc:0.9856 - val_loss:0.3994 - val_acc:0.9197
Epoch 557/1000
62s 124ms/step - loss:0.1446 - acc:0.9860 - val_loss:0.3963 - val_acc:0.9194
Epoch 558/1000
62s 124ms/step - loss:0.1460 - acc:0.9852 - val_loss:0.4125 - val_acc:0.9140
Epoch 559/1000
62s 125ms/step - loss:0.1446 - acc:0.9859 - val_loss:0.4092 - val_acc:0.9165
Epoch 560/1000
62s 124ms/step - loss:0.1442 - acc:0.9865 - val_loss:0.3911 - val_acc:0.9212
Epoch 561/1000
62s 124ms/step - loss:0.1459 - acc:0.9852 - val_loss:0.3984 - val_acc:0.9185
Epoch 562/1000
62s 124ms/step - loss:0.1473 - acc:0.9851 - val_loss:0.4080 - val_acc:0.9196
Epoch 563/1000
62s 124ms/step - loss:0.1465 - acc:0.9860 - val_loss:0.4058 - val_acc:0.9166
Epoch 564/1000
62s 124ms/step - loss:0.1423 - acc:0.9870 - val_loss:0.4046 - val_acc:0.9180
Epoch 565/1000
62s 124ms/step - loss:0.1486 - acc:0.9851 - val_loss:0.4022 - val_acc:0.9184
Epoch 566/1000
62s 124ms/step - loss:0.1478 - acc:0.9853 - val_loss:0.3896 - val_acc:0.9224
Epoch 567/1000
62s 124ms/step - loss:0.1470 - acc:0.9850 - val_loss:0.4141 - val_acc:0.9151
Epoch 568/1000
62s 124ms/step - loss:0.1438 - acc:0.9862 - val_loss:0.4139 - val_acc:0.9197
Epoch 569/1000
62s 125ms/step - loss:0.1470 - acc:0.9851 - val_loss:0.4143 - val_acc:0.9156
Epoch 570/1000
62s 125ms/step - loss:0.1484 - acc:0.9845 - val_loss:0.4151 - val_acc:0.9148
Epoch 571/1000
62s 125ms/step - loss:0.1479 - acc:0.9849 - val_loss:0.4206 - val_acc:0.9136
Epoch 572/1000
62s 124ms/step - loss:0.1458 - acc:0.9855 - val_loss:0.4172 - val_acc:0.9147
Epoch 573/1000
62s 124ms/step - loss:0.1450 - acc:0.9860 - val_loss:0.4267 - val_acc:0.9156
Epoch 574/1000
62s 124ms/step - loss:0.1514 - acc:0.9834 - val_loss:0.4357 - val_acc:0.9127
Epoch 575/1000
62s 124ms/step - loss:0.1475 - acc:0.9851 - val_loss:0.4212 - val_acc:0.9142
Epoch 576/1000
62s 125ms/step - loss:0.1464 - acc:0.9858 - val_loss:0.4141 - val_acc:0.9162
Epoch 577/1000
62s 125ms/step - loss:0.1478 - acc:0.9846 - val_loss:0.4065 - val_acc:0.9151
Epoch 578/1000
62s 125ms/step - loss:0.1418 - acc:0.9868 - val_loss:0.4090 - val_acc:0.9145
Epoch 579/1000
62s 125ms/step - loss:0.1456 - acc:0.9852 - val_loss:0.4350 - val_acc:0.9101
Epoch 580/1000
62s 125ms/step - loss:0.1422 - acc:0.9870 - val_loss:0.4116 - val_acc:0.9185
Epoch 581/1000
62s 125ms/step - loss:0.1449 - acc:0.9858 - val_loss:0.4245 - val_acc:0.9127
Epoch 582/1000
62s 125ms/step - loss:0.1429 - acc:0.9863 - val_loss:0.4157 - val_acc:0.9163
Epoch 583/1000
62s 125ms/step - loss:0.1473 - acc:0.9851 - val_loss:0.4094 - val_acc:0.9165
Epoch 584/1000
62s 125ms/step - loss:0.1500 - acc:0.9845 - val_loss:0.4269 - val_acc:0.9115
Epoch 585/1000
62s 125ms/step - loss:0.1450 - acc:0.9860 - val_loss:0.4189 - val_acc:0.9165
Epoch 586/1000
62s 125ms/step - loss:0.1450 - acc:0.9859 - val_loss:0.4153 - val_acc:0.9153
Epoch 587/1000
62s 125ms/step - loss:0.1453 - acc:0.9859 - val_loss:0.4166 - val_acc:0.9155
Epoch 588/1000
62s 125ms/step - loss:0.1409 - acc:0.9875 - val_loss:0.4088 - val_acc:0.9193
Epoch 589/1000
62s 125ms/step - loss:0.1455 - acc:0.9854 - val_loss:0.4220 - val_acc:0.9149
Epoch 590/1000
62s 125ms/step - loss:0.1466 - acc:0.9848 - val_loss:0.4264 - val_acc:0.9136
Epoch 591/1000
62s 125ms/step - loss:0.1424 - acc:0.9868 - val_loss:0.4212 - val_acc:0.9178
Epoch 592/1000
62s 125ms/step - loss:0.1441 - acc:0.9862 - val_loss:0.4271 - val_acc:0.9127
Epoch 593/1000
62s 124ms/step - loss:0.1469 - acc:0.9852 - val_loss:0.4247 - val_acc:0.9170
Epoch 594/1000
62s 125ms/step - loss:0.1468 - acc:0.9845 - val_loss:0.4080 - val_acc:0.9192
Epoch 595/1000
62s 125ms/step - loss:0.1437 - acc:0.9857 - val_loss:0.4111 - val_acc:0.9174
Epoch 596/1000
62s 125ms/step - loss:0.1451 - acc:0.9852 - val_loss:0.4290 - val_acc:0.9124
Epoch 597/1000
62s 124ms/step - loss:0.1465 - acc:0.9856 - val_loss:0.4203 - val_acc:0.9167
Epoch 598/1000
62s 125ms/step - loss:0.1451 - acc:0.9855 - val_loss:0.4203 - val_acc:0.9136
Epoch 599/1000
62s 125ms/step - loss:0.1460 - acc:0.9857 - val_loss:0.4248 - val_acc:0.9161
Epoch 600/1000
62s 124ms/step - loss:0.1466 - acc:0.9856 - val_loss:0.4286 - val_acc:0.9143
Epoch 601/1000
lr changed to 0.0009999999776482583
62s 125ms/step - loss:0.1318 - acc:0.9907 - val_loss:0.3912 - val_acc:0.9255
Epoch 602/1000
62s 124ms/step - loss:0.1212 - acc:0.9945 - val_loss:0.3822 - val_acc:0.9269
Epoch 603/1000
62s 125ms/step - loss:0.1176 - acc:0.9960 - val_loss:0.3786 - val_acc:0.9289
Epoch 604/1000
62s 125ms/step - loss:0.1168 - acc:0.9959 - val_loss:0.3779 - val_acc:0.9286
Epoch 605/1000
