網(wǎng)上有很多關(guān)于pos機(jī)上網(wǎng)參數(shù),深度殘差網(wǎng)絡(luò)+自適應(yīng)參數(shù)化ReLU的知識(shí)，也有很多人為大家解答關(guān)于pos機(jī)上網(wǎng)參數(shù)的問(wèn)題，今天pos機(jī)之家(www.afbey.com)為大家整理了關(guān)于這方面的知識(shí)，讓我們一起來(lái)看下吧!

本文目錄一覽：

1、pos機(jī)上網(wǎng)參數(shù)

2、POS機(jī)的EMV參數(shù)下載什么意思？

pos機(jī)上網(wǎng)參數(shù)

本文在調(diào)參記錄23的基礎(chǔ)上，增加卷積核的個(gè)數(shù)，最少是64個(gè)，最多是256個(gè)，繼續(xù)測(cè)試深度殘差網(wǎng)絡(luò)+自適應(yīng)參數(shù)化ReLU激活函數(shù)在cifar10數(shù)據(jù)集上的效果。

自適應(yīng)參數(shù)化ReLU激活函數(shù)被放在了殘差模塊的第二個(gè)卷積層之后，它的基本原理如下：

自適應(yīng)參數(shù)化ReLU激活函數(shù)

Keras程序：

#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Tue Apr 14 04:17:45 2020Implemented using TensorFlow 1.0.1 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(64, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(inputs)net = residual_block(net, 20, 64, downsample=False)net = residual_block(net, 1, 128, downsample=True)net = residual_block(net, 19, 128, downsample=False)net = residual_block(net, 1, 256, downsample=True)net = residual_block(net, 19, 256, 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="360px",height="auto" />

實(shí)驗(yàn)結(jié)果：

Using TensorFlow backend.x_train shape: (50000, 32, 32, 3)50000 train samples10000 test samplesEpoch 1/500281s 562ms/step - loss: 9.6683 - acc: 0.2858 - val_loss: 8.5491 - val_acc: 0.4224Epoch 2/500236s 471ms/step - loss: 7.8652 - acc: 0.4406 - val_loss: 7.0180 - val_acc: 0.5270Epoch 3/500235s 471ms/step - loss: 6.5241 - acc: 0.5264 - val_loss: 5.7927 - val_acc: 0.6159Epoch 4/500235s 471ms/step - loss: 5.4217 - acc: 0.6013 - val_loss: 4.7898 - val_acc: 0.6878Epoch 5/500235s 471ms/step - loss: 4.5434 - acc: 0.6542 - val_loss: 4.0362 - val_acc: 0.7256Epoch 6/500235s 470ms/step - loss: 3.8297 - acc: 0.6947 - val_loss: 3.3928 - val_acc: 0.7654Epoch 7/500235s 471ms/step - loss: 3.2680 - acc: 0.7257 - val_loss: 2.8972 - val_acc: 0.7805Epoch 8/500236s 471ms/step - loss: 2.8023 - acc: 0.7493 - val_loss: 2.4718 - val_acc: 0.8117Epoch 9/500235s 471ms/step - loss: 2.4351 - acc: 0.7652 - val_loss: 2.1518 - val_acc: 0.8216Epoch 10/500235s 470ms/step - loss: 2.1298 - acc: 0.7822 - val_loss: 1.8664 - val_acc: 0.8355Epoch 11/500235s 470ms/step - loss: 1.8768 - acc: 0.7961 - val_loss: 1.6576 - val_acc: 0.8407Epoch 12/500235s 470ms/step - loss: 1.6745 - acc: 0.8071 - val_loss: 1.4888 - val_acc: 0.8456Epoch 13/500235s 471ms/step - loss: 1.5155 - acc: 0.8139 - val_loss: 1.3255 - val_acc: 0.8598Epoch 14/500235s 471ms/step - loss: 1.3782 - acc: 0.8230 - val_loss: 1.2249 - val_acc: 0.8616Epoch 15/500235s 471ms/step - loss: 1.2630 - acc: 0.8293 - val_loss: 1.1236 - val_acc: 0.8655Epoch 16/500235s 471ms/step - loss: 1.1829 - acc: 0.8342 - val_loss: 1.0384 - val_acc: 0.8768Epoch 17/500235s 470ms/step - loss: 1.1094 - acc: 0.8389 - val_loss: 0.9748 - val_acc: 0.8752Epoch 18/500236s 471ms/step - loss: 1.0510 - acc: 0.8448 - val_loss: 0.9660 - val_acc: 0.8697Epoch 19/500235s 471ms/step - loss: 1.0037 - acc: 0.8472 - val_loss: 0.9055 - val_acc: 0.8760Epoch 20/500235s 471ms/step - loss: 0.9615 - acc: 0.8520 - val_loss: 0.8935 - val_acc: 0.8711Epoch 21/500235s 471ms/step - loss: 0.9345 - acc: 0.8545 - val_loss: 0.8621 - val_acc: 0.8743Epoch 22/500235s 470ms/step - loss: 0.9044 - acc: 0.8589 - val_loss: 0.8440 - val_acc: 0.8776Epoch 23/500235s 470ms/step - loss: 0.8816 - acc: 0.8625 - val_loss: 0.8310 - val_acc: 0.8792Epoch 24/500235s 470ms/step - loss: 0.8640 - acc: 0.8659 - val_loss: 0.8157 - val_acc: 0.8820Epoch 25/500235s 470ms/step - loss: 0.8446 - acc: 0.8696 - val_loss: 0.7921 - val_acc: 0.8873Epoch 26/500235s 470ms/step - loss: 0.8283 - acc: 0.8716 - val_loss: 0.7739 - val_acc: 0.8934Epoch 27/500235s 470ms/step - loss: 0.8212 - acc: 0.8720 - val_loss: 0.7726 - val_acc: 0.8885Epoch 28/500235s 471ms/step - loss: 0.8089 - acc: 0.8743 - val_loss: 0.7783 - val_acc: 0.8855Epoch 29/500235s 470ms/step - loss: 0.7970 - acc: 0.8775 - val_loss: 0.7350 - val_acc: 0.8988Epoch 30/500235s 470ms/step - loss: 