本文在调参记录20的基础上,将残差模块的个数,从27个增加到60个,继续测试深度残差网络ResNet+自适应参数化ReLU激活函数在Cifar10数据集上的表现。自适应参数化ReLU函数被放在了残差模块的第二个卷积层之后,这与Squeeze
本文在调参记录20的基础上,将残差模块的个数,从27个增加到60个,继续测试深度残差网络ResNet+自适应参数化ReLU激活函数在Cifar10数据集上的表现。
自适应参数化ReLU函数被放在了残差模块的第二个卷积层之后,这与Squeeze-and-Excitation Networks或者深度残差收缩网络是相似的。其基本原理如下
Keras程序如下:
#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Tue Apr 14 04:17:45 2020Implemented using Tensorflow 1.10.0 and Keras 2.2.1Minghang 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 @author: Minghang Zhao"""from __future__ import print_functionimport kerasimport numpy as npfrom keras.datasets import cifar10from keras.layers import Dense, Conv2D, BatchNORMalization, Activation, Minimumfrom keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D, Concatenate, Reshapefrom keras.regularizers import l2from keras import backend as Kfrom keras.models import Modelfrom keras import optimizersfrom keras.preprocessing.image import ImageDataGeneratorfrom keras.callbacks import LearningRateSchedulerK.set_learning_phase(1)# The data, split between train and test sets(x_train, y_train), (x_test, y_test) = cifar10.load_data()# Noised datax_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 matricesy_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 150 epochesdef scheduler(epoch): if epoch % 150 == 0 and epoch != 0: lr = K.get_value(model.optimizer.lr) K.set_value(model.optimizer.lr, lr * 0.1) print("lr changed to {}".format(lr * 0.1)) return K.get_value(model.optimizer.lr)# An adaptively parametric rectifier linear unit (APReLU)def aprelu(inputs): # get the number of channels channels = inputs.get_shape().as_list()[-1] # get a zero feature map zeros_input = keras.layers.subtract([inputs, inputs]) # get a feature map with only positive features pos_input = Activation('relu')(inputs) # get a feature map with only negative features neg_input = Minimum()([inputs,zeros_input]) # define a network to obtain the scaling coefficients scales_p = GlobalAveragePooling2D()(pos_input) scales_n = GlobalAveragePooling2D()(neg_input) scales = Concatenate()([scales_n, scales_p]) scales = Dense(channels//16, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales) scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales) scales = Activation('relu')(scales) scales = Dense(channels, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales) scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales) scales = Activation('sigmoid')(scales) scales = Reshape((1,1,channels))(scales) # apply a paramtetric relu neg_part = keras.layers.multiply([scales, neg_input]) return keras.layers.add([pos_input, neg_part])# Residual Blockdef residual_block(incoming, nb_blocks, out_channels, downsample=False, downsample_strides=2): residual = incoming in_channels = incoming.get_shape().as_list()[-1] for i in range(nb_blocks): identity = residual if not downsample: downsample_strides = 1 residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) residual = Activation('relu')(residual) residual = Conv2D(out_channels, 3, strides=(downsample_strides, downsample_strides), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(residual) residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) residual = Activation('relu')(residual) residual = Conv2D(out_channels, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(residual) residual = aprelu(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 modelinputs = 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, 20, 32, downsample=False)net = residual_block(net, 1, 32, downsample=True)net = residual_block(net, 19, 32, downsample=False)net = residual_block(net, 1, 64, downsample=True)net = residual_block(net, 19, 64, downsample=False)net = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(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 augmentationdatagen = ImageDataGenerator( # randomly rotate images in the range (deg 0 to 180) rotation_range=30, # Range for random zoom zoom_range = 0.2, # shear angle in counter-clockwise direction in degrees shear_range = 30, # randomly flip images horizontal_flip=True, # randomly shift images horizontally width_shift_range=0.125, # randomly shift images vertically height_shift_range=0.125)reduce_lr = LearningRateScheduler(scheduler)# fit the model on the batches generated by datagen.flow().model.fit_generator(datagen.flow(x_train, y_train, batch_size=100), validation_data=(x_test, y_test), epochs=500, verbose=1, callbacks=[reduce_lr], workers=4)# get resultsK.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])
实验结果如下:
Using TensorFlow backend.x_train shape: (50000, 32, 32, 3)50000 train samples10000 test samplesEpoch 1/500156s 312ms/step - loss: 3.7450 - acc: 0.4151 - val_loss: 3.1432 - val_acc: 0.5763Epoch 2/500113s 226ms/step - loss: 2.9954 - acc: 0.5750 - val_loss: 2.5940 - val_acc: 0.6689Epoch 3/500113s 226ms/step - loss: 2.5203 - acc: 0.6476 - val_loss: 2.1871 - val_acc: 0.7254Epoch 4/500113s 225ms/step - loss: 2.1855 - acc: 0.6865 - val_loss: 1.9171 - val_acc: 0.7488Epoch 5/500113s 225ms/step - loss: 1.9224 - acc: 0.7144 - val_loss: 1.6662 - val_acc: 0.7774Epoch 6/500113s 225ms/step - loss: 1.7111 - acc: 0.7331 - val_loss: 1.4882 - val_acc: 0.7915Epoch 7/500113s 226ms/step - loss: 1.5472 - acc: 0.7483 - val_loss: 1.3414 - val_acc: 0.7994Epoch 8/500113s 226ms/step - loss: 1.4095 - acc: 0.7633 - val_loss: 1.2149 - val_acc: 0.8194Epoch 9/500113s 226ms/step - loss: 1.3008 - acc: 0.7739 - val_loss: 1.1264 - val_acc: 0.8234Epoch 10/500113s 226ms/step - loss: 1.2077 - acc: 0.7824 - val_loss: 1.0474 - val_acc: 0.8322Epoch 11/500113s 225ms/step - loss: 1.1382 - acc: 0.7885 - val_loss: 0.9929 - val_acc: 0.8343Epoch 12/500113s 225ms/step - loss: 1.0722 - acc: 0.7955 - val_loss: 0.9418 - val_acc: 0.8400Epoch 13/500113s 225ms/step - loss: 1.0242 - acc: 0.8032 - val_loss: 0.9018 - val_acc: 0.8421Epoch 14/500113s 225ms/step - loss: 0.9843 - acc: 0.8083 - val_loss: 0.8639 - val_acc: 0.8506Epoch 15/500113s 225ms/step - loss: 0.9520 - acc: 0.8101 - val_loss: 0.8522 - val_acc: 0.8491Epoch 16/500113s 226ms/step - loss: 0.9313 - acc: 0.8130 - val_loss: 0.8124 - val_acc: 0.8541Epoch 17/500113s 226ms/step - loss: 0.9033 - acc: 0.8190 - val_loss: 0.8156 - val_acc: 0.8484Epoch 18/500113s 226ms/step - loss: 0.8791 - acc: 0.8223 - val_loss: 0.7796 - val_acc: 0.8572Epoch 19/500113s 226ms/step - loss: 0.8628 - acc: 0.8289 - val_loss: 0.7842 - val_acc: 0.8559Epoch 20/500113s 225ms/step - loss: 0.8528 - acc: 0.8292 - val_loss: 0.7725 - val_acc: 0.8533Epoch 21/500113s 225ms/step - loss: 0.8432 - acc: 0.8292 - val_loss: 0.7405 - val_acc: 0.8687Epoch 22/500113s 225ms/step - loss: 0.8260 - acc: 0.8347 - val_loss: 0.7425 - val_acc: 0.8648Epoch 23/500113s 225ms/step - loss: 0.8180 - acc: 0.8357 - val_loss: 0.7319 - val_acc: 0.8666Epoch 24/500113s 226ms/step - loss: 0.8146 - acc: 0.8385 - val_loss: 0.7158 - val_acc: 0.8761Epoch 25/500113s 226ms/step - loss: 0.8029 - acc: 0.8387 - val_loss: 0.7228 - val_acc: 0.8705Epoch 26/500113s 225ms/step - loss: 0.7968 - acc: 0.8425 - val_loss: 0.7160 - val_acc: 0.8725Epoch 27/500113s 225ms/step - loss: 0.7940 - acc: 0.8433 - val_loss: 0.7176 - val_acc: 0.8747Epoch 28/500113s 226ms/step - loss: 0.7904 - acc: 0.8439 - val_loss: 0.7080 - val_acc: 0.8747Epoch 29/500113s 225ms/step - loss: 0.7810 - acc: 0.8450 - val_loss: 0.7234 - val_acc: 0.8679Epoch 30/500113s 225ms/step - loss: 0.7807 - acc: 0.8457 - val_loss: 0.6999 - val_acc: 0.8754Epoch 31/500113s 225ms/step - loss: 0.7795 - acc: 0.8487 - val_loss: 0.7116 - val_acc: 0.8745Epoch 32/500113s 225ms/step - loss: 0.7722 - acc: 0.8497 - val_loss: 0.7064 - val_acc: 0.8798Epoch 33/500113s 226ms/step - loss: 0.7678 - acc: 0.8533 - val_loss: 0.7148 - val_acc: 0.8709Epoch 34/500113s 226ms/step - loss: 0.7634 - acc: 0.8528 - val_loss: 0.7095 - val_acc: 0.8741Epoch 35/500113s 225ms/step - loss: 0.7684 - acc: 0.8535 - val_loss: 0.7070 - val_acc: 0.8768Epoch 36/500113s 225ms/step - loss: 0.7630 - acc: 0.8540 - val_loss: 0.6935 - val_acc: 0.8804Epoch 37/500113s 225ms/step - loss: 0.7557 - acc: 0.8566 - val_loss: 0.6997 - val_acc: 0.8785Epoch 38/500113s 225ms/step - loss: 0.7518 - acc: 0.8591 - val_loss: 0.7090 - val_acc: 0.8771Epoch 39/500113s 225ms/step - loss: 0.7537 - acc: 0.8581 - val_loss: 0.6784 - val_acc: 0.8879Epoch 40/500113s 226ms/step - loss: 0.7537 - acc: 0.8566 - val_loss: 0.6778 - val_acc: 0.8854Epoch 41/500113s 226ms/step - loss: 0.7461 - acc: 0.8613 - val_loss: 0.6941 - val_acc: 0.8800Epoch 42/500113s 226ms/step - loss: 0.7518 - acc: 0.8586 - val_loss: 0.7230 - val_acc: 0.8731Epoch 43/500113s 225ms/step - loss: 0.7562 - acc: 0.8561 - val_loss: 0.6876 - val_acc: 0.8859Epoch 44/500113s 225ms/step - loss: 0.7398 - acc: 0.8626 - val_loss: 0.6793 - val_acc: 0.8861Epoch 45/500113s 225ms/step - loss: 0.7402 - acc: 0.8638 - val_loss: 0.6860 - val_acc: 0.8857Epoch 46/500113s 225ms/step - loss: 0.7430 - acc: 0.8626 - val_loss: 0.6878 - val_acc: 0.8857Epoch 47/500113s 225ms/step - loss: 0.7372 - acc: 0.8656 - val_loss: 0.6758 - val_acc: 0.8885Epoch 48/500113s 225ms/step - loss: 0.7364 - acc: 0.8649 - val_loss: 0.6837 - val_acc: 0.8849Epoch 49/500113s 226ms/step - loss: 0.7374 - acc: 0.8639 - val_loss: 0.6730 - val_acc: 0.8902Epoch 50/500113s 226ms/step - loss: 0.7389 - acc: 0.8657 - val_loss: 0.6848 - val_acc: 0.8868Epoch 51/500113s 227ms/step - loss: 0.7354 - acc: 0.8654 - val_loss: 0.6788 - val_acc: 0.8892Epoch 52/500113s 227ms/step - loss: 0.7286 - acc: 0.8691 - val_loss: 0.6942 - val_acc: 0.8800Epoch 53/500113s 225ms/step - loss: 0.7365 - acc: 0.8653 - val_loss: 0.6929 - val_acc: 0.8820Epoch 54/500113s 226ms/step - loss: 0.7295 - acc: 0.8685 - val_loss: 0.6761 - val_acc: 0.8892Epoch 55/500113s 226ms/step - loss: 0.7319 - acc: 0.8694 - val_loss: 0.6715 - val_acc: 0.8886Epoch 56/500113s 226ms/step - loss: 0.7315 - acc: 0.8681 - val_loss: 0.6807 - val_acc: 0.8891Epoch 57/500113s 226ms/step - loss: 0.7330 - acc: 0.8679 - val_loss: 0.6705 - val_acc: 0.8943Epoch 58/500113s 226ms/step - loss: 0.7269 - acc: 0.8715 - val_loss: 0.7076 - val_acc: 0.8776Epoch 59/500113s 226ms/step - loss: 0.7314 - acc: 0.8690 - val_loss: 0.6747 - val_acc: 0.8884Epoch 60/500113s 226ms/step - loss: 0.7323 - acc: 0.8699 - val_loss: 0.6775 - val_acc: 0.8867Epoch 61/500113s 225ms/step - loss: 0.7289 - acc: 0.8698 - val_loss: 0.6851 - val_acc: 0.8838Epoch 62/500112s 225ms/step - loss: 0.7290 - acc: 0.8688 - val_loss: 0.6995 - val_acc: 0.8838Epoch 63/500112s 225ms/step - loss: 0.7302 - acc: 0.8696 - val_loss: 0.6758 - val_acc: 0.8913Epoch 64/500113s 225ms/step - loss: 0.7264 - acc: 0.8714 - val_loss: 0.6770 - val_acc: 0.8907Epoch 65/500113s 225ms/step - loss: 0.7238 - acc: 0.8725 - val_loss: 0.6898 - val_acc: 0.8865Epoch 66/500113s 225ms/step - loss: 0.7218 - acc: 0.8728 - val_loss: 0.6712 - val_acc: 0.8936Epoch 67/500113s 225ms/step - loss: 0.7235 - acc: 0.8729 - val_loss: 0.6829 - val_acc: 0.8888Epoch 68/500112s 225ms/step - loss: 0.7226 - acc: 0.8740 - val_loss: 0.6635 - val_acc: 0.8967Epoch 69/500112s 225ms/step - loss: 0.7281 - acc: 0.8713 - val_loss: 0.6750 - val_acc: 0.8912Epoch 70/500112s 225ms/step - loss: 0.7218 - acc: 0.8735 - val_loss: 0.6937 - val_acc: 0.8855Epoch 71/500113s 225ms/step - loss: 0.7207 - acc: 0.8738 - val_loss: 0.7040 - val_acc: 0.8796Epoch 72/500113s 225ms/step - loss: 0.7215 - acc: 0.8748 - val_loss: 0.6944 - val_acc: 0.8890Epoch 73/500113s 225ms/step - loss: 0.7206 - acc: 0.8742 - val_loss: 0.6757 - val_acc: 0.8903Epoch 74/500113s 225ms/step - loss: 0.7172 - acc: 0.8750 - val_loss: 0.6872 - val_acc: 0.8889Epoch 75/500113s 225ms/step - loss: 0.7183 - acc: 0.8758 - val_loss: 0.6691 - val_acc: 0.8950Epoch 76/500112s 225ms/step - loss: 0.7188 - acc: 0.8749 - val_loss: 0.6823 - val_acc: 0.8872Epoch 77/500112s 225ms/step - loss: 0.7165 - acc: 0.8753 - val_loss: 0.6794 - val_acc: 0.8913Epoch 78/500113s 225ms/step - loss: 0.7159 - acc: 0.8760 - val_loss: 0.7313 - val_acc: 0.8730Epoch 79/500112s 225ms/step - loss: 0.7146 - acc: 0.8772 - val_loss: 0.7072 - val_acc: 0.8798Epoch 80/500113s 225ms/step - loss: 0.7196 - acc: 0.8754 - val_loss: 0.6698 - val_acc: 0.8951Epoch 81/500113s 225ms/step - loss: 0.7112 - acc: 0.8789 - val_loss: 0.6696 - val_acc: 0.8939Epoch 82/500113s 225ms/step - loss: 0.7180 - acc: 0.8757 - val_loss: 0.6697 - val_acc: 0.8944Epoch 83/500113s 225ms/step - loss: 0.7126 - acc: 0.8770 - val_loss: 0.6615 - val_acc: 0.8972Epoch 84/500112s 225ms/step - loss: 0.7112 - acc: 0.8799 - val_loss: 0.6893 - val_acc: 0.8848Epoch 85/500112s 225ms/step - loss: 0.7149 - acc: 0.8766 - val_loss: 0.6679 - val_acc: 0.8963Epoch 86/500112s 225ms/step - loss: 0.7109 - acc: 0.8769 - val_loss: 0.6713 - val_acc: 0.8953Epoch 87/500112s 225ms/step - loss: 0.7088 - acc: 0.8803 - val_loss: 0.6571 - val_acc: 0.8985Epoch 88/500112s 225ms/step - loss: 0.7119 - acc: 0.8789 - val_loss: 0.6786 - val_acc: 0.8919Epoch 89/500113s 225ms/step - loss: 0.7111 - acc: 0.8767 - val_loss: 0.6741 - val_acc: 0.8925Epoch 90/500113s 225ms/step - loss: 0.7096 - acc: 0.8788 - val_loss: 0.7048 - val_acc: 0.8829Epoch 91/500113s 225ms/step - loss: 0.7056 - acc: 0.8787 - val_loss: 0.6714 - val_acc: 0.8933Epoch 92/500113s 225ms/step - loss: 0.7121 - acc: 0.8786 - val_loss: 0.6962 - val_acc: 0.8857Epoch 93/500112s 225ms/step - loss: 0.7078 - acc: 0.8805 - val_loss: 0.6854 - val_acc: 0.8882Epoch 94/500112s 225ms/step - loss: 0.7026 - acc: 0.8830 - val_loss: 0.6821 - val_acc: 0.8894Epoch 95/500112s 225ms/step - loss: 0.7063 - acc: 0.8812 - val_loss: 0.6900 - val_acc: 0.8866Epoch 96/500113s 225ms/step - loss: 0.7091 - acc: 0.8803 - val_loss: 0.6765 - val_acc: 0.8961Epoch 97/500113s 225ms/step - loss: 0.7036 - acc: 0.8810 - val_loss: 0.6744 - val_acc: 0.8946Epoch 98/500113s 225ms/step - loss: 0.7081 - acc: 0.8794 - val_loss: 0.6673 - val_acc: 0.8952Epoch 99/500113s 225ms/step - loss: 0.7091 - acc: 0.8799 - val_loss: 0.6713 - val_acc: 0.8931Epoch 100/500112s 225ms/step - loss: 0.7066 - acc: 0.8814 - val_loss: 0.6701 - val_acc: 0.8938Epoch 101/500112s 225ms/step - loss: 0.7114 - acc: 0.8797 - val_loss: 0.6702 - val_acc: 0.8961Epoch 102/500112s 225ms/step - loss: 0.7028 - acc: 0.8816 - val_loss: 0.6682 - val_acc: 0.8965Epoch 103/500115s 229ms/step - loss: 0.7026 - acc: 0.8826 - val_loss: 0.6839 - val_acc: 0.8905Epoch 104/500116s 232ms/step - loss: 0.7047 - acc: 0.8810 - val_loss: 0.6711 - val_acc: 0.8953Epoch 105/500113s 227ms/step - loss: 0.7039 - acc: 0.8814 - val_loss: 0.6785 - val_acc: 0.8928Epoch 106/500113s 227ms/step - loss: 0.7064 - acc: 0.8824 - val_loss: 0.6767 - val_acc: 0.8928Epoch 107/500114s 227ms/step - loss: 0.7069 - acc: 0.8804 - val_loss: 0.6523 - val_acc: 0.9039Epoch 108/500113s 226ms/step - loss: 0.7051 - acc: 0.8813 - val_loss: 0.6804 - val_acc: 0.8919Epoch 109/500113s 227ms/step - loss: 0.6994 - acc: 0.8833 - val_loss: 0.6735 - val_acc: 0.8955Epoch 110/500113s 226ms/step - loss: 0.7034 - acc: 0.8829 - val_loss: 0.6633 - val_acc: 0.8982Epoch 111/500113s 226ms/step - loss: 0.7008 - acc: 0.8839 - val_loss: 0.6726 - val_acc: 0.8911Epoch 112/500113s 226ms/step - loss: 0.7010 - acc: 0.8828 - val_loss: 0.6609 - val_acc: 0.8981Epoch 113/500113s 226ms/step - loss: 0.7055 - acc: 0.8811 - val_loss: 0.6971 - val_acc: 0.8839Epoch 114/500113s 226ms/step - loss: 0.7023 - acc: 0.8834 - val_loss: 0.6695 - val_acc: 0.8949Epoch 115/500113s 227ms/step - loss: 0.7028 - acc: 0.8832 - val_loss: 0.6720 - val_acc: 0.8975Epoch 116/500113s 226ms/step - loss: 0.7005 - acc: 0.8843 - val_loss: 0.6934 - val_acc: 0.8880Epoch 117/500113s 226ms/step - loss: 0.7030 - acc: 0.8842 - val_loss: 0.6827 - val_acc: 0.8932Epoch 118/500113s 226ms/step - loss: 0.7016 - acc: 0.8861 - val_loss: 0.6817 - val_acc: 0.8936Epoch 119/500112s 225ms/step - loss: 0.7037 - acc: 0.8841 - val_loss: 0.6781 - val_acc: 0.8958Epoch 120/500113s 226ms/step - loss: 0.7014 - acc: 0.8837 - val_loss: 0.6793 - val_acc: 0.8936Epoch 121/500113s 227ms/step - loss: 0.7016 - acc: 0.8829 - val_loss: 0.6608 - val_acc: 0.9021Epoch 122/500113s 227ms/step - loss: 0.6984 - acc: 0.8848 - val_loss: 0.6910 - val_acc: 0.8891Epoch 123/500113s 227ms/step - loss: 0.6991 - acc: 0.8846 - val_loss: 0.6739 - val_acc: 0.8955Epoch 124/500113s 226ms/step - loss: 0.6990 - acc: 0.8846 - val_loss: 0.6570 - val_acc: 0.9016Epoch 125/500113s 226ms/step - loss: 0.6992 - acc: 0.8846 - val_loss: 0.6822 - val_acc: 0.8909Epoch 126/500113s 226ms/step - loss: 0.7034 - acc: 0.8824 - val_loss: 0.6745 - val_acc: 0.8981Epoch 127/500114s 227ms/step - loss: 0.6946 - acc: 0.8866 - val_loss: 0.6683 - val_acc: 0.8949Epoch 128/500113s 227ms/step - loss: 0.6965 - acc: 0.8850 - val_loss: 0.6737 - val_acc: 0.8963Epoch 129/500113s 227ms/step - loss: 0.7051 - acc: 0.8827 - val_loss: 0.6649 - val_acc: 0.8981Epoch 130/500113s 227ms/step - loss: 0.6976 - acc: 0.8846 - val_loss: 0.6652 - val_acc: 0.8990Epoch 131/500113s 227ms/step - loss: 0.7012 - acc: 0.8841 - val_loss: 0.6639 - val_acc: 0.8959Epoch 132/500113s 226ms/step - loss: 0.6958 - acc: 0.8850 - val_loss: 0.6691 - val_acc: 0.8946Epoch 133/500113s 226ms/step - loss: 0.6963 - acc: 0.8849 - val_loss: 0.6856 - val_acc: 0.8914Epoch 134/500113s 225ms/step - loss: 0.6970 - acc: 0.8862 - val_loss: 0.6668 - val_acc: 0.8966Epoch 135/500112s 225ms/step - loss: 0.7032 - acc: 0.8821 - val_loss: 0.6686 - val_acc: 0.8974Epoch 136/500113s 226ms/step - loss: 0.6983 - acc: 0.8875 - val_loss: 0.6755 - val_acc: 0.8957Epoch 137/500113s 225ms/step - loss: 0.6947 - acc: 0.8871 - val_loss: 0.6649 - val_acc: 0.8966Epoch 138/500113s 226ms/step - loss: 0.6941 - acc: 0.8877 - val_loss: 0.6825 - val_acc: 0.8892Epoch 139/500113s 225ms/step - loss: 0.6954 - acc: 0.8870 - val_loss: 0.6597 - val_acc: 0.9013Epoch 140/500113s 225ms/step - loss: 0.6950 - acc: 0.8855 - val_loss: 0.6797 - val_acc: 0.8891Epoch 141/500113s 225ms/step - loss: 0.6965 - acc: 0.8854 - val_loss: 0.6886 - val_acc: 0.8924Epoch 142/500113s 225ms/step - loss: 0.6912 - acc: 0.8879 - val_loss: 0.6643 - val_acc: 0.8985Epoch 143/500113s 225ms/step - loss: 0.6955 - acc: 0.8869 - val_loss: 0.6971 - val_acc: 0.8889Epoch 144/500112s 225ms/step - loss: 0.6932 - acc: 0.8870 - val_loss: 0.6666 - val_acc: 0.8969Epoch 145/500113s 225ms/step - loss: 0.6914 - acc: 0.8875 - val_loss: 0.6700 - val_acc: 0.8981Epoch 146/500113s 225ms/step - loss: 0.6989 - acc: 0.8856 - val_loss: 0.6825 - val_acc: 0.8936Epoch 147/500113s 225ms/step - loss: 0.6970 - acc: 0.8861 - val_loss: 0.6667 - val_acc: 0.8995Epoch 148/500113s 225ms/step - loss: 0.6911 - acc: 0.8880 - val_loss: 0.6808 - val_acc: 0.8912Epoch 149/500112s 225ms/step - loss: 0.6987 - acc: 0.8853 - val_loss: 0.6893 - val_acc: 0.8885Epoch 150/500112s 225ms/step - loss: 0.6952 - acc: 0.8868 - val_loss: 0.6745 - val_acc: 0.8932Epoch 151/500lr changed to 0.010000000149011612113s 225ms/step - loss: 0.5880 - acc: 0.9249 - val_loss: 0.5801 - val_acc: 0.9269Epoch 152/500113s 225ms/step - loss: 0.5264 - acc: 0.9440 - val_loss: 0.5680 - val_acc: 0.9276Epoch 153/500113s 225ms/step - loss: 0.5067 - acc: 0.9467 - val_loss: 0.5533 - val_acc: 0.9320Epoch 154/500113s 225ms/step - loss: 0.4909 - acc: 0.9512 - val_loss: 0.5453 - val_acc: 0.9325Epoch 155/500112s 225ms/step - loss: 0.4762 - acc: 0.9550 - val_loss: 0.5348 - val_acc: 0.9330Epoch 156/500112s 225ms/step - loss: 0.4647 - acc: 0.9559 - val_loss: 0.5253 - val_acc: 0.9360Epoch 157/500112s 225ms/step - loss: 0.4550 - acc: 0.9583 - val_loss: 0.5218 - val_acc: 0.9354Epoch 158/500113s 225ms/step - loss: 0.4475 - acc: 0.9579 - val_loss: 0.5165 - val_acc: 0.9351Epoch 159/500112s 225ms/step - loss: 0.4348 - acc: 0.9615 - val_loss: 0.5185 - val_acc: 0.9346Epoch 160/500112s 225ms/step - loss: 0.4245 - acc: 0.9629 - val_loss: 0.5120 - val_acc: 0.9342Epoch 161/500113s 