62s 125ms/step - loss:0.1146 - acc:0.9965 - val_loss:0.3782 - val_acc:0.9295
Epoch 606/1000
62s 125ms/step - loss:0.1130 - acc:0.9973 - val_loss:0.3791 - val_acc:0.9294
Epoch 607/1000
62s 125ms/step - loss:0.1127 - acc:0.9974 - val_loss:0.3780 - val_acc:0.9301
Epoch 608/1000
62s 125ms/step - loss:0.1118 - acc:0.9976 - val_loss:0.3777 - val_acc:0.9300
Epoch 609/1000
62s 125ms/step - loss:0.1112 - acc:0.9975 - val_loss:0.3760 - val_acc:0.9298
Epoch 610/1000
62s 125ms/step - loss:0.1102 - acc:0.9978 - val_loss:0.3769 - val_acc:0.9301
Epoch 611/1000
62s 125ms/step - loss:0.1106 - acc:0.9977 - val_loss:0.3775 - val_acc:0.9309
Epoch 612/1000
62s 125ms/step - loss:0.1092 - acc:0.9979 - val_loss:0.3781 - val_acc:0.9304
Epoch 613/1000
62s 124ms/step - loss:0.1096 - acc:0.9979 - val_loss:0.3768 - val_acc:0.9297
Epoch 614/1000
62s 125ms/step - loss:0.1092 - acc:0.9979 - val_loss:0.3770 - val_acc:0.9302
Epoch 615/1000
62s 125ms/step - loss:0.1084 - acc:0.9982 - val_loss:0.3779 - val_acc:0.9309
Epoch 616/1000
62s 125ms/step - loss:0.1077 - acc:0.9983 - val_loss:0.3804 - val_acc:0.9299
Epoch 617/1000
62s 125ms/step - loss:0.1073 - acc:0.9983 - val_loss:0.3799 - val_acc:0.9302
Epoch 618/1000
62s 125ms/step - loss:0.1069 - acc:0.9985 - val_loss:0.3816 - val_acc:0.9305
Epoch 619/1000
62s 125ms/step - loss:0.1063 - acc:0.9985 - val_loss:0.3814 - val_acc:0.9303
Epoch 620/1000
62s 125ms/step - loss:0.1066 - acc:0.9983 - val_loss:0.3817 - val_acc:0.9301
Epoch 621/1000
62s 125ms/step - loss:0.1060 - acc:0.9987 - val_loss:0.3811 - val_acc:0.9303
Epoch 622/1000
62s 124ms/step - loss:0.1058 - acc:0.9985 - val_loss:0.3815 - val_acc:0.9298
Epoch 623/1000
62s 124ms/step - loss:0.1051 - acc:0.9986 - val_loss:0.3810 - val_acc:0.9302
Epoch 624/1000
62s 124ms/step - loss:0.1050 - acc:0.9986 - val_loss:0.3825 - val_acc:0.9303
Epoch 625/1000
62s 124ms/step - loss:0.1048 - acc:0.9987 - val_loss:0.3845 - val_acc:0.9294
Epoch 626/1000
62s 125ms/step - loss:0.1040 - acc:0.9988 - val_loss:0.3842 - val_acc:0.9296
Epoch 627/1000
62s 125ms/step - loss:0.1037 - acc:0.9988 - val_loss:0.3833 - val_acc:0.9304
Epoch 628/1000
62s 124ms/step - loss:0.1048 - acc:0.9982 - val_loss:0.3844 - val_acc:0.9303
Epoch 629/1000
62s 124ms/step - loss:0.1045 - acc:0.9984 - val_loss:0.3829 - val_acc:0.9289
Epoch 630/1000
62s 125ms/step - loss:0.1032 - acc:0.9988 - val_loss:0.3823 - val_acc:0.9302
Epoch 631/1000
62s 125ms/step - loss:0.1034 - acc:0.9987 - val_loss:0.3809 - val_acc:0.9314
Epoch 632/1000
62s 125ms/step - loss:0.1029 - acc:0.9987 - val_loss:0.3812 - val_acc:0.9309
Epoch 633/1000
62s 125ms/step - loss:0.1023 - acc:0.9990 - val_loss:0.3815 - val_acc:0.9303
Epoch 634/1000
62s 124ms/step - loss:0.1025 - acc:0.9987 - val_loss:0.3854 - val_acc:0.9303
Epoch 635/1000
62s 124ms/step - loss:0.1022 - acc:0.9988 - val_loss:0.3849 - val_acc:0.9305
Epoch 636/1000
62s 124ms/step - loss:0.1015 - acc:0.9989 - val_loss:0.3840 - val_acc:0.9312
Epoch 637/1000
62s 124ms/step - loss:0.1012 - acc:0.9991 - val_loss:0.3831 - val_acc:0.9308
Epoch 638/1000
62s 125ms/step - loss:0.1012 - acc:0.9990 - val_loss:0.3830 - val_acc:0.9315
Epoch 639/1000
62s 124ms/step - loss:0.1012 - acc:0.9989 - val_loss:0.3826 - val_acc:0.9309
Epoch 640/1000
62s 125ms/step - loss:0.1006 - acc:0.9990 - val_loss:0.3838 - val_acc:0.9309
Epoch 641/1000
62s 125ms/step - loss:0.1004 - acc:0.9989 - val_loss:0.3843 - val_acc:0.9315
Epoch 642/1000
62s 125ms/step - loss:0.0998 - acc:0.9992 - val_loss:0.3852 - val_acc:0.9311
Epoch 643/1000
62s 124ms/step - loss:0.1001 - acc:0.9991 - val_loss:0.3846 - val_acc:0.9309
Epoch 644/1000
62s 124ms/step - loss:0.1000 - acc:0.9990 - val_loss:0.3847 - val_acc:0.9304
Epoch 645/1000
62s 124ms/step - loss:0.0993 - acc:0.9992 - val_loss:0.3843 - val_acc:0.9314
Epoch 646/1000
62s 125ms/step - loss:0.0993 - acc:0.9991 - val_loss:0.3823 - val_acc:0.9313
Epoch 647/1000
62s 125ms/step - loss:0.0989 - acc:0.9992 - val_loss:0.3840 - val_acc:0.9305
Epoch 648/1000
62s 125ms/step - loss:0.0991 - acc:0.9990 - val_loss:0.3843 - val_acc:0.9313
Epoch 649/1000
62s 125ms/step - loss:0.0984 - acc:0.9992 - val_loss:0.3854 - val_acc:0.9315
Epoch 650/1000
62s 125ms/step - loss:0.0982 - acc:0.9991 - val_loss:0.3853 - val_acc:0.9322
Epoch 651/1000
62s 125ms/step - loss:0.0981 - acc:0.9993 - val_loss:0.3860 - val_acc:0.9312
Epoch 652/1000
62s 124ms/step - loss:0.0982 - acc:0.9990 - val_loss:0.3880 - val_acc:0.9307
Epoch 653/1000
62s 125ms/step - loss:0.0980 - acc:0.9990 - val_loss:0.3868 - val_acc:0.9314
Epoch 654/1000
62s 125ms/step - loss:0.0973 - acc:0.9993 - val_loss:0.3846 - val_acc:0.9319