0.7911 - acc: 0.8792 - val_loss: 0.7695 - val_acc: 0.8860Epoch 31/500235s 470ms/step - loss: 0.7846 - acc: 0.8802 - val_loss: 0.7392 - val_acc: 0.8989Epoch 32/500235s 471ms/step - loss: 0.7784 - acc: 0.8814 - val_loss: 0.7618 - val_acc: 0.8888Epoch 33/500235s 470ms/step - loss: 0.7724 - acc: 0.8842 - val_loss: 0.7547 - val_acc: 0.8937Epoch 34/500235s 470ms/step - loss: 0.7680 - acc: 0.8856 - val_loss: 0.7400 - val_acc: 0.8941Epoch 35/500235s 470ms/step - loss: 0.7646 - acc: 0.8865 - val_loss: 0.7079 - val_acc: 0.9096Epoch 36/500235s 470ms/step - loss: 0.7567 - acc: 0.8889 - val_loss: 0.7297 - val_acc: 0.8991Epoch 37/500235s 471ms/step - loss: 0.7518 - acc: 0.8920 - val_loss: 0.7265 - val_acc: 0.9011Epoch 38/500235s 470ms/step - loss: 0.7499 - acc: 0.8911 - val_loss: 0.7068 - val_acc: 0.9108Epoch 39/500235s 470ms/step - loss: 0.7455 - acc: 0.8927 - val_loss: 0.7524 - val_acc: 0.8939Epoch 40/500235s 470ms/step - loss: 0.7451 - acc: 0.8926 - val_loss: 0.7293 - val_acc: 0.9007Epoch 41/500235s 471ms/step - loss: 0.7434 - acc: 0.8951 - val_loss: 0.6985 - val_acc: 0.9097Epoch 42/500235s 470ms/step - loss: 0.7439 - acc: 0.8933 - val_loss: 0.7252 - val_acc: 0.9018Epoch 43/500235s 470ms/step - loss: 0.7433 - acc: 0.8952 - val_loss: 0.7304 - val_acc: 0.9006Epoch 44/500235s 470ms/step - loss: 0.7393 - acc: 0.8958 - val_loss: 0.6997 - val_acc: 0.9134Epoch 45/500235s 470ms/step - loss: 0.7348 - acc: 0.8992 - val_loss: 0.7287 - val_acc: 0.9035Epoch 46/500235s 470ms/step - loss: 0.7373 - acc: 0.8976 - val_loss: 0.7235 - val_acc: 0.9036Epoch 47/500235s 470ms/step - loss: 0.7382 - acc: 0.8974 - val_loss: 0.7178 - val_acc: 0.9081Epoch 48/500235s 470ms/step - loss: 0.7363 - acc: 0.8975 - val_loss: 0.7247 - val_acc: 0.9044Epoch 49/500235s 470ms/step - loss: 0.7306 - acc: 0.9009 - val_loss: 0.7328 - val_acc: 0.9006Epoch 50/500235s 470ms/step - loss: 0.7356 - acc: 0.9003 - val_loss: 0.7096 - val_acc: 0.9114Epoch 51/500235s 470ms/step - loss: 0.7282 - acc: 0.9029 - val_loss: 0.7156 - val_acc: 0.9076Epoch 52/500235s 470ms/step - loss: 0.7286 - acc: 0.9014 - val_loss: 0.7233 - val_acc: 0.9046Epoch 53/500235s 470ms/step - loss: 0.7304 - acc: 0.9016 - val_loss: 0.7087 - val_acc: 0.9088Epoch 54/500235s 470ms/step - loss: 0.7261 - acc: 0.9030 - val_loss: 0.7202 - val_acc: 0.9085Epoch 55/500235s 470ms/step - loss: 0.7257 - acc: 0.9034 - val_loss: 0.7138 - val_acc: 0.9095Epoch 56/500235s 470ms/step - loss: 0.7230 - acc: 0.9043 - val_loss: 0.7196 - val_acc: 0.9084Epoch 57/500235s 470ms/step - loss: 0.7212 - acc: 0.9048 - val_loss: 0.7094 - val_acc: 0.9098Epoch 58/500236s 473ms/step - loss: 0.7247 - acc: 0.9037 - val_loss: 0.7177 - val_acc: 0.9101Epoch 59/500236s 473ms/step - loss: 0.7183 - acc: 0.9067 - val_loss: 0.7385 - val_acc: 0.9026Epoch 60/500236s 472ms/step - loss: 0.7224 - acc: 0.9044 - val_loss: 0.7005 - val_acc: 0.9120Epoch 61/500236s 472ms/step - loss: 0.7185 - acc: 0.9050 - val_loss: 0.7287 - val_acc: 0.9067Epoch 62/500236s 472ms/step - loss: 0.7237 - acc: 0.9049 - val_loss: 0.6969 - val_acc: 0.9160Epoch 63/500236s 472ms/step - loss: 0.7177 - acc: 0.9074 - val_loss: 0.7044 - val_acc: 0.9117Epoch 64/500236s 472ms/step - loss: 0.7140 - acc: 0.9096 - val_loss: 0.7135 - val_acc: 0.9089Epoch 65/500236s 472ms/step - loss: 0.7120 - acc: 0.9074 - val_loss: 0.7107 - val_acc: 0.9093Epoch 66/500236s 472ms/step - loss: 0.7148 - acc: 0.9074 - val_loss: 0.7084 - val_acc: 0.9090Epoch 67/500236s 472ms/step - loss: 0.7156 - acc: 0.9081 - val_loss: 0.7086 - val_acc: 0.9132Epoch 68/500236s 472ms/step - loss: 0.7180 - acc: 0.9074 - val_loss: 0.7177 - val_acc: 0.9090Epoch 69/500237s 473ms/step - loss: 0.7111 - acc: 0.9094 - val_loss: 0.7278 - val_acc: 0.9047Epoch 70/500236s 473ms/step - loss: 0.7138 - acc: 0.9093 - val_loss: 0.7179 - val_acc: 0.9090Epoch 71/500237s 473ms/step - loss: 0.7165 - acc: 0.9084 - val_loss: 0.7251 - val_acc: 0.9065Epoch 72/500236s 473ms/step - loss: 0.7133 - acc: 0.9109 - val_loss: 0.6957 - val_acc: 