225ms/step - loss: 0.4177 - acc: 0.9638 - val_loss: 0.5018 - val_acc: 0.9365Epoch 162/500113s 225ms/step - loss: 0.4123 - acc: 0.9638 - val_loss: 0.5089 - val_acc: 0.9323Epoch 163/500113s 225ms/step - loss: 0.4046 - acc: 0.9647 - val_loss: 0.4858 - val_acc: 0.9379Epoch 164/500112s 225ms/step - loss: 0.3988 - acc: 0.9654 - val_loss: 0.4954 - val_acc: 0.9334Epoch 165/500112s 225ms/step - loss: 0.3880 - acc: 0.9677 - val_loss: 0.4836 - val_acc: 0.9362Epoch 166/500112s 225ms/step - loss: 0.3873 - acc: 0.9656 - val_loss: 0.4829 - val_acc: 0.9364Epoch 167/500112s 225ms/step - loss: 0.3819 - acc: 0.9661 - val_loss: 0.4774 - val_acc: 0.9362Epoch 168/500113s 225ms/step - loss: 0.3697 - acc: 0.9691 - val_loss: 0.4738 - val_acc: 0.9353Epoch 169/500113s 225ms/step - loss: 0.3664 - acc: 0.9688 - val_loss: 0.4863 - val_acc: 0.9318Epoch 170/500113s 225ms/step - loss: 0.3630 - acc: 0.9687 - val_loss: 0.4720 - val_acc: 0.9349Epoch 171/500113s 225ms/step - loss: 0.3587 - acc: 0.9687 - val_loss: 0.4613 - val_acc: 0.9355Epoch 172/500112s 225ms/step - loss: 0.3558 - acc: 0.9680 - val_loss: 0.4569 - val_acc: 0.9381Epoch 173/500112s 225ms/step - loss: 0.3453 - acc: 0.9714 - val_loss: 0.4611 - val_acc: 0.9359Epoch 174/500112s 225ms/step - loss: 0.3427 - acc: 0.9712 - val_loss: 0.4663 - val_acc: 0.9335Epoch 175/500112s 225ms/step - loss: 0.3369 - acc: 0.9709 - val_loss: 0.4493 - val_acc: 0.9386Epoch 176/500112s 225ms/step - loss: 0.3342 - acc: 0.9709 - val_loss: 0.4462 - val_acc: 0.9390Epoch 177/500113s 225ms/step - loss: 0.3293 - acc: 0.9721 - val_loss: 0.4442 - val_acc: 0.9368Epoch 178/500113s 225ms/step - loss: 0.3271 - acc: 0.9712 - val_loss: 0.4484 - val_acc: 0.9373Epoch 179/500113s 225ms/step - loss: 0.3217 - acc: 0.9730 - val_loss: 0.4435 - val_acc: 0.9335Epoch 180/500112s 225ms/step - loss: 0.3189 - acc: 0.9730 - val_loss: 0.4352 - val_acc: 0.9372Epoch 181/500112s 225ms/step - loss: 0.3133 - acc: 0.9748 - val_loss: 0.4449 - val_acc: 0.9313Epoch 182/500112s 225ms/step - loss: 0.3109 - acc: 0.9737 - val_loss: 0.4395 - val_acc: 0.9365Epoch 183/500112s 225ms/step - loss: 0.3092 - acc: 0.9720 - val_loss: 0.4329 - val_acc: 0.9374Epoch 184/500113s 225ms/step - loss: 0.3045 - acc: 0.9743 - val_loss: 0.4374 - val_acc: 0.9362Epoch 185/500113s 225ms/step - loss: 0.3005 - acc: 0.9741 - val_loss: 0.4256 - val_acc: 0.9371Epoch 186/500113s 225ms/step - loss: 0.3022 - acc: 0.9728 - val_loss: 0.4335 - val_acc: 0.9344Epoch 187/500112s 225ms/step - loss: 0.2969 - acc: 0.9737 - val_loss: 0.4246 - val_acc: 0.9343Epoch 188/500113s 225ms/step - loss: 0.2931 - acc: 0.9751 - val_loss: 0.4229 - val_acc: 0.9339Epoch 189/500112s 225ms/step - loss: 0.2929 - acc: 0.9734 - val_loss: 0.4216 - val_acc: 0.9362Epoch 190/500112s 225ms/step - loss: 0.2892 - acc: 0.9743 - val_loss: 0.4263 - val_acc: 0.9358Epoch 191/500112s 225ms/step - loss: 0.2869 - acc: 0.9744 - val_loss: 0.4181 - val_acc: 0.9342Epoch 192/500113s 225ms/step - loss: 0.2867 - acc: 0.9743 - val_loss: 0.4099 - val_acc: 0.9367Epoch 193/500113s 225ms/step - loss: 0.2848 - acc: 0.9739 - val_loss: 0.4184 - val_acc: 0.9378Epoch 194/500113s 226ms/step - loss: 0.2820 - acc: 0.9744 - val_loss: 0.4223 - val_acc: 0.9360Epoch 195/500113s 225ms/step - loss: 0.2827 - acc: 0.9726 - val_loss: 0.4049 - val_acc: 0.9375Epoch 196/500113s 225ms/step - loss: 0.2778 - acc: 0.9743 - val_loss: 0.4126 - val_acc: 0.9321Epoch 197/500113s 225ms/step - loss: 0.2761 - acc: 0.9738 - val_loss: 0.4225 - val_acc: 0.9305Epoch 198/500113s 225ms/step - loss: 0.2750 - acc: 0.9743 - val_loss: 0.4122 - val_acc: 0.9330Epoch 199/500113s 226ms/step - loss: 0.2713 - acc: 0.9751 - val_loss: 0.4222 - val_acc: 0.9323Epoch 200/500113s 226ms/step - loss: 0.2710 - acc: 0.9742 - val_loss: 0.4112 - val_acc: 0.9348Epoch 201/500113s 227ms/step - loss: 0.2696 - acc: 0.9743 - val_loss: 0.4100 - val_acc: 0.9359Epoch 202/500113s 227ms/step - loss: 0.2694 - acc: 0.9729 - val_loss: 0.4060 - val_acc: 0.9333Epoch 203/500113s 226ms/step - loss: 0.2662 - acc: 0.9741 - val_loss: 0.4018 - val_acc: 0.9387Epoch 204/500113s 226ms/step - loss: 0.2695 - acc: 0.9731 - val_loss: 0.3977 - val_acc: 0.9361Epoch 205/500113s 226ms/step - loss: 0.2605 - acc: 0.9757 - val_loss: 0.3963 - val_acc: 0.9366Epoch 206/500113s 226ms/step - loss: 0.2609 - acc: 0.9750 - val_loss: 0.3835 - val_acc: 0.9405Epoch 207/500113s 226ms/step - loss: 0.2599 - acc: 0.9744 - val_loss: 0.3933 - val_acc: 0.9370Epoch 208/500113s 226ms/step - loss: 0.2628 - acc: 0.9737 - val_loss: 0.4033 - val_acc: 0.9340Epoch 209/500113s 226ms/step - loss: 0.2612 - acc: 0.9731 - val_loss: 0.3999 - val_acc: 0.9342Epoch 210/500113s 226ms/step - loss: 0.2619 - acc: 0.9736 - val_loss: 0.3882 - val_acc: 0.9348Epoch 211/500113s 226ms/step - loss: 0.2550 - acc: 0.9753 - val_loss: 0.3986 - val_acc: 0.9367Epoch 212/500113s 226ms/step - loss: 0.2590 - acc: 0.9730 - val_loss: 0.3952 - val_acc: 0.9347Epoch 213/500113s 226ms/step - loss: 0.2566 - acc: 0.9742 - val_loss: 0.3871 - val_acc: 0.9378Epoch 214/500113s 226ms/step - loss: 0.2521 - acc: 0.9751 - val_loss: 0.3802 - val_acc: 0.9393Epoch 215/500113s 226ms/step - loss: 0.2532 - acc: 0.9745 - val_loss: 0.3808 - val_acc: 0.9370Epoch 216/500113s 227ms/step - loss: 0.2480 - acc: 0.9764 - val_loss: 0.3828 - val_acc: 0.9356Epoch 217/500113s 226ms/step - loss: 0.2516 - acc: 0.9742 - val_loss: 0.3902 - val_acc: 0.9355Epoch 218/500113s 227ms/step - loss: 0.2479 - acc: 0.9761 - val_loss: 0.3846 - val_acc: 0.9358Epoch 219/500113s 226ms/step - loss: 0.2514 - acc: 0.9745 - val_loss: 0.3882 - val_acc: 0.9344Epoch 220/500113s 227ms/step - loss: 0.2563 - acc: 0.9715 - val_loss: 0.3814 - val_acc: 0.9362Epoch 221/500113s 226ms/step - loss: 0.2500 - acc: 0.9738 - val_loss: 0.3930 - val_acc: 0.9326Epoch 222/500113s 226ms/step - loss: 0.2479 - acc: 0.9739 - val_loss: 0.3908 - val_acc: 0.9330Epoch 223/500113s 226ms/step - loss: 0.2487 - acc: 0.9733 - val_loss: 0.3893 - val_acc: 0.9334Epoch 224/500113s 226ms/step - loss: 0.2468 - acc: 0.9741 - val_loss: 0.3931 - val_acc: 0.9317Epoch 225/500113s 227ms/step - loss: 0.2467 - acc: 0.9743 - val_loss: 0.3810 - val_acc: 0.9346Epoch 226/500113s 227ms/step - loss: 0.2484 - acc: 0.9735 - val_loss: 0.3867 - val_acc: 0.9356Epoch 227/500113s 226ms/step - loss: 0.2420 - acc: 0.9752 - val_loss: 0.3772 - val_acc: 0.9341Epoch 228/500112s 225ms/step - loss: 0.2455 - acc: 0.9740 - val_loss: 0.3844 - val_acc: 0.9348Epoch 229/500112s 224ms/step - loss: 0.2452 - acc: 0.9729 - val_loss: 0.3765 - val_acc: 0.9355Epoch 230/500112s 224ms/step - loss: 0.2447 - acc: 0.9742 - val_loss: 0.3883 - val_acc: 