Epoch 655/1000
62s 125ms/step - loss:0.0971 - acc:0.9994 - val_loss:0.3826 - val_acc:0.9309
Epoch 656/1000
62s 125ms/step - loss:0.0970 - acc:0.9990 - val_loss:0.3831 - val_acc:0.9319
Epoch 657/1000
62s 125ms/step - loss:0.0970 - acc:0.9991 - val_loss:0.3833 - val_acc:0.9310
Epoch 658/1000
62s 124ms/step - loss:0.0966 - acc:0.9992 - val_loss:0.3810 - val_acc:0.9314
Epoch 659/1000
62s 125ms/step - loss:0.0967 - acc:0.9990 - val_loss:0.3795 - val_acc:0.9330
Epoch 660/1000
62s 125ms/step - loss:0.0962 - acc:0.9992 - val_loss:0.3816 - val_acc:0.9329
Epoch 661/1000
62s 124ms/step - loss:0.0964 - acc:0.9991 - val_loss:0.3839 - val_acc:0.9321
Epoch 662/1000
62s 125ms/step - loss:0.0956 - acc:0.9992 - val_loss:0.3841 - val_acc:0.9321
Epoch 663/1000
62s 125ms/step - loss:0.0953 - acc:0.9993 - val_loss:0.3820 - val_acc:0.9320
Epoch 664/1000
62s 125ms/step - loss:0.0949 - acc:0.9994 - val_loss:0.3808 - val_acc:0.9326
Epoch 665/1000
63s 125ms/step - loss:0.0957 - acc:0.9990 - val_loss:0.3808 - val_acc:0.9332
Epoch 666/1000
62s 125ms/step - loss:0.0955 - acc:0.9989 - val_loss:0.3811 - val_acc:0.9320
Epoch 667/1000
62s 125ms/step - loss:0.0948 - acc:0.9993 - val_loss:0.3811 - val_acc:0.9330
Epoch 668/1000
62s 124ms/step - loss:0.0949 - acc:0.9991 - val_loss:0.3822 - val_acc:0.9320
Epoch 669/1000
62s 125ms/step - loss:0.0947 - acc:0.9992 - val_loss:0.3843 - val_acc:0.9321
Epoch 670/1000
62s 124ms/step - loss:0.0943 - acc:0.9992 - val_loss:0.3810 - val_acc:0.9314
Epoch 671/1000
62s 125ms/step - loss:0.0941 - acc:0.9991 - val_loss:0.3823 - val_acc:0.9324
Epoch 672/1000
62s 125ms/step - loss:0.0937 - acc:0.9993 - val_loss:0.3826 - val_acc:0.9328
Epoch 673/1000
62s 125ms/step - loss:0.0936 - acc:0.9992 - val_loss:0.3816 - val_acc:0.9330
Epoch 674/1000
62s 125ms/step - loss:0.0935 - acc:0.9991 - val_loss:0.3806 - val_acc:0.9328
Epoch 675/1000
62s 125ms/step - loss:0.0931 - acc:0.9992 - val_loss:0.3828 - val_acc:0.9331
Epoch 676/1000
62s 124ms/step - loss:0.0935 - acc:0.9989 - val_loss:0.3859 - val_acc:0.9327
Epoch 677/1000
62s 124ms/step - loss:0.0927 - acc:0.9993 - val_loss:0.3836 - val_acc:0.9329
Epoch 678/1000
62s 125ms/step - loss:0.0925 - acc:0.9994 - val_loss:0.3829 - val_acc:0.9325
Epoch 679/1000
62s 125ms/step - loss:0.0924 - acc:0.9993 - val_loss:0.3823 - val_acc:0.9341
Epoch 680/1000
62s 125ms/step - loss:0.0920 - acc:0.9993 - val_loss:0.3843 - val_acc:0.9326
Epoch 681/1000
62s 125ms/step - loss:0.0922 - acc:0.9993 - val_loss:0.3855 - val_acc:0.9315
Epoch 682/1000
62s 125ms/step - loss:0.0918 - acc:0.9993 - val_loss:0.3850 - val_acc:0.9314
Epoch 683/1000
62s 125ms/step - loss:0.0915 - acc:0.9994 - val_loss:0.3850 - val_acc:0.9312
Epoch 684/1000
62s 125ms/step - loss:0.0911 - acc:0.9995 - val_loss:0.3848 - val_acc:0.9313
Epoch 685/1000
62s 125ms/step - loss:0.0908 - acc:0.9996 - val_loss:0.3854 - val_acc:0.9322
Epoch 686/1000
62s 125ms/step - loss:0.0912 - acc:0.9992 - val_loss:0.3836 - val_acc:0.9325
Epoch 687/1000
62s 125ms/step - loss:0.0909 - acc:0.9993 - val_loss:0.3848 - val_acc:0.9320
Epoch 688/1000
63s 125ms/step - loss:0.0904 - acc:0.9995 - val_loss:0.3857 - val_acc:0.9316
Epoch 689/1000
62s 125ms/step - loss:0.0904 - acc:0.9994 - val_loss:0.3858 - val_acc:0.9318
Epoch 690/1000
62s 125ms/step - loss:0.0901 - acc:0.9995 - val_loss:0.3829 - val_acc:0.9320
Epoch 691/1000
62s 124ms/step - loss:0.0906 - acc:0.9993 - val_loss:0.3816 - val_acc:0.9324
Epoch 692/1000
62s 124ms/step - loss:0.0900 - acc:0.9992 - val_loss:0.3827 - val_acc:0.9308
Epoch 693/1000
62s 124ms/step - loss:0.0898 - acc:0.9994 - val_loss:0.3814 - val_acc:0.9324
Epoch 694/1000
62s 124ms/step - loss:0.0898 - acc:0.9994 - val_loss:0.3820 - val_acc:0.9329
Epoch 695/1000
63s 125ms/step - loss:0.0892 - acc:0.9995 - val_loss:0.3823 - val_acc:0.9335
Epoch 696/1000
62s 125ms/step - loss:0.0893 - acc:0.9992 - val_loss:0.3825 - val_acc:0.9326
Epoch 697/1000
62s 123ms/step - loss:0.0891 - acc:0.9994 - val_loss:0.3827 - val_acc:0.9324
Epoch 698/1000
62s 123ms/step - loss:0.0892 - acc:0.9992 - val_loss:0.3812 - val_acc:0.9331
Epoch 699/1000
62s 124ms/step - loss:0.0888 - acc:0.9992 - val_loss:0.3822 - val_acc:0.9310
Epoch 700/1000
62s 125ms/step - loss:0.0883 - acc:0.9995 - val_loss:0.3825 - val_acc:0.9317
Epoch 755/1000
62s 124ms/step - loss:0.0792 - acc:0.9996 - val_loss:0.3819 - val_acc:0.9316
Epoch 756/1000
62s 123ms/step - loss:0.0791 - acc:0.9996 - val_loss:0.3808 - val_acc:0.9312
Epoch 757/1000
62s 123ms/step - loss:0.0787 - acc:0.9996 - val_loss:0.3823 - val_acc:0.9318
Epoch 758/1000