0.9160Epoch 73/500236s 473ms/step - loss: 0.7129 - acc: 0.9106 - val_loss: 0.7008 - val_acc: 0.9154Epoch 74/500237s 473ms/step - loss: 0.7109 - acc: 0.9110 - val_loss: 0.7126 - val_acc: 0.9121Epoch 75/500236s 473ms/step - loss: 0.7143 - acc: 0.9105 - val_loss: 0.7286 - val_acc: 0.9061Epoch 76/500236s 472ms/step - loss: 0.7091 - acc: 0.9125 - val_loss: 0.7024 - val_acc: 0.9149Epoch 77/500236s 472ms/step - loss: 0.7129 - acc: 0.9104 - val_loss: 0.7176 - val_acc: 0.9106Epoch 78/500236s 472ms/step - loss: 0.7108 - acc: 0.9118 - val_loss: 0.6977 - val_acc: 0.9191Epoch 79/500237s 473ms/step - loss: 0.7088 - acc: 0.9123 - val_loss: 0.7253 - val_acc: 0.9069Epoch 80/500237s 473ms/step - loss: 0.7138 - acc: 0.9106 - val_loss: 0.7052 - val_acc: 0.9192Epoch 81/500236s 472ms/step - loss: 0.7120 - acc: 0.9130 - val_loss: 0.7205 - val_acc: 0.9113Epoch 82/500236s 472ms/step - loss: 0.7099 - acc: 0.9129 - val_loss: 0.7249 - val_acc: 0.9120Epoch 83/500236s 472ms/step - loss: 0.7076 - acc: 0.9117 - val_loss: 0.7329 - val_acc: 0.9060Epoch 84/500236s 472ms/step - loss: 0.7150 - acc: 0.9105 - val_loss: 0.6931 - val_acc: 0.9205Epoch 85/500236s 472ms/step - loss: 0.7062 - acc: 0.9159 - val_loss: 0.7189 - val_acc: 0.9107Epoch 86/500236s 472ms/step - loss: 0.7111 - acc: 0.9117 - val_loss: 0.6910 - val_acc: 0.9204Epoch 87/500236s 472ms/step - loss: 0.7070 - acc: 0.9138 - val_loss: 0.6921 - val_acc: 0.9201Epoch 88/500236s 472ms/step - loss: 0.7050 - acc: 0.9142 - val_loss: 0.6977 - val_acc: 0.9186Epoch 89/500236s 472ms/step - loss: 0.7056 - acc: 0.9136 - val_loss: 0.7174 - val_acc: 0.9109Epoch 90/500236s 472ms/step - loss: 0.7032 - acc: 0.9154 - val_loss: 0.6996 - val_acc: 0.9184Epoch 91/500236s 472ms/step - loss: 0.7060 - acc: 0.9139 - val_loss: 0.7090 - val_acc: 0.9143Epoch 92/500236s 472ms/step - loss: 0.7066 - acc: 0.9130 - val_loss: 0.7228 - val_acc: 0.9114Epoch 93/500236s 473ms/step - loss: 0.7063 - acc: 0.9155 - val_loss: 0.7039 - val_acc: 0.9216Epoch 94/500236s 473ms/step - loss: 0.7072 - acc: 0.9140 - val_loss: 0.7116 - val_acc: 0.9150Epoch 95/500236s 472ms/step - loss: 0.7096 - acc: 0.9143 - val_loss: 0.7216 - val_acc: 0.9109Epoch 96/500236s 473ms/step - loss: 0.7006 - acc: 0.9161 - val_loss: 0.7143 - val_acc: 0.9141Epoch 97/500236s 472ms/step - loss: 0.7069 - acc: 0.9142 - val_loss: 0.6954 - val_acc: 0.9224Epoch 98/500236s 473ms/step - loss: 0.7064 - acc: 0.9151 - val_loss: 0.7273 - val_acc: 0.9081Epoch 99/500236s 472ms/step - loss: 0.7038 - acc: 0.9161 - val_loss: 0.7274 - val_acc: 0.9132Epoch 100/500236s 472ms/step - loss: 0.7064 - acc: 0.9162 - val_loss: 0.7092 - val_acc: 0.9159Epoch 101/500236s 472ms/step - loss: 0.7011 - acc: 0.9169 - val_loss: 0.7331 - val_acc: 0.9080Epoch 102/500236s 472ms/step - loss: 0.7047 - acc: 0.9159 - val_loss: 0.7092 - val_acc: 0.9185Epoch 103/500237s 473ms/step - loss: 0.6994 - acc: 0.9166 - val_loss: 0.7029 - val_acc: 0.9180Epoch 104/500237s 473ms/step - loss: 0.6976 - acc: 0.9186 - val_loss: 0.7215 - val_acc: 0.9083Epoch 105/500236s 473ms/step - loss: 0.7002 - acc: 0.9159 - val_loss: 0.7191 - val_acc: 0.9111Epoch 106/500236s 472ms/step - loss: 0.7019 - acc: 0.9152 - val_loss: 0.7217 - val_acc: 0.9138Epoch 107/500236s 472ms/step - loss: 0.7078 - acc: 0.9154 - val_loss: 0.6926 - val_acc: 0.9249Epoch 108/500236s 472ms/step - loss: 0.7069 - acc: 0.9154 - val_loss: 0.7048 - val_acc: 0.9214Epoch 109/500236s 472ms/step - loss: 0.6975 - acc: 0.9182 - val_loss: 0.7130 - val_acc: 0.9130Epoch 110/500236s 472ms/step - loss: 0.7010 - acc: 0.9168 - val_loss: 0.7074 - val_acc: 0.9140Epoch 111/500236s 472ms/step - loss: 0.7020 - acc: 0.9175 - val_loss: 0.7142 - val_acc: 0.9161Epoch 112/500236s 473ms/step - loss: 0.6991 - acc: 0.9179 - val_loss: 0.7238 - val_acc: 0.9075Epoch 113/500236s 473ms/step - loss: 0.7022 - acc: 0.9165 - val_loss: 0.7162 - val_acc: 0.9165Epoch 114/500236s 473ms/step - loss: 0.7006 - acc: 0.9177 - val_loss: 0.7261 - val_acc: 0.9125Epoch 115/500237s 