0.9315Epoch 231/500112s 224ms/step - loss: 0.2451 - acc: 0.9743 - val_loss: 0.3814 - val_acc: 0.9350Epoch 232/500113s 226ms/step - loss: 0.2422 - acc: 0.9745 - val_loss: 0.3960 - val_acc: 0.9344Epoch 233/500113s 226ms/step - loss: 0.2392 - acc: 0.9759 - val_loss: 0.3841 - val_acc: 0.9340Epoch 234/500113s 226ms/step - loss: 0.2401 - acc: 0.9751 - val_loss: 0.3749 - val_acc: 0.9378Epoch 235/500113s 226ms/step - loss: 0.2428 - acc: 0.9733 - val_loss: 0.3801 - val_acc: 0.9339Epoch 236/500113s 226ms/step - loss: 0.2423 - acc: 0.9728 - val_loss: 0.3838 - val_acc: 0.9317Epoch 237/500113s 226ms/step - loss: 0.2447 - acc: 0.9739 - val_loss: 0.3912 - val_acc: 0.9336Epoch 238/500113s 226ms/step - loss: 0.2415 - acc: 0.9734 - val_loss: 0.3828 - val_acc: 0.9316Epoch 239/500113s 225ms/step - loss: 0.2422 - acc: 0.9736 - val_loss: 0.3828 - val_acc: 0.9348Epoch 240/500113s 225ms/step - loss: 0.2409 - acc: 0.9735 - val_loss: 0.3760 - val_acc: 0.9357Epoch 241/500113s 225ms/step - loss: 0.2414 - acc: 0.9738 - val_loss: 0.3782 - val_acc: 0.9333Epoch 242/500113s 225ms/step - loss: 0.2379 - acc: 0.9747 - val_loss: 0.3821 - val_acc: 0.9334Epoch 243/500113s 225ms/step - loss: 0.2370 - acc: 0.9746 - val_loss: 0.3912 - val_acc: 0.9333Epoch 244/500113s 225ms/step - loss: 0.2399 - acc: 0.9730 - val_loss: 0.3748 - val_acc: 0.9351Epoch 245/500112s 225ms/step - loss: 0.2402 - acc: 0.9729 - val_loss: 0.3815 - val_acc: 0.9326Epoch 246/500112s 225ms/step - loss: 0.2405 - acc: 0.9732 - val_loss: 0.3700 - val_acc: 0.9370Epoch 247/500113s 225ms/step - loss: 0.2383 - acc: 0.9743 - val_loss: 0.3789 - val_acc: 0.9350Epoch 248/500113s 226ms/step - loss: 0.2354 - acc: 0.9752 - val_loss: 0.3728 - val_acc: 0.9353Epoch 249/500113s 226ms/step - loss: 0.2341 - acc: 0.9751 - val_loss: 0.3940 - val_acc: 0.9303Epoch 250/500113s 226ms/step - loss: 0.2365 - acc: 0.9742 - val_loss: 0.3741 - val_acc: 0.9354Epoch 251/500113s 226ms/step - loss: 0.2384 - acc: 0.9741 - val_loss: 0.3947 - val_acc: 0.9274Epoch 252/500113s 226ms/step - loss: 0.2348 - acc: 0.9744 - val_loss: 0.3767 - val_acc: 0.9321Epoch 253/500113s 226ms/step - loss: 0.2389 - acc: 0.9733 - val_loss: 0.3813 - val_acc: 0.9313Epoch 254/500113s 226ms/step - loss: 0.2364 - acc: 0.9744 - val_loss: 0.3834 - val_acc: 0.9344Epoch 255/500113s 226ms/step - loss: 0.2392 - acc: 0.9737 - val_loss: 0.3870 - val_acc: 0.9295Epoch 256/500113s 226ms/step - loss: 0.2359 - acc: 0.9737 - val_loss: 0.3754 - val_acc: 0.9334Epoch 257/500113s 227ms/step - loss: 0.2395 - acc: 0.9726 - val_loss: 0.3790 - val_acc: 0.9330Epoch 258/500113s 226ms/step - loss: 0.2328 - acc: 0.9752 - val_loss: 0.3878 - val_acc: 0.9319Epoch 259/500113s 225ms/step - loss: 0.2371 - acc: 0.9728 - val_loss: 0.3820 - val_acc: 0.9336Epoch 260/500112s 225ms/step - loss: 0.2331 - acc: 0.9749 - val_loss: 0.3849 - val_acc: 0.9307Epoch 261/500113s 225ms/step - loss: 0.2357 - acc: 0.9736 - val_loss: 0.3882 - val_acc: 0.9310Epoch 262/500113s 225ms/step - loss: 0.2369 - acc: 0.9735 - val_loss: 0.3761 - val_acc: 0.9344Epoch 263/500113s 225ms/step - loss: 0.2344 - acc: 0.9741 - val_loss: 0.3788 - val_acc: 0.9324Epoch 264/500113s 225ms/step - loss: 0.2360 - acc: 0.9730 - val_loss: 0.3844 - val_acc: 0.9285Epoch 265/500113s 225ms/step - loss: 0.2370 - acc: 0.9737 - val_loss: 0.3862 - val_acc: 0.9309Epoch 266/500113s 226ms/step - loss: 0.2353 - acc: 0.9735 - val_loss: 0.3754 - val_acc: 0.9333Epoch 267/500113s 225ms/step - loss: 0.2355 - acc: 0.9737 - val_loss: 0.3944 - val_acc: 0.9294Epoch 268/500113s 225ms/step - loss: 0.2296 - acc: 0.9758 - val_loss: 0.3946 - val_acc: 0.9307Epoch 269/500112s 225ms/step - loss: 0.2355 - acc: 0.9732 - val_loss: 0.3855 - val_acc: 0.9322Epoch 270/500112s 225ms/step - loss: 0.2351 - acc: 0.9742 - val_loss: 0.3753 - val_acc: 0.9336Epoch 271/500113s 225ms/step - loss: 0.2336 - acc: 0.9745 - val_loss: 0.3856 - val_acc: 0.9281Epoch 272/500113s 225ms/step - loss: 0.2359 - acc: 0.9736 - val_loss: 0.3606 - val_acc: 0.9368Epoch 273/500113s 225ms/step - loss: 0.2301 - acc: 0.9751 - val_loss: 0.3759 - val_acc: 0.9334Epoch 274/500113s 225ms/step - loss: 0.2307 - acc: 0.9751 - val_loss: 0.3776 - val_acc: 0.9322Epoch 275/500113s 225ms/step - loss: 0.2349 - acc: 0.9742 - val_loss: 0.3715 - val_acc: 0.9376Epoch 276/500113s 225ms/step - loss: 0.2393 - acc: 0.9719 - val_loss: 0.3619 - val_acc: 0.9383Epoch 277/500113s 225ms/step - loss: 0.2299 - acc: 0.9750 - val_loss: 0.3697 - val_acc: 0.9340Epoch 278/500112s 225ms/step - loss: 0.2314 - acc: 0.9743 - val_loss: 0.3743 - val_acc: 0.9303Epoch 279/500112s 225ms/step - loss: 0.2325 - acc: 0.9735 - val_loss: 0.3725 - val_acc: 0.9317Epoch 280/500112s 225ms/step - loss: 0.2337 - acc: 0.9738 - val_loss: 0.3929 - val_acc: 0.9284Epoch 281/500113s 225ms/step - loss: 0.2311 - acc: 0.9751 - val_loss: 0.3826 - val_acc: 0.9303Epoch 282/500113s 225ms/step - loss: 0.2316 - acc: 0.9753 - val_loss: 0.3922 - val_acc: 0.9295Epoch 283/500113s 225ms/step - loss: 0.2321 - acc: 0.9741 - val_loss: 0.3757 - val_acc: 0.9313Epoch 284/500112s 225ms/step - loss: 0.2323 - acc: 0.9744 - val_loss: 0.3874 - val_acc: 0.9296Epoch 285/500112s 225ms/step - loss: 0.2318 - acc: 0.9752 - val_loss: 0.4014 - val_acc: 0.9278Epoch 286/500112s 225ms/step - loss: 0.2314 - acc: 0.9744 - val_loss: 0.3838 - val_acc: 0.9332Epoch 287/500112s 225ms/step - loss: 0.2324 - acc: 0.9741 - val_loss: 0.3912 - val_acc: 0.9284Epoch 288/500112s 225ms/step - loss: 0.2325 - acc: 0.9735 - val_loss: 0.3842 - val_acc: 0.9317Epoch 289/500113s 225ms/step - loss: 0.2285 - acc: 0.9760 - val_loss: 0.3814 - val_acc: 0.9328Epoch 290/500113s 225ms/step - loss: 0.2286 - acc: 0.9759 - val_loss: 0.3796 - val_acc: 0.9326Epoch 291/500112s 225ms/step - loss: 0.2306 - acc: 0.9752 - val_loss: 0.3871 - val_acc: 0.9281Epoch 292/500112s 225ms/step - loss: 0.2304 - acc: 0.9742 - val_loss: 0.3822 - val_acc: 0.9302Epoch 293/500112s 225ms/step - loss: 0.2300 - acc: 0.9742 - val_loss: 0.3958 - val_acc: 0.9304Epoch 294/500112s 225ms/step - loss: 0.2308 - acc: 0.9740 - val_loss: 0.3838 - val_acc: 0.9301Epoch 295/500113s 225ms/step - loss: 0.2336 - acc: 0.9721 - val_loss: 0.3784 - val_acc: 0.9347Epoch 296/500113s 225ms/step - loss: 0.2316 - acc: 0.9743 - val_loss: 0.3737 - val_acc: 0.9308Epoch 297/500113s 225ms/step - loss: 0.2273 - acc: 0.9759 - val_loss: 0.3791 - val_acc: 0.9345Epoch 298/500113s 225ms/step - loss: 0.2303 - acc: 0.9750 - val_loss: 0.3935 - val_acc: 0.9289Epoch 299/500112s 225ms/step - loss: 0.2291 - acc: 0.9750 - val_loss: 0.3793 - val_acc: 0.9300Epoch 300/500113s 225ms/step - loss: 0.2299 - acc: 