62s 124ms/step - loss:0.0788 - acc:0.9995 - val_loss:0.3813 - val_acc:0.9322
Epoch 759/1000
62s 124ms/step - loss:0.0783 - acc:0.9997 - val_loss:0.3816 - val_acc:0.9330
Epoch 760/1000
62s 124ms/step - loss:0.0782 - acc:0.9997 - val_loss:0.3780 - val_acc:0.9331
Epoch 761/1000
62s 124ms/step - loss:0.0783 - acc:0.9995 - val_loss:0.3778 - val_acc:0.9325
Epoch 762/1000
62s 124ms/step - loss:0.0780 - acc:0.9996 - val_loss:0.3769 - val_acc:0.9319
Epoch 763/1000
62s 124ms/step - loss:0.0780 - acc:0.9996 - val_loss:0.3781 - val_acc:0.9324
Epoch 764/1000
62s 124ms/step - loss:0.0779 - acc:0.9996 - val_loss:0.3798 - val_acc:0.9331
Epoch 765/1000
62s 123ms/step - loss:0.0778 - acc:0.9995 - val_loss:0.3799 - val_acc:0.9323
Epoch 766/1000
62s 124ms/step - loss:0.0777 - acc:0.9996 - val_loss:0.3809 - val_acc:0.9311
Epoch 767/1000
62s 124ms/step - loss:0.0772 - acc:0.9996 - val_loss:0.3797 - val_acc:0.9322
Epoch 768/1000
62s 124ms/step - loss:0.0772 - acc:0.9996 - val_loss:0.3814 - val_acc:0.9323
Epoch 769/1000
62s 124ms/step - loss:0.0770 - acc:0.9996 - val_loss:0.3811 - val_acc:0.9330
Epoch 770/1000
62s 124ms/step - loss:0.0763 - acc:0.9999 - val_loss:0.3816 - val_acc:0.9331
Epoch 771/1000
62s 124ms/step - loss:0.0764 - acc:0.9997 - val_loss:0.3830 - val_acc:0.9317
Epoch 772/1000
62s 124ms/step - loss:0.0767 - acc:0.9995 - val_loss:0.3810 - val_acc:0.9320
Epoch 773/1000
62s 123ms/step - loss:0.0768 - acc:0.9995 - val_loss:0.3831 - val_acc:0.9325
Epoch 774/1000
62s 123ms/step - loss:0.0764 - acc:0.9995 - val_loss:0.3824 - val_acc:0.9334
Epoch 775/1000
62s 124ms/step - loss:0.0761 - acc:0.9997 - val_loss:0.3816 - val_acc:0.9329
Epoch 776/1000
62s 124ms/step - loss:0.0758 - acc:0.9997 - val_loss:0.3815 - val_acc:0.9340
Epoch 777/1000
62s 124ms/step - loss:0.0756 - acc:0.9998 - val_loss:0.3810 - val_acc:0.9333
Epoch 778/1000
62s 124ms/step - loss:0.0756 - acc:0.9996 - val_loss:0.3838 - val_acc:0.9322
Epoch 779/1000
62s 124ms/step - loss:0.0755 - acc:0.9996 - val_loss:0.3831 - val_acc:0.9329
Epoch 780/1000
62s 124ms/step - loss:0.0756 - acc:0.9994 - val_loss:0.3833 - val_acc:0.9313
Epoch 781/1000
62s 124ms/step - loss:0.0756 - acc:0.9995 - val_loss:0.3831 - val_acc:0.9325
Epoch 782/1000
62s 124ms/step - loss:0.0751 - acc:0.9996 - val_loss:0.3820 - val_acc:0.9340
Epoch 783/1000
62s 123ms/step - loss:0.0749 - acc:0.9996 - val_loss:0.3818 - val_acc:0.9328
Epoch 784/1000
62s 124ms/step - loss:0.0749 - acc:0.9995 - val_loss:0.3788 - val_acc:0.9331
Epoch 785/1000
62s 124ms/step - loss:0.0747 - acc:0.9995 - val_loss:0.3800 - val_acc:0.9335
Epoch 786/1000
62s 124ms/step - loss:0.0745 - acc:0.9996 - val_loss:0.3790 - val_acc:0.9333
Epoch 787/1000
62s 123ms/step - loss:0.0745 - acc:0.9995 - val_loss:0.3798 - val_acc:0.9348
Epoch 788/1000
62s 123ms/step - loss:0.0746 - acc:0.9995 - val_loss:0.3808 - val_acc:0.9340
Epoch 789/1000
62s 124ms/step - loss:0.0741 - acc:0.9996 - val_loss:0.3784 - val_acc:0.9347
Epoch 790/1000
62s 124ms/step - loss:0.0741 - acc:0.9996 - val_loss:0.3764 - val_acc:0.9334
Epoch 791/1000
62s 124ms/step - loss:0.0739 - acc:0.9996 - val_loss:0.3747 - val_acc:0.9340
Epoch 792/1000
62s 124ms/step - loss:0.0736 - acc:0.9996 - val_loss:0.3762 - val_acc:0.9326
Epoch 793/1000
62s 124ms/step - loss:0.0737 - acc:0.9996 - val_loss:0.3747 - val_acc:0.9341
Epoch 794/1000
62s 124ms/step - loss:0.0736 - acc:0.9996 - val_loss:0.3778 - val_acc:0.9322
Epoch 795/1000
62s 123ms/step - loss:0.0732 - acc:0.9997 - val_loss:0.3804 - val_acc:0.9324
Epoch 796/1000
62s 123ms/step - loss:0.0732 - acc:0.9996 - val_loss:0.3771 - val_acc:0.9336
Epoch 797/1000
62s 124ms/step - loss:0.0733 - acc:0.9994 - val_loss:0.3761 - val_acc:0.9325
Epoch 798/1000
62s 123ms/step - loss:0.0729 - acc:0.9996 - val_loss:0.3770 - val_acc:0.9323
Epoch 799/1000
62s 124ms/step - loss:0.0727 - acc:0.9996 - val_loss:0.3768 - val_acc:0.9324
Epoch 800/1000
62s 124ms/step - loss:0.0725 - acc:0.9997 - val_loss:0.3784 - val_acc:0.9329
Epoch 801/1000
62s 123ms/step - loss:0.0723 - acc:0.9997 - val_loss:0.3741 - val_acc:0.9342
Epoch 802/1000
62s 124ms/step - loss:0.0723 - acc:0.9996 - val_loss:0.3772 - val_acc:0.9332
Epoch 803/1000
62s 123ms/step - loss:0.0721 - acc:0.9996 - val_loss:0.3778 - val_acc:0.9329
Epoch 804/1000
62s 123ms/step - loss:0.0722 - acc:0.9995 - val_loss:0.3759 - val_acc:0.9337
Epoch 805/1000
62s 123ms/step - loss:0.0719 - acc:0.9996 - val_loss:0.3788 - val_acc:0.9335
Epoch 806/1000
62s 123ms/step - loss:0.0719 - acc:0.9995 - val_loss:0.3815 - val_acc:0.9332
Epoch 807/1000