473ms/step - loss: 0.6987 - acc: 0.9184 - val_loss: 0.7110 - val_acc: 0.9121Epoch 116/500236s 472ms/step - loss: 0.6984 - acc: 0.9169 - val_loss: 0.7012 - val_acc: 0.9221Epoch 117/500236s 472ms/step - loss: 0.7002 - acc: 0.9162 - val_loss: 0.7278 - val_acc: 0.9113Epoch 118/500236s 472ms/step - loss: 0.6998 - acc: 0.9181 - val_loss: 0.7352 - val_acc: 0.9079Epoch 119/500236s 473ms/step - loss: 0.6989 - acc: 0.9187 - val_loss: 0.7147 - val_acc: 0.9162Epoch 120/500237s 473ms/step - loss: 0.7025 - acc: 0.9175 - val_loss: 0.7014 - val_acc: 0.9195Epoch 121/500236s 473ms/step - loss: 0.7003 - acc: 0.9183 - val_loss: 0.6987 - val_acc: 0.9177Epoch 122/500236s 472ms/step - loss: 0.6996 - acc: 0.9172 - val_loss: 0.7206 - val_acc: 0.9146Epoch 123/500236s 472ms/step - loss: 0.7033 - acc: 0.9174 - val_loss: 0.7128 - val_acc: 0.9187Epoch 124/500236s 472ms/step - loss: 0.6957 - acc: 0.9194 - val_loss: 0.7079 - val_acc: 0.9177Epoch 125/500236s 472ms/step - loss: 0.7028 - acc: 0.9171 - val_loss: 0.7080 - val_acc: 0.9200Epoch 126/500236s 472ms/step - loss: 0.7005 - acc: 0.9167 - val_loss: 0.7362 - val_acc: 0.9096Epoch 127/500236s 472ms/step - loss: 0.7044 - acc: 0.9182 - val_loss: 0.7139 - val_acc: 0.9164Epoch 128/500236s 472ms/step - loss: 0.7031 - acc: 0.9184 - val_loss: 0.7105 - val_acc: 0.9162Epoch 129/500236s 472ms/step - loss: 0.6979 - acc: 0.9194 - val_loss: 0.7255 - val_acc: 0.9160Epoch 130/500236s 472ms/step - loss: 0.7016 - acc: 0.9192 - val_loss: 0.7252 - val_acc: 0.9150Epoch 131/500236s 472ms/step - loss: 0.6991 - acc: 0.9208 - val_loss: 0.7086 - val_acc: 0.9204Epoch 132/500236s 472ms/step - loss: 0.7005 - acc: 0.9195 - val_loss: 0.7169 - val_acc: 0.9163Epoch 133/500236s 472ms/step - loss: 0.7006 - acc: 0.9191 - val_loss: 0.7040 - val_acc: 0.9202Epoch 134/500236s 472ms/step - loss: 0.7009 - acc: 0.9196 - val_loss: 0.7241 - val_acc: 0.9139Epoch 135/500237s 473ms/step - loss: 0.6915 - acc: 0.9211 - val_loss: 0.7318 - val_acc: 0.9088Epoch 136/500236s 472ms/step - loss: 0.7054 - acc: 0.9172 - val_loss: 0.7155 - val_acc: 0.9157Epoch 137/500236s 473ms/step - loss: 0.7006 - acc: 0.9191 - val_loss: 0.7221 - val_acc: 0.9152Epoch 138/500236s 472ms/step - loss: 0.6938 - acc: 0.9209 - val_loss: 0.7026 - val_acc: 0.9228Epoch 139/500236s 472ms/step - loss: 0.6994 - acc: 0.9189 - val_loss: 0.7087 - val_acc: 0.9200Epoch 140/500236s 472ms/step - loss: 0.6990 - acc: 0.9194 - val_loss: 0.7284 - val_acc: 0.9125Epoch 141/500236s 472ms/step - loss: 0.7056 - acc: 0.9174 - val_loss: 0.7021 - val_acc: 0.9224Epoch 142/500236s 472ms/step - loss: 0.6948 - acc: 0.9199 - val_loss: 0.7238 - val_acc: 0.9201Epoch 143/500236s 472ms/step - loss: 0.6957 - acc: 0.9199 - val_loss: 0.7073 - val_acc: 0.9164Epoch 144/500236s 472ms/step - loss: 0.6981 - acc: 0.9206 - val_loss: 0.7212 - val_acc: 0.9148Epoch 145/500236s 472ms/step - loss: 0.6976 - acc: 0.9212 - val_loss: 0.7079 - val_acc: 0.9204Epoch 146/500236s 473ms/step - loss: 0.6993 - acc: 0.9197 - val_loss: 0.7286 - val_acc: 0.9154Epoch 147/500236s 472ms/step - loss: 0.6891 - acc: 0.9234 - val_loss: 0.7160 - val_acc: 0.9175Epoch 148/500236s 472ms/step - loss: 0.6978 - acc: 0.9203 - val_loss: 0.7208 - val_acc: 0.9138Epoch 149/500236s 472ms/step - loss: 0.6975 - acc: 0.9196 - val_loss: 0.7227 - val_acc: 0.9138Epoch 150/500236s 472ms/step - loss: 0.6930 - acc: 0.9217 - val_loss: 0.7080 - val_acc: 0.9171Epoch 151/500lr changed to 0.010000000149011612236s 472ms/step - loss: 0.5908 - acc: 0.9565 - val_loss: 0.6227 - val_acc: 0.9453Epoch 152/500236s 472ms/step - loss: 0.5375 - acc: 0.9734 - val_loss: 0.6086 - val_acc: 0.9479Epoch 153/500236s 472ms/step - loss: 0.5165 - acc: 0.9768 - val_loss: 0.5996 - val_acc: 0.9481Epoch 154/500236s 472ms/step - loss: 0.5005 - acc: 0.9798 - val_loss: 0.5907 - val_acc: 0.9494Epoch 155/500236s 472ms/step - loss: 0.4879 - acc: 0.9815 - val_loss: 0.5831 - val_acc: 0.9512Epoch 156/500236s 472ms/step - loss: 0.4739 - acc: 0.9842 - val_loss: 0.5746 - val_acc: 