0.9746 - val_loss: 0.3846 - val_acc: 0.9306Epoch 301/500lr changed to 0.0009999999776482583112s 225ms/step - loss: 0.2081 - acc: 0.9831 - val_loss: 0.3536 - val_acc: 0.9390Epoch 302/500113s 226ms/step - loss: 0.1928 - acc: 0.9890 - val_loss: 0.3467 - val_acc: 0.9398Epoch 303/500113s 226ms/step - loss: 0.1888 - acc: 0.9899 - val_loss: 0.3437 - val_acc: 0.9412Epoch 304/500113s 226ms/step - loss: 0.1863 - acc: 0.9907 - val_loss: 0.3394 - val_acc: 0.9441Epoch 305/500113s 226ms/step - loss: 0.1840 - acc: 0.9912 - val_loss: 0.3429 - val_acc: 0.9433Epoch 306/500113s 227ms/step - loss: 0.1829 - acc: 0.9915 - val_loss: 0.3398 - val_acc: 0.9446Epoch 307/500113s 226ms/step - loss: 0.1798 - acc: 0.9928 - val_loss: 0.3412 - val_acc: 0.9450Epoch 308/500113s 226ms/step - loss: 0.1800 - acc: 0.9920 - val_loss: 0.3410 - val_acc: 0.9457Epoch 309/500113s 227ms/step - loss: 0.1785 - acc: 0.9929 - val_loss: 0.3397 - val_acc: 0.9451Epoch 310/500113s 226ms/step - loss: 0.1784 - acc: 0.9926 - val_loss: 0.3417 - val_acc: 0.9449Epoch 311/500113s 226ms/step - loss: 0.1759 - acc: 0.9935 - val_loss: 0.3421 - val_acc: 0.9452Epoch 312/500113s 226ms/step - loss: 0.1747 - acc: 0.9942 - val_loss: 0.3403 - val_acc: 0.9456Epoch 313/500113s 227ms/step - loss: 0.1750 - acc: 0.9936 - val_loss: 0.3413 - val_acc: 0.9442Epoch 314/500113s 227ms/step - loss: 0.1745 - acc: 0.9941 - val_loss: 0.3404 - val_acc: 0.9459Epoch 315/500113s 226ms/step - loss: 0.1714 - acc: 0.9948 - val_loss: 0.3407 - val_acc: 0.9466Epoch 316/500113s 227ms/step - loss: 0.1709 - acc: 0.9949 - val_loss: 0.3393 - val_acc: 0.9478Epoch 317/500113s 226ms/step - loss: 0.1714 - acc: 0.9944 - val_loss: 0.3402 - val_acc: 0.9464Epoch 318/500113s 227ms/step - loss: 0.1709 - acc: 0.9946 - val_loss: 0.3412 - val_acc: 0.9453Epoch 319/500113s 227ms/step - loss: 0.1700 - acc: 0.9949 - val_loss: 0.3433 - val_acc: 0.9454Epoch 320/500113s 227ms/step - loss: 0.1697 - acc: 0.9948 - val_loss: 0.3413 - val_acc: 0.9452Epoch 321/500113s 226ms/step - loss: 0.1689 - acc: 0.9948 - val_loss: 0.3382 - val_acc: 0.9460Epoch 322/500113s 226ms/step - loss: 0.1680 - acc: 0.9951 - val_loss: 0.3406 - val_acc: 0.9461Epoch 323/500113s 226ms/step - loss: 0.1674 - acc: 0.9953 - val_loss: 0.3395 - val_acc: 0.9467Epoch 324/500113s 225ms/step - loss: 0.1683 - acc: 0.9947 - val_loss: 0.3424 - val_acc: 0.9473Epoch 325/500112s 225ms/step - loss: 0.1659 - acc: 0.9957 - val_loss: 0.3431 - val_acc: 0.9458Epoch 326/500113s 225ms/step - loss: 0.1666 - acc: 0.9951 - val_loss: 0.3427 - val_acc: 0.9461Epoch 327/500113s 225ms/step - loss: 0.1655 - acc: 0.9955 - val_loss: 0.3434 - val_acc: 0.9454Epoch 328/500113s 225ms/step - loss: 0.1666 - acc: 0.9948 - val_loss: 0.3415 - val_acc: 0.9466Epoch 329/500113s 226ms/step - loss: 0.1660 - acc: 0.9955 - val_loss: 0.3420 - val_acc: 0.9461Epoch 330/500113s 225ms/step - loss: 0.1655 - acc: 0.9954 - val_loss: 0.3414 - val_acc: 0.9461Epoch 331/500113s 225ms/step - loss: 0.1654 - acc: 0.9951 - val_loss: 0.3424 - val_acc: 0.9461Epoch 332/500113s 225ms/step - loss: 0.1638 - acc: 0.9959 - val_loss: 0.3433 - val_acc: 0.9455Epoch 333/500112s 225ms/step - loss: 0.1635 - acc: 0.9958 - val_loss: 0.3471 - val_acc: 0.9449Epoch 334/500113s 225ms/step - loss: 0.1641 - acc: 0.9955 - val_loss: 0.3459 - val_acc: 0.9453Epoch 335/500112s 225ms/step - loss: 0.1625 - acc: 0.9960 - val_loss: 0.3452 - val_acc: 0.9448Epoch 336/500113s 225ms/step - loss: 0.1623 - acc: 0.9957 - val_loss: 0.3459 - val_acc: 0.9452Epoch 337/500113s 226ms/step - loss: 0.1623 - acc: 0.9958 - val_loss: 0.3450 - val_acc: 0.9455Epoch 338/500113s 225ms/step - loss: 0.1608 - acc: 0.9962 - val_loss: 0.3457 - val_acc: 0.9459Epoch 339/500113s 225ms/step - loss: 0.1609 - acc: 0.9959 - val_loss: 0.3453 - val_acc: 0.9461Epoch 340/500112s 225ms/step - loss: 0.1609 - acc: 0.9958 - val_loss: 0.3462 - val_acc: 0.9444Epoch 341/500113s 225ms/step - loss: 0.1601 - acc: 0.9961 - val_loss: 0.3452 - val_acc: 0.9470Epoch 342/500113s 225ms/step - loss: 0.1603 - acc: 0.9959 - val_loss: 0.3451 - val_acc: 0.9459Epoch 343/500113s 225ms/step - loss: 0.1602 - acc: 0.9961 - val_loss: 0.3421 - val_acc: 0.9462Epoch 344/500113s 225ms/step - loss: 0.1607 - acc: 0.9959 - val_loss: 0.3442 - val_acc: 0.9456Epoch 345/500113s 226ms/step - loss: 0.1589 - acc: 0.9964 - val_loss: 0.3431 - val_acc: 0.9461Epoch 346/500113s 226ms/step - loss: 0.1588 - acc: 0.9962 - val_loss: 0.3445 - val_acc: 0.9461Epoch 347/500113s 225ms/step - loss: 0.1585 - acc: 0.9960 - val_loss: 0.3415 - val_acc: 0.9452Epoch 348/500113s 225ms/step - loss: 0.1569 - acc: 0.9967 - val_loss: 0.3407 - val_acc: 0.9459Epoch 349/500112s 225ms/step - loss: 0.1574 - acc: 0.9966 - val_loss: 0.3378 - val_acc: 0.9473Epoch 350/500113s 226ms/step - loss: 0.1580 - acc: 0.9960 - val_loss: 0.3403 - val_acc: 0.9466Epoch 351/500113s 226ms/step - loss: 0.1577 - acc: 0.9961 - val_loss: 0.3405 - val_acc: 0.9461Epoch 352/500113s 226ms/step - loss: 0.1560 - acc: 0.9968 - val_loss: 0.3381 - val_acc: 0.9478Epoch 353/500113s 226ms/step - loss: 0.1569 - acc: 0.9962 - val_loss: 0.3405 - val_acc: 0.9467Epoch 354/500113s 226ms/step - loss: 0.1564 - acc: 0.9964 - val_loss: 0.3428 - val_acc: 0.9446Epoch 355/500113s 226ms/step - loss: 0.1557 - acc: 0.9967 - val_loss: 0.3414 - val_acc: 0.9453Epoch 356/500113s 226ms/step - loss: 0.1552 - acc: 0.9965 - val_loss: 0.3409 - val_acc: 0.9451Epoch 357/500113s 226ms/step - loss: 0.1557 - acc: 0.9964 - val_loss: 0.3384 - val_acc: 0.9463Epoch 358/500113s 226ms/step - loss: 0.1553 - acc: 0.9965 - val_loss: 0.3404 - val_acc: 0.9476Epoch 359/500113s 226ms/step - loss: 0.1545 - acc: 0.9962 - val_loss: 0.3439 - val_acc: 0.9462Epoch 360/500113s 226ms/step - loss: 0.1552 - acc: 0.9963 - val_loss: 0.3407 - val_acc: 0.9468Epoch 361/500113s 227ms/step - loss: 0.1544 - acc: 0.9966 - val_loss: 0.3405 - val_acc: 0.9462Epoch 362/500113s 226ms/step - loss: 0.1538 - acc: 0.9968 - val_loss: 0.3421 - val_acc: 0.9458Epoch 363/500113s 227ms/step - loss: 0.1537 - acc: 0.9964 - val_loss: 0.3379 - val_acc: 0.9475Epoch 364/500113s 226ms/step - loss: 0.1534 - acc: 0.9964 - val_loss: 0.3379 - val_acc: 0.9464Epoch 365/500113s 226ms/step - loss: 0.1518 - acc: 0.9970 - val_loss: 0.3386 - val_acc: 0.9465Epoch 366/500113s 226ms/step - loss: 0.1524 - acc: 0.9968 - val_loss: 0.3393 - val_acc: 0.9477Epoch 367/500113s 226ms/step - loss: 0.1517 - acc: 0.9969 - val_loss: 0.3394 - val_acc: 0.9469Epoch 368/500113s 226ms/step - loss: 0.1513 - acc: 0.9969 - val_loss: 0.3384 - val_acc: 0.9478Epoch 369/500113s 227ms/step - loss: 0.1525 - acc: 0.9961 - val_loss: 0.3363 - val_acc: 0.9481Epoch 370/500113s 227ms/step - loss: 0.1518 - acc: 0.9962 - val_loss: 0.3387 - val_acc: 0.9476Epoch 371/500113s 226ms/step - loss: 0.1508 - acc: 0.9967 - val_loss: 0.3377 - val_acc: 0.9464Epoch 372/500113s 226ms/step - loss: 0.1504 - acc: 0.9968 - val_loss: 0.3354 - val_acc: 0.9480Epoch 373/500113s 226ms/step - loss: 0.1501 - acc: 0.9970 - val_loss: 0.3368 - val_acc: 0.9482Epoch 374/500113s 226ms/step - loss: 0.1507 - acc: 0.9962 - val_loss: 0.3427 - val_acc: 0.9460Epoch 375/500113s 226ms/step - loss: 0.1501 - acc: 0.9966 - val_loss: 0.3393 - val_acc: 0.9467Epoch 376/500113s 226ms/step - loss: 0.1502 - acc: 0.9968 - val_loss: 0.3370 - val_acc: 0.9473Epoch 377/500113s 226ms/step - loss: 0.1502 - acc: 0.9963 - val_loss: 0.3394 - val_acc: 0.9483Epoch 378/500113s 227ms/step - loss: 0.1493 - acc: 0.9968 - val_loss: 0.3388 - val_acc: 0.9462Epoch 379/500113s 226ms/step - loss: 0.1488 - acc: 0.9967 - val_loss: 0.3359 - val_acc: 0.9469Epoch 380/500113s 226ms/step - loss: 0.1480 - acc: 0.9971 - val_loss: 0.3339 - val_acc: 0.9491Epoch 381/500113s 226ms/step - loss: 0.1490 - acc: 0.9969 - val_loss: 0.3339 - val_acc: 0.9491Epoch 382/500113s 226ms/step - loss: 0.1480 - acc: 0.9967 - val_loss: 0.3327 - val_acc: 0.9488Epoch 383/500113s 226ms/step - loss: 0.1471 - acc: 0.9970 - val_loss: 0.3320 - val_acc: 0.9482Epoch 384/500113s 226ms/step - loss: 0.1464 - acc: 0.9972 - val_loss: 0.3324 - val_acc: 0.9473Epoch 385/500113s 226ms/step - loss: 0.1476 - acc: 0.9967 - val_loss: 0.3372 - val_acc: 0.9466Epoch 386/500113s 226ms/step - loss: 0.1474 - acc: 0.9966 - val_loss: 0.3369 - val_acc: 0.9467Epoch 387/500113s 227ms/step - loss: 0.1478 - acc: 0.9964 - val_loss: 0.3360 - val_acc: 0.9486Epoch 388/500113s 227ms/step - loss: 0.1474 - acc: 0.9967 - val_loss: 0.3312 - val_acc: 0.9481Epoch 389/500113s 226ms/step - loss: 0.1460 - acc: 0.9969 - val_loss: 0.3304 - val_acc: 0.9486Epoch 390/500113s 226ms/step - loss: 0.1448 - acc: 0.9974 - val_loss: 0.3322 - val_acc: 0.9502Epoch 391/500113s 226ms/step - loss: 0.1456 - acc: 0.9971 - val_loss: 0.3331 - val_acc: 0.9494Epoch 392/500113s 227ms/step - loss: 0.1455 - acc: 0.9970 - val_loss: 0.3367 - val_acc: 0.9477Epoch 393/500113s 227ms/step - loss: 0.1452 - acc: 0.9968 - val_loss: 0.3359 - val_acc: 0.9479Epoch 394/500113s 226ms/step - loss: 0.1446 - acc: 0.9971 - val_loss: 0.3331 - val_acc: 0.9484Epoch 395/500113s 226ms/step - loss: 0.1455 - acc: 0.9965 - val_loss: 0.3309 - val_acc: 0.9512Epoch 396/500113s 227ms/step - loss: 0.1451 - acc: 0.9966 - val_loss: 0.3285 - val_acc: 0.9498Epoch 397/500113s 226ms/step - loss: 0.1439 - acc: 0.9970 - val_loss: 0.3292 - val_acc: 0.9496Epoch 398/500113s 226ms/step - loss: 0.1436 - acc: 0.9971 - val_loss: 0.3320 - val_acc: 0.9488Epoch 399/500113s 226ms/step - loss: 0.1436 - acc: 0.9969 - val_loss: 0.3312 - val_acc: 0.9491Epoch 400/500113s 226ms/step - loss: 0.1447 - acc: 0.9967 - val_loss: 0.3280 - val_acc: 0.9486Epoch 401/500113s 225ms/step - loss: 0.1435 - acc: 0.9969 - val_loss: 0.3281 - val_acc: 0.9489Epoch 402/500113s 225ms/step - loss: 0.1421 - acc: 0.9973 - val_loss: 0.3280 - val_acc: 0.9483Epoch 403/500113s 226ms/step - loss: 0.1426 - acc: 0.9970 - val_loss: 0.3281 - val_acc: 0.9478Epoch 404/500113s 227ms/step - loss: 0.1427 - acc: 0.9969 - val_loss: 0.3269 - val_acc: 0.9484Epoch 405/500113s 226ms/step - loss: 0.1425 - acc: 0.9969 - val_loss: 0.3267 - val_acc: 0.9495Epoch 406/500113s 226ms/step - loss: 0.1417 - acc: 0.9971 - val_loss: 0.3263 - val_acc: 0.9483Epoch 407/500113s 226ms/step - loss: 0.1422 - acc: 0.9971 - val_loss: 0.3268 - val_acc: 0.9496Epoch 408/500113s 226ms/step - loss: 0.1413 - acc: 0.9971 - val_loss: 0.3270 - val_acc: 0.9487Epoch 409/500113s 226ms/step - loss: 0.1417 - acc: 0.9970 - val_loss: 0.3246 - val_acc: 0.9499Epoch 410/500113s 226ms/step - loss: 0.1412 - acc: 0.9969 - val_loss: 0.3243 - val_acc: 0.9488Epoch 411/500113s 226ms/step - loss: 0.1405 - acc: 0.9973 - val_loss: 0.3263 - val_acc: 0.9503Epoch 412/500113s 226ms/step - loss: 0.1406 - acc: 0.9971 - val_loss: 0.3222 - val_acc: 0.9497Epoch 413/500113s 226ms/step - loss: 0.1412 - acc: 0.9968 - val_loss: 0.3249 - val_acc: 0.9497Epoch 414/500113s 226ms/step - loss: 0.1401 - acc: 0.9971 - val_loss: 0.3257 - val_acc: 0.9487Epoch 415/500113s 226ms/step - loss: 0.1394 - acc: 0.9973 - val_loss: 0.3263 - val_acc: 0.9492Epoch 416/500113s 226ms/step - loss: 0.1394 - acc: 0.9973 - val_loss: 0.3279 - val_acc: 0.9470Epoch 417/500113s 227ms/step - loss: 0.1393 - acc: 0.9973 - val_loss: 0.3298 - val_acc: 0.9473Epoch 418/500113s 227ms/step - loss: 0.1387 - acc: 0.9973 - val_loss: 0.3277 - val_acc: 0.9478Epoch 419/500113s 227ms/step - loss: 0.1383 - acc: 0.9970 - val_loss: 0.3247 - val_acc: 0.9482Epoch 420/500113s 226ms/step - loss: 0.1390 - acc: 0.9971 - val_loss: 0.3288 - val_acc: 0.9465Epoch 421/500113s 226ms/step - loss: 0.1374 - acc: 0.9976 - val_loss: 0.3266 - val_acc: 0.9480Epoch 422/500113s 226ms/step - loss: 0.1385 - acc: 0.9972 - val_loss: 0.3261 - val_acc: 0.9489Epoch 423/500113s 226ms/step - loss: 0.1382 - acc: 0.9971 - val_loss: 0.3274 - val_acc: 0.9479Epoch 424/500113s 226ms/step - loss: 0.1377 - acc: 0.9973 - val_loss: 0.3287 - val_acc: 0.9478Epoch 425/500113s 226ms/step - loss: 0.1374 - acc: 0.9973 - val_loss: 0.3291 - val_acc: 0.9484Epoch 426/500113s 226ms/step - loss: 0.1367 - acc: 0.9977 - val_loss: 0.3282 - val_acc: 0.9483Epoch 427/500113s 226ms/step - loss: 0.1365 - acc: 0.9974 - val_loss: 0.3260 - val_acc: 0.9497Epoch 428/500113s 226ms/step - loss: 0.1366 - acc: 0.9973 - val_loss: 0.3257 - val_acc: 0.9498Epoch 429/500113s 225ms/step - loss: 0.1353 - acc: 0.9978 - val_loss: 0.3262 - val_acc: 0.9489Epoch 430/500112s 225ms/step - loss: 0.1365 - acc: 0.9972 - val_loss: 0.3315 - val_acc: 0.9463Epoch 431/500113s 225ms/step - loss: 0.1364 - acc: 0.9976 - val_loss: 0.3292 - val_acc: 0.9476Epoch 432/500113s 225ms/step - loss: 0.1356 - acc: 0.9973 - val_loss: 0.3270 - val_acc: 0.9489Epoch 433/500113s 225ms/step - loss: 0.1348 - acc: 0.9976 - val_loss: 0.3246 - val_acc: 0.9495Epoch 434/500113s 225ms/step - loss: 0.1350 - acc: 0.9975 - val_loss: 0.3265 - val_acc: 0.9479Epoch 435/500113s 225ms/step - loss: 0.1360 - acc: 0.9969 - val_loss: 0.3319 - val_acc: 0.9479Epoch 436/500113s 225ms/step - loss: 0.1344 - acc: 0.9975 - val_loss: 0.3297 - val_acc: 0.9472Epoch 437/500112s 225ms/step - loss: 0.1351 - acc: 0.9969 - val_loss: 0.3296 - val_acc: 0.9484Epoch 438/500112s 225ms/step - loss: 0.1349 - acc: 0.9972 - val_loss: 0.3268 - val_acc: 0.9483Epoch 439/500113s 225ms/step - loss: 0.1337 - acc: 0.9974 - val_loss: 0.3236 - val_acc: 0.9485Epoch 440/500113s 226ms/step - loss: 0.1335 - acc: 0.9978 - val_loss: 0.3239 - val_acc: 0.9473Epoch 441/500113s 226ms/step - loss: 0.1337 - acc: 0.9975 - val_loss: 0.3215 - val_acc: 0.9489Epoch 442/500113s 226ms/step - loss: 0.1327 - acc: 0.9976 - val_loss: 0.3201 - val_acc: 0.9497Epoch 443/500113s 226ms/step - loss: 0.1338 - acc: 0.9973 - val_loss: 0.3210 - val_acc: 0.9501Epoch 444/500113s 227ms/step - loss: 0.1335 - acc: 0.9975 - val_loss: 0.3232 - val_acc: 0.9487Epoch 445/500113s 226ms/step - loss: 0.1325 - acc: 0.9974 - val_loss: 0.3232 - val_acc: 0.9487Epoch 446/500113s 226ms/step - loss: 0.1344 - acc: 0.9968 - val_loss: 0.3225 - val_acc: 0.9485Epoch 447/500113s 226ms/step - loss: 0.1317 - acc: 0.9978 - val_loss: 0.3251 - val_acc: 0.9471Epoch 448/500113s 226ms/step - loss: 0.1331 - acc: 0.9969 - val_loss: 0.3241 - val_acc: 0.9493Epoch 449/500113s 226ms/step - loss: 0.1322 - acc: 0.9974 - val_loss: 0.3257 - val_acc: 0.9484Epoch 450/500113s 226ms/step - loss: 0.1313 - acc: 0.9978 - val_loss: 0.3216 - val_acc: 0.9492Epoch 451/500lr changed to 9.999999310821295e-05113s 226ms/step - loss: 0.1308 - acc: 0.9979 - val_loss: 0.3216 - val_acc: 0.9498Epoch 452/500113s 226ms/step - loss: 0.1318 - acc: 0.9971 - val_loss: 0.3211 - val_acc: 0.9492Epoch 453/500112s 225ms/step - loss: 0.1308 - acc: 0.9976 - val_loss: 0.3210 - val_acc: 0.9497Epoch 454/500113s 225ms/step - loss: 0.1297 - acc: 0.9981 - val_loss: 0.3207 - val_acc: 0.9494Epoch 455/500113s 225ms/step - loss: 0.1309 - acc: 0.9978 - val_loss: 0.3204 - val_acc: 0.9493Epoch 456/500113s 226ms/step - loss: 0.1312 - acc: 0.9978 - val_loss: 0.3202 - val_acc: 0.9494Epoch 457/500113s 225ms/step - loss: 0.1300 - acc: 0.9979 - val_loss: 0.3200 - val_acc: 0.9496Epoch 458/500113s 226ms/step - loss: 0.1307 - acc: 0.9979 - val_loss: 0.3196 - val_acc: 0.9497Epoch 459/500113s 226ms/step - loss: 0.1303 - acc: 0.9978 - val_loss: 0.3195 - val_acc: 0.9505Epoch 460/500112s 225ms/step - loss: 0.1305 - acc: 0.9976 - val_loss: 0.3195 - val_acc: 0.9499Epoch 461/500113s 225ms/step - loss: 0.1301 - acc: 0.9979 - val_loss: 0.3194 - val_acc: 0.9501Epoch 462/500112s 225ms/step - loss: 0.1303 - acc: 0.9978 - val_loss: 0.3187 - val_acc: 0.9498Epoch 463/500113s 226ms/step - loss: 0.1306 - acc: 0.9977 - val_loss: 0.3191 - val_acc: 0.9503Epoch 464/500113s 225ms/step - loss: 0.1299 - acc: 0.9978 - val_loss: 0.3188 - val_acc: 0.9506Epoch 465/500113s 225ms/step - loss: 0.1302 - acc: 0.9978 - val_loss: 0.3189 - val_acc: 0.9501Epoch 466/500113s 227ms/step - loss: 0.1300 - acc: 0.9980 - val_loss: 0.3187 - val_acc: 0.9499Epoch 467/500113s 226ms/step - loss: 0.1302 - acc: 0.9980 - val_loss: 0.3187 - val_acc: 0.9502Epoch 468/500113s 225ms/step - loss: 0.1299 - acc: 0.9979 - val_loss: 0.3184 - val_acc: 0.9501Epoch 469/500113s 225ms/step - loss: 0.1291 - acc: 0.9982 - val_loss: 0.3185 - val_acc: 0.9503Epoch 470/500113s 225ms/step - loss: 0.1298 - acc: 0.9980 - val_loss: 0.3182 - val_acc: 0.9501Epoch 471/500113s 225ms/step - loss: 0.1297 - acc: 0.9979 - val_loss: 0.3181 - val_acc: 0.9503Epoch 472/500113s 225ms/step - loss: 0.1300 - acc: 0.9979 - val_loss: 0.3184 - val_acc: 0.9503Epoch 473/500113s 225ms/step - loss: 0.1299 - acc: 0.9980 - val_loss: 0.3184 - val_acc: 0.9505Epoch 474/500113s 225ms/step - loss: 0.1306 - acc: 0.9976 - val_loss: 0.3180 - val_acc: 0.9506Epoch 475/500112s 225ms/step - loss: 0.1302 - acc: 0.9978 - val_loss: 0.3178 - val_acc: 0.9504Epoch 476/500113s 225ms/step - loss: 0.1297 - acc: 0.9977 - val_loss: 0.3177 - val_acc: 0.9503Epoch 477/500113s 225ms/step - loss: 0.1295 - acc: 0.9980 - val_loss: 0.3173 - val_acc: 0.9501Epoch 478/500112s 225ms/step - loss: 0.1297 - acc: 0.9981 - val_loss: 0.3172 - val_acc: 0.9501Epoch 479/500112s 225ms/step - loss: 0.1299 - acc: 0.9978 - val_loss: 0.3171 - val_acc: 0.9508Epoch 480/500113s 225ms/step - loss: 0.1291 - acc: 0.9980 - val_loss: 0.3174 - val_acc: 0.9506Epoch 481/500113s 225ms/step - loss: 0.1297 - acc: 0.9981 - val_loss: 0.3177 - val_acc: 0.9499Epoch 482/500113s 226ms/step - loss: 0.1295 - acc: 0.9980 - val_loss: 0.3178 - val_acc: 0.9506Epoch 483/500113s 225ms/step - loss: 0.1298 - acc: 0.9977 - val_loss: 0.3176 - val_acc: 0.9508Epoch 484/500113s 225ms/step - loss: 0.1295 - acc: 0.9977 - val_loss: 0.3181 - val_acc: 0.9503Epoch 485/500113s 225ms/step - loss: 0.1286 - acc: 0.9984 - val_loss: 0.3184 - val_acc: 0.9502Epoch 486/500112s 225ms/step - loss: 0.1290 - acc: 0.9981 - val_loss: 0.3175 - val_acc: 0.9508Epoch 487/500112s 225ms/step - loss: 0.1292 - acc: 0.9980 - val_loss: 0.3177 - val_acc: 0.9505Epoch 488/500113s 225ms/step - loss: 0.1292 - acc: 0.9982 - val_loss: 0.3175 - val_acc: 0.9503Epoch 489/500113s 226ms/step - loss: 0.1300 - acc: 0.9978 - val_loss: 0.3176 - val_acc: 0.9503Epoch 490/500113s 225ms/step - loss: 0.1293 - acc: 0.9979 - val_loss: 0.3176 - val_acc: 0.9505Epoch 491/500113s 225ms/step - loss: 0.1289 - acc: 0.9981 - val_loss: 0.3177 - val_acc: 0.9501Epoch 492/500113s 225ms/step - loss: 0.1293 - acc: 0.9982 - val_loss: 0.3174 - val_acc: 0.9504Epoch 493/500112s 225ms/step - loss: 0.1285 - acc: 0.9983 - val_loss: 0.3178 - val_acc: 0.9503Epoch 494/500112s 225ms/step - loss: 0.1297 - acc: 0.9979 - val_loss: 0.3178 - val_acc: 0.9501Epoch 495/500113s 225ms/step - loss: 0.1290 - acc: 0.9979 - val_loss: 0.3174 - val_acc: 0.9505Epoch 496/500113s 225ms/step - loss: 0.1292 - acc: 0.9979 - val_loss: 0.3171 - val_acc: 0.9508Epoch 497/500113s 225ms/step - loss: 0.1291 - acc: 0.9982 - val_loss: 0.3176 - val_acc: 0.9506Epoch 498/500113s 226ms/step - loss: 0.1285 - acc: 0.9982 - val_loss: 0.3180 - val_acc: 0.9505Epoch 499/500113s 225ms/step - loss: 0.1298 - acc: 0.9978 - val_loss: 0.3183 - val_acc: 0.9500Epoch 500/500113s 225ms/step - loss: 0.1290 - acc: 0.9981 - val_loss: 0.3182 - val_acc: 0.9512Train loss: 0.1252169744670391Train accuracy: 0.9990800008773804Test loss: 0.31817472279071807Test accuracy: 0.9512000060081482
准确率到了95.12%,看来增加深度还是管用的。相较于调参记录20的94.17%高了接近1%。
如果深度再翻倍会怎么样呢?
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
https://ieeexplore.ieee.org/document/8998530
作者的哈工大主页:
Http://homepage.hit.edu.cn/zhaominghang
————————————————
版权声明:本文为CSDN博主「dangqing1988」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/dangqing1988/article/details/106157819
--结束END--
本文标题: 深度残差网络+自适应参数化ReLU激活函数(调参记录21)Cifar10~95.12%
本文链接: https://lsjlt.com/news/243969.html(转载时请注明来源链接)
有问题或投稿请发送至: 邮箱/279061341@qq.com QQ/279061341
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
2024-05-24
回答
回答
回答
回答
回答
回答
回答
回答
回答
回答
0