62s 123ms/step - loss:0.0716 - acc:0.9997 - val_loss:0.3774 - val_acc:0.9321
Epoch 808/1000
62s 124ms/step - loss:0.0714 - acc:0.9997 - val_loss:0.3774 - val_acc:0.9337
Epoch 809/1000
62s 124ms/step - loss:0.0714 - acc:0.9997 - val_loss:0.3786 - val_acc:0.9320
Epoch 810/1000
62s 124ms/step - loss:0.0713 - acc:0.9996 - val_loss:0.3776 - val_acc:0.9322
Epoch 811/1000
62s 123ms/step - loss:0.0712 - acc:0.9996 - val_loss:0.3782 - val_acc:0.9332
Epoch 812/1000
62s 123ms/step - loss:0.0709 - acc:0.9997 - val_loss:0.3837 - val_acc:0.9322
Epoch 813/1000
62s 123ms/step - loss:0.0705 - acc:0.9998 - val_loss:0.3839 - val_acc:0.9322
Epoch 814/1000
62s 123ms/step - loss:0.0707 - acc:0.9996 - val_loss:0.3820 - val_acc:0.9318
Epoch 815/1000
62s 123ms/step - loss:0.0705 - acc:0.9997 - val_loss:0.3829 - val_acc:0.9309
Epoch 816/1000
62s 124ms/step - loss:0.0703 - acc:0.9996 - val_loss:0.3810 - val_acc:0.9318
Epoch 817/1000
62s 124ms/step - loss:0.0700 - acc:0.9998 - val_loss:0.3799 - val_acc:0.9316
Epoch 818/1000
62s 124ms/step - loss:0.0701 - acc:0.9996 - val_loss:0.3789 - val_acc:0.9314
Epoch 819/1000
62s 124ms/step - loss:0.0698 - acc:0.9997 - val_loss:0.3802 - val_acc:0.9326
Epoch 820/1000
62s 123ms/step - loss:0.0699 - acc:0.9996 - val_loss:0.3837 - val_acc:0.9301
Epoch 821/1000
62s 123ms/step - loss:0.0697 - acc:0.9996 - val_loss:0.3833 - val_acc:0.9317
Epoch 822/1000
62s 124ms/step - loss:0.0698 - acc:0.9995 - val_loss:0.3851 - val_acc:0.9305
Epoch 823/1000
62s 124ms/step - loss:0.0694 - acc:0.9997 - val_loss:0.3824 - val_acc:0.9311
Epoch 824/1000
62s 124ms/step - loss:0.0693 - acc:0.9995 - val_loss:0.3830 - val_acc:0.9303
Epoch 825/1000
62s 124ms/step - loss:0.0690 - acc:0.9998 - val_loss:0.3802 - val_acc:0.9298
Epoch 826/1000
62s 124ms/step - loss:0.0689 - acc:0.9996 - val_loss:0.3810 - val_acc:0.9305
Epoch 827/1000
62s 124ms/step - loss:0.0689 - acc:0.9997 - val_loss:0.3813 - val_acc:0.9309
Epoch 828/1000
62s 124ms/step - loss:0.0688 - acc:0.9996 - val_loss:0.3799 - val_acc:0.9316
Epoch 829/1000
62s 123ms/step - loss:0.0687 - acc:0.9996 - val_loss:0.3766 - val_acc:0.9322
Epoch 830/1000
62s 124ms/step - loss:0.0688 - acc:0.9995 - val_loss:0.3764 - val_acc:0.9329
Epoch 831/1000
62s 124ms/step - loss:0.0684 - acc:0.9996 - val_loss:0.3750 - val_acc:0.9324
Epoch 832/1000
62s 124ms/step - loss:0.0685 - acc:0.9996 - val_loss:0.3781 - val_acc:0.9314
Epoch 833/1000
62s 124ms/step - loss:0.0682 - acc:0.9997 - val_loss:0.3741 - val_acc:0.9313
Epoch 834/1000
62s 124ms/step - loss:0.0682 - acc:0.9996 - val_loss:0.3738 - val_acc:0.9312
Epoch 835/1000
62s 124ms/step - loss:0.0680 - acc:0.9996 - val_loss:0.3753 - val_acc:0.9319
Epoch 836/1000
62s 124ms/step - loss:0.0679 - acc:0.9997 - val_loss:0.3753 - val_acc:0.9317
Epoch 837/1000
62s 123ms/step - loss:0.0677 - acc:0.9996 - val_loss:0.3769 - val_acc:0.9320
Epoch 838/1000
62s 123ms/step - loss:0.0674 - acc:0.9997 - val_loss:0.3775 - val_acc:0.9317
Epoch 839/1000
62s 124ms/step - loss:0.0678 - acc:0.9995 - val_loss:0.3779 - val_acc:0.9327
Epoch 840/1000
62s 124ms/step - loss:0.0673 - acc:0.9995 - val_loss:0.3773 - val_acc:0.9319
Epoch 841/1000
62s 124ms/step - loss:0.0672 - acc:0.9996 - val_loss:0.3764 - val_acc:0.9333
Epoch 842/1000
62s 124ms/step - loss:0.0670 - acc:0.9997 - val_loss:0.3741 - val_acc:0.9323
Epoch 843/1000
62s 124ms/step - loss:0.0667 - acc:0.9997 - val_loss:0.3723 - val_acc:0.9321
Epoch 844/1000
62s 124ms/step - loss:0.0667 - acc:0.9997 - val_loss:0.3731 - val_acc:0.9315
Epoch 845/1000
62s 123ms/step - loss:0.0668 - acc:0.9996 - val_loss:0.3733 - val_acc:0.9320
Epoch 846/1000
62s 124ms/step - loss:0.0666 - acc:0.9996 - val_loss:0.3722 - val_acc:0.9315
Epoch 847/1000
62s 123ms/step - loss:0.0664 - acc:0.9996 - val_loss:0.3719 - val_acc:0.9327
Epoch 848/1000
62s 124ms/step - loss:0.0662 - acc:0.9997 - val_loss:0.3720 - val_acc:0.9309
Epoch 849/1000
62s 124ms/step - loss:0.0660 - acc:0.9996 - val_loss:0.3716 - val_acc:0.9316
Epoch 850/1000
62s 124ms/step - loss:0.0660 - acc:0.9996 - val_loss:0.3732 - val_acc:0.9310
Epoch 851/1000
62s 123ms/step - loss:0.0661 - acc:0.9995 - val_loss:0.3718 - val_acc:0.9314
Epoch 852/1000
62s 123ms/step - loss:0.0657 - acc:0.9997 - val_loss:0.3748 - val_acc:0.9300
Epoch 853/1000
62s 124ms/step - loss:0.0654 - acc:0.9997 - val_loss:0.3724 - val_acc:0.9314
Epoch 854/1000
62s 124ms/step - loss:0.0658 - acc:0.9995 - val_loss:0.3750 - val_acc:0.9283
Epoch 855/1000
62s 124ms/step - loss:0.0652 - acc:0.9998 - val_loss:0.3719 - val_acc:0.9314
Epoch 856/1000
62s 124ms/step - loss:0.0652 - acc:0.9998 - val_loss:0.3724 - val_acc:0.9314