0.9508Epoch 157/500236s 472ms/step - loss: 0.4628 - acc: 0.9846 - val_loss: 0.5674 - val_acc: 0.9516Epoch 158/500236s 472ms/step - loss: 0.4513 - acc: 0.9866 - val_loss: 0.5614 - val_acc: 0.9513Epoch 159/500236s 472ms/step - loss: 0.4419 - acc: 0.9882 - val_loss: 0.5624 - val_acc: 0.9510Epoch 160/500236s 472ms/step - loss: 0.4331 - acc: 0.9874 - val_loss: 0.5522 - val_acc: 0.9516Epoch 161/500236s 472ms/step - loss: 0.4238 - acc: 0.9895 - val_loss: 0.5444 - val_acc: 0.9517Epoch 162/500236s 473ms/step - loss: 0.4177 - acc: 0.9885 - val_loss: 0.5420 - val_acc: 0.9517Epoch 163/500236s 472ms/step - loss: 0.4088 - acc: 0.9897 - val_loss: 0.5349 - val_acc: 0.9511Epoch 164/500236s 472ms/step - loss: 0.4013 - acc: 0.9897 - val_loss: 0.5262 - val_acc: 0.9537Epoch 165/500236s 472ms/step - loss: 0.3953 - acc: 0.9895 - val_loss: 0.5197 - val_acc: 0.9520Epoch 166/500236s 472ms/step - loss: 0.3872 - acc: 0.9908 - val_loss: 0.5165 - val_acc: 0.9517Epoch 167/500236s 472ms/step - loss: 0.3805 - acc: 0.9911 - val_loss: 0.5151 - val_acc: 0.9519Epoch 168/500236s 472ms/step - loss: 0.3732 - acc: 0.9910 - val_loss: 0.5118 - val_acc: 0.9506Epoch 169/500236s 472ms/step - loss: 0.3677 - acc: 0.9913 - val_loss: 0.5079 - val_acc: 0.9497Epoch 170/500236s 472ms/step - loss: 0.3603 - acc: 0.9913 - val_loss: 0.4986 - val_acc: 0.9512Epoch 171/500236s 472ms/step - loss: 0.3551 - acc: 0.9920 - val_loss: 0.4933 - val_acc: 0.9517Epoch 172/500236s 472ms/step - loss: 0.3506 - acc: 0.9916 - val_loss: 0.4847 - val_acc: 0.9527Epoch 173/500236s 473ms/step - loss: 0.3436 - acc: 0.9921 - val_loss: 0.4808 - val_acc: 0.9528Epoch 174/500236s 472ms/step - loss: 0.3374 - acc: 0.9922 - val_loss: 0.4800 - val_acc: 0.9528Epoch 175/500236s 472ms/step - loss: 0.3324 - acc: 0.9924 - val_loss: 0.4743 - val_acc: 0.9512Epoch 176/500236s 472ms/step - loss: 0.3277 - acc: 0.9925 - val_loss: 0.4741 - val_acc: 0.9505Epoch 177/500236s 472ms/step - loss: 0.3222 - acc: 0.9929 - val_loss: 0.4663 - val_acc: 0.9503Epoch 178/500236s 472ms/step - loss: 0.3179 - acc: 0.9926 - val_loss: 0.4694 - val_acc: 0.9497Epoch 179/500236s 472ms/step - loss: 0.3148 - acc: 0.9922 - val_loss: 0.4584 - val_acc: 0.9502Epoch 180/500236s 472ms/step - loss: 0.3082 - acc: 0.9938 - val_loss: 0.4647 - val_acc: 0.9484Epoch 181/500236s 471ms/step - loss: 0.3024 - acc: 0.9936 - val_loss: 0.4562 - val_acc: 0.9503Epoch 182/500236s 472ms/step - loss: 0.2996 - acc: 0.9931 - val_loss: 0.4528 - val_acc: 0.9518Epoch 183/500236s 472ms/step - loss: 0.2949 - acc: 0.9935 - val_loss: 0.4555 - val_acc: 0.9503Epoch 184/500236s 472ms/step - loss: 0.2916 - acc: 0.9932 - val_loss: 0.4519 - val_acc: 0.9481Epoch 185/500236s 472ms/step - loss: 0.2886 - acc: 0.9929 - val_loss: 0.4428 - val_acc: 0.9491Epoch 186/500236s 472ms/step - loss: 0.2857 - acc: 0.9929 - val_loss: 0.4383 - val_acc: 0.9495Epoch 187/500236s 472ms/step - loss: 0.2816 - acc: 0.9928 - val_loss: 0.4380 - val_acc: 0.9479Epoch 188/500236s 472ms/step - loss: 0.2764 - acc: 0.9935 - val_loss: 0.4373 - val_acc: 0.9479Epoch 189/500236s 472ms/step - loss: 0.2742 - acc: 0.9930 - val_loss: 0.4204 - val_acc: 0.9510Epoch 190/500236s 472ms/step - loss: 0.2697 - acc: 0.9935 - val_loss: 0.4241 - val_acc: 0.9500Epoch 191/500236s 472ms/step - loss: 0.2642 - acc: 0.9940 - val_loss: 0.4287 - val_acc: 0.9486Epoch 192/500236s 472ms/step - loss: 0.2631 - acc: 0.9932 - val_loss: 0.4230 - val_acc: 0.9478Epoch 193/500236s 472ms/step - loss: 0.2614 - acc: 0.9929 - val_loss: 0.4182 - val_acc: 0.9470Epoch 194/500236s 472ms/step - loss: 0.2577 - acc: 0.9929 - val_loss: 0.4143 - val_acc: 0.9465Epoch 195/500236s 472ms/step - loss: 0.2551 - acc: 0.9933 - val_loss: 0.4124 - val_acc: 0.9488Epoch 196/500236s 472ms/step - loss: 0.2522 - acc: 0.9933 - val_loss: 0.4111 - val_acc: 0.9469Epoch 197/500236s 472ms/step - loss: 0.2487 - acc: 0.9930 - val_loss: 0.4062 - val_acc: 0.9515Epoch 198/500236s 472ms/step - loss: 0.2474 - acc: 0.9926 - val_loss: 0.4036 - val_acc: 0.9505Epoch 199/500236s 472ms/step - loss: 0.2419 - acc: 0.9943 - val_loss: 0.3958 - val_acc: 0.9522Epoch 200/500236s 472ms/step - loss: 0.2393 - acc: 0.9939 - val_loss: 0.4007 - val_acc: 0.9509Epoch 201/500236s 472ms/step - loss: 0.2399 - acc: 0.9927 - val_loss: 0.3961 - val_acc: 0.9475Epoch 202/500236s 472ms/step - loss: 0.2385 - acc: 0.9922 - val_loss: 0.3966 - val_acc: 0.9486Epoch 203/500236s 471ms/step - loss: 0.2354 - acc: 0.9926 - val_loss: 0.3975 - val_acc: 0.9502Epoch 204/500236s 472ms/step - loss: 0.2314 - acc: 0.9935 - val_loss: 0.3895 - val_acc: 0.9510Epoch 205/500236s 472ms/step - loss: 0.2286 - acc: 0.9939 - val_loss: 0.3812 - val_acc: 0.9511Epoch 206/500236s 471ms/step - loss: 0.2286 - acc: 0.9926 - val_loss: 0.3841 - val_acc: 0.9500Epoch 207/500236s 472ms/step - loss: 0.2286 - acc: 0.9919 - val_loss: 0.3856 - val_acc: 0.9480Epoch 208/500236s 472ms/step - loss: 0.2249 - acc: 0.9928 - val_loss: 0.3721 - val_acc: 0.9509Epoch 209/500236s 471ms/step - loss: 0.2228 - acc: 0.9927 - val_loss: 0.3787 - val_acc: 0.9504Epoch 210/500236s 472ms/step - loss: 0.2222 - acc: 0.9925 - val_loss: 0.3797 - val_acc: 0.9483Epoch 211/500236s 471ms/step - loss: 0.2223 - acc: 0.9917 - val_loss: 0.3699 - val_acc: 0.9516Epoch 212/500236s 472ms/step - loss: 0.2185 - acc: 0.9925 - val_loss: 0.3764 - val_acc: 0.9500Epoch 213/500236s 472ms/step - loss: 0.2165 - acc: 0.9924 - val_loss: 0.3842 - val_acc: 0.9466Epoch 214/500236s 472ms/step - loss: 0.2151 - acc: 0.9925 - val_loss: 0.3631 - val_acc: 0.9517Epoch 215/500236s 471ms/step - loss: 0.2148 - acc: 0.9921 - val_loss: 0.3738 - val_acc: 0.9485Epoch 216/500236s 472ms/step - loss: 0.2137 - acc: 0.9920 - val_loss: 0.3658 - val_acc: 0.9489Epoch 217/500236s 472ms/step - loss: 0.2141 - acc: 0.9916 - val_loss: 0.3644 - val_acc: 0.9492Epoch 218/500236s 472ms/step - loss: 0.2071 - acc: 0.9929 - val_loss: 0.3660 - val_acc: 0.9489Epoch 219/500236s 472ms/step - loss: 0.2108 - acc: 0.9912 - val_loss: 0.3556 - val_acc: 0.9510Epoch 220/500236s 471ms/step - loss: 0.2068 - acc: 0.9921 - val_loss: 0.3661 - val_acc: 0.9492Epoch 221/500236s 472ms/step - loss: 0.2061 - acc: 0.9921 - val_loss: 0.3592 - val_acc: 0.9478Epoch 222/500236s 472ms/step - loss: 0.2073 - acc: 0.9908 - val_loss: 0.3573 - val_acc: 0.9485Epoch 223/500236s 472ms/step - loss: 0.2066 - acc: 0.9913 - val_loss: 0.3703 - val_acc: 0.9447Epoch 224/500236s 472ms/step - loss: 0.2075 - acc: 0.9903 - val_loss: 0.3552 - val_acc: 0.9499Epoch 225/500236s 471ms/step - loss: 0.2015 - acc: 0.9922 - val_loss: 0.3700 - val_acc: 0.9470Epoch 226/500236s 472ms/step - loss: 0.2033 - acc: 0.9914 - val_loss: 0.3646 - val_acc: 0.9483Epoch 227/500236s 472ms/step - loss: 0.2039 - acc: 0.9908 - val_loss: 0.3619 - val_acc: 0.9483Epoch 228/500236s 472ms/step - loss: 0.1979 - acc: 0.9927 - val_loss: 0.3593 - val_acc: 0.9490Epoch 229/500236s 472ms/step - loss: 0.1987 - acc: 0.9915 - val_loss: 0.3628 - val_acc: 0.9469Epoch 230/500236s 472ms/step - loss: 0.1991 - acc: 0.9916 - val_loss: 0.3524 - val_acc: 0.9471Epoch 231/500236s 472ms/step - loss: 0.1983 - acc: 0.9913 - val_loss: 0.3551 - val_acc: 0.9484Epoch 232/500236s 472ms/step - loss: 0.1953 - acc: 0.9923 - val_loss: 0.3511 - val_acc: 0.9465Epoch 233/500236s 472ms/step - loss: 0.1950 - acc: 0.9917 - val_loss: 0.3513 - val_acc: 0.9472Epoch 234/500236s 472ms/step - loss: 0.1930 - acc: 0.9920 - val_loss: 0.3515 - val_acc: 0.9501Epoch 235/500236s 472ms/step - loss: 0.1956 - acc: 0.9909 - val_loss: 0.3401 - val_acc: 0.9506Epoch 236/500236s 472ms/step - loss: 0.1941 - acc: 0.9909 - val_loss: 0.3536 - val_acc: 0.9471Epoch 237/500236s 472ms/step - loss: 0.1961 - acc: 0.9904 - val_loss: 0.3740 - val_acc: 0.9419Epoch 238/500236s 471ms/step - loss: 0.1975 - acc: 0.9894 - val_loss: 0.3527 - val_acc: 0.9472Epoch 239/500236s 472ms/step - loss: 0.1947 - acc: 0.9908 - val_loss: 0.3384 - val_acc: 0.9506Epoch 240/500236s 472ms/step - loss: 0.1910 - acc: 0.9915 - val_loss: 0.3403 - val_acc: 0.9489Epoch 