Epoch 857/1000
62s 123ms/step - loss:0.0652 - acc:0.9995 - val_loss:0.3732 - val_acc:0.9300
Epoch 858/1000
62s 124ms/step - loss:0.0648 - acc:0.9997 - val_loss:0.3714 - val_acc:0.9307
Epoch 859/1000
62s 123ms/step - loss:0.0654 - acc:0.9994 - val_loss:0.3719 - val_acc:0.9315
Epoch 860/1000
62s 124ms/step - loss:0.0645 - acc:0.9997 - val_loss:0.3726 - val_acc:0.9308
Epoch 861/1000
62s 123ms/step - loss:0.0648 - acc:0.9996 - val_loss:0.3725 - val_acc:0.9308
Epoch 862/1000
62s 123ms/step - loss:0.0645 - acc:0.9997 - val_loss:0.3698 - val_acc:0.9312
Epoch 863/1000
62s 124ms/step - loss:0.0642 - acc:0.9997 - val_loss:0.3715 - val_acc:0.9305
Epoch 864/1000
62s 124ms/step - loss:0.0643 - acc:0.9997 - val_loss:0.3724 - val_acc:0.9302
Epoch 865/1000
62s 124ms/step - loss:0.0639 - acc:0.9998 - val_loss:0.3748 - val_acc:0.9304
Epoch 866/1000
62s 124ms/step - loss:0.0641 - acc:0.9995 - val_loss:0.3751 - val_acc:0.9315
Epoch 867/1000
62s 124ms/step - loss:0.0638 - acc:0.9997 - val_loss:0.3729 - val_acc:0.9325
Epoch 868/1000
62s 123ms/step - loss:0.0637 - acc:0.9997 - val_loss:0.3750 - val_acc:0.9320
Epoch 869/1000
62s 124ms/step - loss:0.0634 - acc:0.9997 - val_loss:0.3738 - val_acc:0.9312
Epoch 870/1000
62s 123ms/step - loss:0.0634 - acc:0.9996 - val_loss:0.3731 - val_acc:0.9313
Epoch 871/1000
62s 124ms/step - loss:0.0632 - acc:0.9998 - val_loss:0.3750 - val_acc:0.9311
Epoch 872/1000
62s 124ms/step - loss:0.0633 - acc:0.9997 - val_loss:0.3784 - val_acc:0.9313
Epoch 873/1000
62s 124ms/step - loss:0.0635 - acc:0.9995 - val_loss:0.3719 - val_acc:0.9312
Epoch 874/1000
62s 123ms/step - loss:0.0631 - acc:0.9996 - val_loss:0.3706 - val_acc:0.9330
Epoch 875/1000
62s 124ms/step - loss:0.0626 - acc:0.9997 - val_loss:0.3711 - val_acc:0.9331
Epoch 876/1000
62s 123ms/step - loss:0.0628 - acc:0.9996 - val_loss:0.3730 - val_acc:0.9332
Epoch 877/1000
62s 123ms/step - loss:0.0626 - acc:0.9997 - val_loss:0.3744 - val_acc:0.9323
Epoch 878/1000
62s 124ms/step - loss:0.0623 - acc:0.9997 - val_loss:0.3724 - val_acc:0.9321
Epoch 879/1000
62s 124ms/step - loss:0.0624 - acc:0.9996 - val_loss:0.3749 - val_acc:0.9312
Epoch 880/1000
62s 124ms/step - loss:0.0621 - acc:0.9997 - val_loss:0.3728 - val_acc:0.9314
Epoch 881/1000
62s 123ms/step - loss:0.0620 - acc:0.9997 - val_loss:0.3733 - val_acc:0.9317
Epoch 882/1000
62s 124ms/step - loss:0.0623 - acc:0.9996 - val_loss:0.3779 - val_acc:0.9298
Epoch 883/1000
62s 124ms/step - loss:0.0621 - acc:0.9996 - val_loss:0.3733 - val_acc:0.9309
Epoch 884/1000
62s 123ms/step - loss:0.0617 - acc:0.9997 - val_loss:0.3714 - val_acc:0.9312
Epoch 885/1000
62s 124ms/step - loss:0.0615 - acc:0.9997 - val_loss:0.3708 - val_acc:0.9313
Epoch 886/1000
62s 124ms/step - loss:0.0615 - acc:0.9997 - val_loss:0.3727 - val_acc:0.9305
Epoch 887/1000
62s 123ms/step - loss:0.0616 - acc:0.9996 - val_loss:0.3699 - val_acc:0.9313
Epoch 888/1000
62s 124ms/step - loss:0.0611 - acc:0.9997 - val_loss:0.3709 - val_acc:0.9310
Epoch 889/1000
62s 124ms/step - loss:0.0611 - acc:0.9997 - val_loss:0.3718 - val_acc:0.9309
Epoch 890/1000
62s 124ms/step - loss:0.0611 - acc:0.9997 - val_loss:0.3721 - val_acc:0.9315
Epoch 891/1000
62s 124ms/step - loss:0.0606 - acc:0.9998 - val_loss:0.3726 - val_acc:0.9324
Epoch 892/1000
62s 123ms/step - loss:0.0606 - acc:0.9997 - val_loss:0.3737 - val_acc:0.9321
Epoch 893/1000
62s 123ms/step - loss:0.0607 - acc:0.9996 - val_loss:0.3709 - val_acc:0.9325
Epoch 894/1000
62s 123ms/step - loss:0.0602 - acc:0.9999 - val_loss:0.3701 - val_acc:0.9325
Epoch 895/1000
62s 124ms/step - loss:0.0604 - acc:0.9997 - val_loss:0.3670 - val_acc:0.9327
Epoch 896/1000
62s 124ms/step - loss:0.0606 - acc:0.9995 - val_loss:0.3646 - val_acc:0.9325
Epoch 897/1000
62s 124ms/step - loss:0.0603 - acc:0.9997 - val_loss:0.3693 - val_acc:0.9315
Epoch 898/1000
62s 123ms/step - loss:0.0602 - acc:0.9996 - val_loss:0.3705 - val_acc:0.9312
Epoch 899/1000
62s 124ms/step - loss:0.0599 - acc:0.9997 - val_loss:0.3697 - val_acc:0.9309
Epoch 900/1000
62s 123ms/step - loss:0.0600 - acc:0.9997 - val_loss:0.3694 - val_acc:0.9313
Epoch 901/1000
lr changed to 9.999999310821295e-05
62s 123ms/step - loss:0.0597 - acc:0.9998 - val_loss:0.3694 - val_acc:0.9313
Epoch 902/1000
62s 124ms/step - loss:0.0595 - acc:0.9998 - val_loss:0.3685 - val_acc:0.9316
Epoch 903/1000
62s 124ms/step - loss:0.0597 - acc:0.9998 - val_loss:0.3685 - val_acc:0.9314
Epoch 904/1000
62s 124ms/step - loss:0.0599 - acc:0.9997 - val_loss:0.3686 - val_acc:0.9316
Epoch 905/1000
62s 124ms/step - loss:0.0598 - acc:0.9997 - val_loss:0.3684 - val_acc:0.9316