241/500236s 472ms/step - loss: 0.1920 - acc: 0.9907 - val_loss: 0.3510 - val_acc: 0.9443Epoch 242/500236s 472ms/step - loss: 0.1940 - acc: 0.9899 - val_loss: 0.3439 - val_acc: 0.9487Epoch 243/500236s 472ms/step - loss: 0.1885 - acc: 0.9918 - val_loss: 0.3400 - val_acc: 0.9496Epoch 244/500236s 471ms/step - loss: 0.1901 - acc: 0.9912 - val_loss: 0.3487 - val_acc: 0.9483Epoch 245/500236s 471ms/step - loss: 0.1885 - acc: 0.9916 - val_loss: 0.3321 - val_acc: 0.9526Epoch 246/500236s 472ms/step - loss: 0.1887 - acc: 0.9912 - val_loss: 0.3563 - val_acc: 0.9456Epoch 247/500236s 471ms/step - loss: 0.1912 - acc: 0.9901 - val_loss: 0.3408 - val_acc: 0.9457Epoch 248/500236s 472ms/step - loss: 0.1900 - acc: 0.9907 - val_loss: 0.3511 - val_acc: 0.9462Epoch 249/500236s 472ms/step - loss: 0.1902 - acc: 0.9898 - val_loss: 0.3484 - val_acc: 0.9470Epoch 250/500236s 472ms/step - loss: 0.1854 - acc: 0.9916 - val_loss: 0.3378 - val_acc: 0.9509Epoch 251/500236s 471ms/step - loss: 0.1896 - acc: 0.9899 - val_loss: 0.3470 - val_acc: 0.9466Epoch 252/500236s 472ms/step - loss: 0.1885 - acc: 0.9906 - val_loss: 0.3437 - val_acc: 0.9500Epoch 253/500236s 472ms/step - loss: 0.1855 - acc: 0.9912 - val_loss: 0.3424 - val_acc: 0.9472Epoch 254/500236s 471ms/step - loss: 0.1835 - acc: 0.9914 - val_loss: 0.3507 - val_acc: 0.9477Epoch 255/500236s 472ms/step - loss: 0.1887 - acc: 0.9900 - val_loss: 0.3447 - val_acc: 0.9457Epoch 256/500236s 472ms/step - loss: 0.1895 - acc: 0.9896 - val_loss: 0.3444 - val_acc: 0.9474Epoch 257/500236s 472ms/step - loss: 0.1876 - acc: 0.9904 - val_loss: 0.3446 - val_acc: 0.9448Epoch 258/500236s 472ms/step - loss: 0.1864 - acc: 0.9901 - val_loss: 0.3412 - val_acc: 0.9471Epoch 259/500236s 471ms/step - loss: 0.1845 - acc: 0.9910 - val_loss: 0.3501 - val_acc: 0.9435Epoch 260/500236s 471ms/step - loss: 0.1886 - acc: 0.9891 - val_loss: 0.3388 - val_acc: 0.9468Epoch 261/500236s 471ms/step - loss: 0.1876 - acc: 0.9893 - val_loss: 0.3583 - val_acc: 0.9458Epoch 262/500236s 471ms/step - loss: 0.1873 - acc: 0.9899 - val_loss: 0.3586 - val_acc: 0.9446Epoch 263/500236s 471ms/step - loss: 0.1814 - acc: 0.9917 - val_loss: 0.3447 - val_acc: 0.9480Epoch 264/500236s 472ms/step - loss: 0.1851 - acc: 0.9908 - val_loss: 0.3413 - val_acc: 0.9464Epoch 265/500236s 471ms/step - loss: 0.1869 - acc: 0.9897 - val_loss: 0.3462 - val_acc: 0.9421Epoch 266/500236s 472ms/step - loss: 0.1830 - acc: 0.9908 - val_loss: 0.3249 - val_acc: 0.9518Epoch 267/500236s 472ms/step - loss: 0.1854 - acc: 0.9905 - val_loss: 0.3291 - val_acc: 0.9479Epoch 268/500236s 471ms/step - loss: 0.1838 - acc: 0.9901 - val_loss: 0.3499 - val_acc: 0.9453Epoch 269/500236s 471ms/step - loss: 0.1842 - acc: 0.9903 - val_loss: 0.3493 - val_acc: 0.9468Epoch 270/500236s 472ms/step - loss: 0.1858 - acc: 0.9897 - val_loss: 0.3450 - val_acc: 0.9461Epoch 271/500236s 471ms/step - loss: 0.1822 - acc: 0.9903 - val_loss: 0.3357 - val_acc: 0.9477Epoch 272/500236s 471ms/step - loss: 0.1840 - acc: 0.9904 - val_loss: 0.3432 - val_acc: 0.9452Epoch 273/500236s 472ms/step - loss: 0.1873 - acc: 0.9894 - val_loss: 0.3369 - val_acc: 0.9472Epoch 274/500236s 472ms/step - loss: 0.1826 - acc: 0.9906 - val_loss: 0.3556 - val_acc: 0.9443Epoch 275/500236s 472ms/step - loss: 0.1812 - acc: 0.9905 - val_loss: 0.3580 - val_acc: 0.9474Epoch 276/500236s 472ms/step - loss: 0.1835 - acc: 0.9900 - val_loss: 0.3549 - val_acc: 0.9447Epoch 277/500236s 471ms/step - loss: 0.1808 - acc: 0.9908 - val_loss: 0.3434 - val_acc: 0.9454Epoch 278/500236s 472ms/step - loss: 0.1822 - acc: 0.9904 - val_loss: 0.3398 - val_acc: 0.9476Epoch 279/500236s 472ms/step - loss: 0.1825 - acc: 0.9906 - val_loss: 0.3292 - val_acc: 0.9497Epoch 280/500236s 471ms/step - loss: 0.1839 - acc: 0.9896 - val_loss: 0.3487 - val_acc: 0.9433Epoch 281/500236s 472ms/step - loss: 0.1826 - acc: 0.9905 - val_loss: 0.3433 - val_acc: 0.9464Epoch 282/500236s 472ms/step - loss: 0.1808 - acc: 0.9910 - val_loss: 0.3261 - val_acc: 0.9469Epoch 