Epoch 906/1000
62s 123ms/step - loss:0.0596 - acc:0.9998 - val_loss:0.3683 - val_acc:0.9313
Epoch 907/1000
62s 123ms/step - loss:0.0596 - acc:0.9998 - val_loss:0.3681 - val_acc:0.9314
Epoch 908/1000
62s 123ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3679 - val_acc:0.9311
Epoch 909/1000
62s 124ms/step - loss:0.0597 - acc:0.9997 - val_loss:0.3676 - val_acc:0.9309
Epoch 910/1000
62s 123ms/step - loss:0.0596 - acc:0.9997 - val_loss:0.3673 - val_acc:0.9311
Epoch 911/1000
62s 123ms/step - loss:0.0597 - acc:0.9997 - val_loss:0.3675 - val_acc:0.9311
Epoch 912/1000
62s 124ms/step - loss:0.0596 - acc:0.9997 - val_loss:0.3671 - val_acc:0.9311
Epoch 913/1000
62s 123ms/step - loss:0.0595 - acc:0.9997 - val_loss:0.3666 - val_acc:0.9314
Epoch 914/1000
62s 124ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3663 - val_acc:0.9317
Epoch 915/1000
62s 123ms/step - loss:0.0598 - acc:0.9996 - val_loss:0.3660 - val_acc:0.9318
Epoch 916/1000
62s 124ms/step - loss:0.0596 - acc:0.9997 - val_loss:0.3658 - val_acc:0.9320
Epoch 917/1000
62s 124ms/step - loss:0.0595 - acc:0.9997 - val_loss:0.3658 - val_acc:0.9318
Epoch 918/1000
62s 124ms/step - loss:0.0596 - acc:0.9997 - val_loss:0.3656 - val_acc:0.9316
Epoch 919/1000
62s 124ms/step - loss:0.0595 - acc:0.9997 - val_loss:0.3654 - val_acc:0.9316
Epoch 920/1000
62s 123ms/step - loss:0.0596 - acc:0.9997 - val_loss:0.3651 - val_acc:0.9314
Epoch 921/1000
62s 124ms/step - loss:0.0593 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9314
Epoch 922/1000
62s 123ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9316
Epoch 923/1000
62s 124ms/step - loss:0.0593 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9316
Epoch 924/1000
62s 124ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3644 - val_acc:0.9315
Epoch 925/1000
62s 124ms/step - loss:0.0592 - acc:0.9998 - val_loss:0.3648 - val_acc:0.9315
Epoch 926/1000
62s 124ms/step - loss:0.0593 - acc:0.9997 - val_loss:0.3647 - val_acc:0.9318
Epoch 927/1000
62s 123ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9313
Epoch 928/1000
62s 124ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9317
Epoch 929/1000
62s 123ms/step - loss:0.0592 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9320
Epoch 930/1000
62s 124ms/step - loss:0.0591 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9322
Epoch 931/1000
62s 124ms/step - loss:0.0592 - acc:0.9999 - val_loss:0.3647 - val_acc:0.9318
Epoch 932/1000
62s 124ms/step - loss:0.0592 - acc:0.9998 - val_loss:0.3644 - val_acc:0.9319
Epoch 933/1000
62s 124ms/step - loss:0.0594 - acc:0.9997 - val_loss:0.3642 - val_acc:0.9319
Epoch 934/1000
62s 123ms/step - loss:0.0594 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9318
Epoch 935/1000
62s 124ms/step - loss:0.0594 - acc:0.9997 - val_loss:0.3641 - val_acc:0.9318
Epoch 936/1000
62s 124ms/step - loss:0.0592 - acc:0.9998 - val_loss:0.3639 - val_acc:0.9313
Epoch 937/1000
62s 124ms/step - loss:0.0592 - acc:0.9998 - val_loss:0.3637 - val_acc:0.9321
Epoch 938/1000
62s 124ms/step - loss:0.0591 - acc:0.9998 - val_loss:0.3638 - val_acc:0.9320
Epoch 939/1000
62s 123ms/step - loss:0.0590 - acc:0.9999 - val_loss:0.3638 - val_acc:0.9320
Epoch 940/1000
62s 124ms/step - loss:0.0591 - acc:0.9998 - val_loss:0.3633 - val_acc:0.9324
Epoch 941/1000
62s 123ms/step - loss:0.0591 - acc:0.9998 - val_loss:0.3635 - val_acc:0.9325
Epoch 942/1000
62s 123ms/step - loss:0.0592 - acc:0.9997 - val_loss:0.3632 - val_acc:0.9324
Epoch 943/1000
62s 124ms/step - loss:0.0591 - acc:0.9997 - val_loss:0.3637 - val_acc:0.9330
Epoch 944/1000
62s 124ms/step - loss:0.0590 - acc:0.9998 - val_loss:0.3638 - val_acc:0.9327
Epoch 945/1000
62s 124ms/step - loss:0.0591 - acc:0.9997 - val_loss:0.3641 - val_acc:0.9329
Epoch 946/1000
62s 124ms/step - loss:0.0590 - acc:0.9998 - val_loss:0.3641 - val_acc:0.9328
Epoch 947/1000
62s 124ms/step - loss:0.0590 - acc:0.9997 - val_loss:0.3645 - val_acc:0.9328
Epoch 948/1000
62s 123ms/step - loss:0.0591 - acc:0.9997 - val_loss:0.3643 - val_acc:0.9329
Epoch 949/1000
62s 124ms/step - loss:0.0591 - acc:0.9997 - val_loss:0.3643 - val_acc:0.9328
Epoch 950/1000
62s 124ms/step - loss:0.0591 - acc:0.9998 - val_loss:0.3647 - val_acc:0.9329
Epoch 951/1000
62s 124ms/step - loss:0.0589 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9330
Epoch 952/1000
62s 123ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9326
Epoch 953/1000
62s 124ms/step - loss:0.0591 - acc:0.9997 - val_loss:0.3645 - val_acc:0.9326
Epoch 954/1000
62s 123ms/step - loss:0.0589 - acc:0.9998 - val_loss:0.3648 - val_acc:0.9329
Epoch 955/1000
62s 124ms/step - loss:0.0587 - acc:0.9999 - val_loss:0.3648 - val_acc:0.9327
Epoch 956/1000
62s 124ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3651 - val_acc:0.9325
Epoch 957/1000
62s 124ms/step - loss:0.0589 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9324
Epoch 958/1000
62s 123ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9320
Epoch 959/1000
62s 124ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9322
Epoch 960/1000
62s 124ms/step - loss:0.0590 - acc:0.9998 - val_loss:0.3651 - val_acc:0.9320
Epoch 961/1000
62s 124ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3652 - val_acc:0.9325
Epoch 962/1000
62s 124ms/step - loss:0.0590 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9322
Epoch 963/1000
62s 124ms/step - loss:0.0590 - acc:0.9997 - val_loss:0.3649 - val_acc:0.9324
Epoch 964/1000
62s 124ms/step - loss:0.0590 - acc:0.9998 - val_loss:0.3651 - val_acc:0.9322
Epoch 965/1000
62s 123ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9324
Epoch 966/1000
62s 124ms/step - loss:0.0589 - acc:0.9997 - val_loss:0.3649 - val_acc:0.9322
Epoch 967/1000
62s 124ms/step - loss:0.0590 - acc:0.9996 - val_loss:0.3649 - val_acc:0.9328
Epoch 968/1000
62s 124ms/step - loss:0.0588 - acc:0.9997 - val_loss:0.3648 - val_acc:0.9328
Epoch 969/1000
62s 124ms/step - loss:0.0589 - acc:0.9998 - val_loss:0.3647 - val_acc:0.9325
Epoch 970/1000
62s 124ms/step - loss:0.0587 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9325
Epoch 971/1000
62s 123ms/step - loss:0.0587 - acc:0.9997 - val_loss:0.3646 - val_acc:0.9328
Epoch 972/1000
62s 124ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9331
Epoch 973/1000
62s 124ms/step - loss:0.0586 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9331
Epoch 974/1000
62s 124ms/step - loss:0.0587 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9326
Epoch 975/1000
62s 124ms/step - loss:0.0586 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9322
Epoch 976/1000
62s 124ms/step - loss:0.0585 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9326
Epoch 977/1000
62s 124ms/step - loss:0.0591 - acc:0.9996 - val_loss:0.3646 - val_acc:0.9323
Epoch 978/1000
62s 124ms/step - loss:0.0587 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9326
Epoch 979/1000
62s 124ms/step - loss:0.0588 - acc:0.9997 - val_loss:0.3646 - val_acc:0.9320
Epoch 980/1000
62s 124ms/step - loss:0.0588 - acc:0.9997 - val_loss:0.3648 - val_acc:0.9319
Epoch 981/1000
62s 123ms/step - loss:0.0587 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9317
Epoch 982/1000
62s 124ms/step - loss:0.0584 - acc:0.9999 - val_loss:0.3650 - val_acc:0.9317
Epoch 983/1000
62s 124ms/step - loss:0.0586 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9323
Epoch 984/1000
62s 124ms/step - loss:0.0586 - acc:0.9998 - val_loss:0.3651 - val_acc:0.9322
Epoch 985/1000
62s 124ms/step - loss:0.0587 - acc:0.9997 - val_loss:0.3651 - val_acc:0.9321
Epoch 986/1000
62s 124ms/step - loss:0.0588 - acc:0.9998 - val_loss:0.3648 - val_acc:0.9323
Epoch 987/1000
62s 124ms/step - loss:0.0586 - acc:0.9997 - val_loss:0.3644 - val_acc:0.9318
Epoch 988/1000
62s 124ms/step - loss:0.0586 - acc:0.9997 - val_loss:0.3648 - val_acc:0.9322
Epoch 989/1000
62s 124ms/step - loss:0.0585 - acc:0.9998 - val_loss:0.3650 - val_acc:0.9322
Epoch 990/1000
62s 124ms/step - loss:0.0586 - acc:0.9998 - val_loss:0.3646 - val_acc:0.9319
Epoch 991/1000
62s 124ms/step - loss:0.0584 - acc:0.9998 - val_loss:0.3647 - val_acc:0.9323
Epoch 992/1000
62s 124ms/step - loss:0.0585 - acc:0.9997 - val_loss:0.3647 - val_acc:0.9320
Epoch 993/1000
62s 124ms/step - loss:0.0587 - acc:0.9997 - val_loss:0.3646 - val_acc:0.9318
Epoch 994/1000
62s 124ms/step - loss:0.0584 - acc:0.9999 - val_loss:0.3650 - val_acc:0.9320
Epoch 995/1000
62s 124ms/step - loss:0.0586 - acc:0.9997 - val_loss:0.3650 - val_acc:0.9315
Epoch 996/1000
62s 123ms/step - loss:0.0585 - acc:0.9998 - val_loss:0.3649 - val_acc:0.9319
Epoch 997/1000
62s 123ms/step - loss:0.0585 - acc:0.9998 - val_loss:0.3645 - val_acc:0.9318
Epoch 998/1000
62s 124ms/step - loss:0.0584 - acc:0.9998 - val_loss:0.3648 - val_acc:0.9320
Epoch 999/1000
62s 124ms/step - loss:0.0584 - acc:0.9999 - val_loss:0.3646 - val_acc:0.9320
Epoch 1000/1000
62s 124ms/step - loss:0.0581 - acc:0.9999 - val_loss:0.3646 - val_acc:0.9323
Train loss:0.062079589650034905
Train accuracy:0.9986200013160705
Test loss:0.3645842906832695
Test accuracy:0.9323000019788742

  epoch   701 754 epoch          

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...