283/500236s 472ms/step - loss: 0.1816 - acc: 0.9907 - val_loss: 0.3523 - val_acc: 0.9418Epoch 284/500236s 472ms/step - loss: 0.1847 - acc: 0.9895 - val_loss: 0.3297 - val_acc: 0.9477Epoch 285/500236s 472ms/step - loss: 0.1813 - acc: 0.9909 - val_loss: 0.3337 - val_acc: 0.9472Epoch 286/500236s 472ms/step - loss: 0.1797 - acc: 0.9911 - val_loss: 0.3495 - val_acc: 0.9457Epoch 287/500236s 471ms/step - loss: 0.1824 - acc: 0.9905 - val_loss: 0.3378 - val_acc: 0.9471Epoch 288/500236s 472ms/step - loss: 0.1815 - acc: 0.9904 - val_loss: 0.3371 - val_acc: 0.9479Epoch 289/500236s 472ms/step - loss: 0.1795 - acc: 0.9909 - val_loss: 0.3345 - val_acc: 0.9481Epoch 290/500236s 472ms/step - loss: 0.1833 - acc: 0.9896 - val_loss: 0.3221 - val_acc: 0.9505Epoch 291/500236s 471ms/step - loss: 0.1798 - acc: 0.9911 - val_loss: 0.3425 - val_acc: 0.9464Epoch 292/500236s 471ms/step - loss: 0.1826 - acc: 0.9899 - val_loss: 0.3563 - val_acc: 0.9407Epoch 293/500236s 471ms/step - loss: 0.1809 - acc: 0.9906 - val_loss: 0.3398 - val_acc: 0.9463Epoch 294/500236s 471ms/step - loss: 0.1835 - acc: 0.9897 - val_loss: 0.3427 - val_acc: 0.9478Epoch 295/500236s 471ms/step - loss: 0.1792 - acc: 0.9913 - val_loss: 0.3443 - val_acc: 0.9463Epoch 296/500236s 471ms/step - loss: 0.1794 - acc: 0.9907 - val_loss: 0.3456 - val_acc: 0.9457Epoch 297/500236s 472ms/step - loss: 0.1751 - acc: 0.9922 - val_loss: 0.3362 - val_acc: 0.9457Epoch 298/500236s 472ms/step - loss: 0.1821 - acc: 0.9893 - val_loss: 0.3465 - val_acc: 0.9440Epoch 299/500236s 472ms/step - loss: 0.1827 - acc: 0.9893 - val_loss: 0.3462 - val_acc: 0.9443Epoch 300/500236s 471ms/step - loss: 0.1793 - acc: 0.9910 - val_loss: 0.3537 - val_acc: 0.9422Epoch 301/500lr changed to 0.0009999999776482583236s 471ms/step - loss: 0.1692 - acc: 0.9943 - val_loss: 0.3201 - val_acc: 0.9535Epoch 302/500236s 472ms/step - loss: 0.1627 - acc: 0.9966 - val_loss: 0.3157 - val_acc: 0.9546Epoch 303/500236s 471ms/step - loss: 0.1600 - acc: 0.9972 - val_loss: 0.3139 - val_acc: 0.9556Epoch 304/500236s 472ms/step - loss: 0.1580 - acc: 0.9980 - val_loss: 0.3134 - val_acc: 0.9543Epoch 305/500236s 471ms/step - loss: 0.1571 - acc: 0.9981 - val_loss: 0.3141 - val_acc: 0.9555Epoch 306/500236s 472ms/step - loss: 0.1567 - acc: 0.9982 - val_loss: 0.3135 - val_acc: 0.9556Epoch 307/500236s 471ms/step - loss: 0.1557 - acc: 0.9983 - val_loss: 0.3120 - val_acc: 0.9546Epoch 308/500236s 471ms/step - loss: 0.1544 - acc: 0.9987 - val_loss: 0.3123 - val_acc: 0.9548Epoch 309/500236s 472ms/step - loss: 0.1543 - acc: 0.9986 - val_loss: 0.3112 - val_acc: 0.9569Epoch 310/500236s 471ms/step - loss: 0.1539 - acc: 0.9988 - val_loss: 0.3101 - val_acc: 0.9567Epoch 311/500236s 472ms/step - loss: 0.1534 - acc: 0.9988 - val_loss: 0.3122 - val_acc: 0.9568Epoch 312/500236s 471ms/step - loss: 0.1531 - acc: 0.9987 - val_loss: 0.3123 - val_acc: 0.9562Epoch 313/500236s 471ms/step - loss: 0.1526 - acc: 0.9985 - val_loss: 0.3129 - val_acc: 0.9559Epoch 314/500236s 472ms/step - loss: 0.1526 - acc: 0.9986 - val_loss: 0.3135 - val_acc: 0.9561Epoch 315/500236s 471ms/step - loss: 0.1518 - acc: 0.9988 - val_loss: 0.3111 - val_acc: 0.9569Epoch 316/500236s 471ms/step - loss: 0.1517 - acc: 0.9986 - val_loss: 0.3121 - val_acc: 0.9563Epoch 317/500236s 471ms/step - loss: 0.1511 - acc: 0.9989 - val_loss: 0.3115 - val_acc: 0.9563Epoch 318/500236s 471ms/step - loss: 0.1508 - acc: 0.9989 - val_loss: 0.3115 - val_acc: 0.9571Epoch 319/500236s 471ms/step - loss: 0.1500 - acc: 0.9990 - val_loss: 0.3102 - val_acc: 0.9576Epoch 320/500236s 471ms/step - loss: 0.1502 - acc: 0.9989 - val_loss: 0.3100 - val_acc: 0.9562Epoch 321/500236s 472ms/step - loss: 0.1494 - acc: 0.9990 - val_loss: 0.3092 - val_acc: 0.9569Epoch 322/500236s 472ms/step - loss: 0.1489 - acc: 0.9990 - val_loss: 0.3092 - val_acc: 0.9562Epoch 323/500236s 472ms/step - loss: 0.1492 - acc: 0.9988 - val_loss: 0.3078 - val_acc: 0.9566Epoch 324/500236s 472ms/step - loss: 0.1485 - acc: 0.9991 - val_loss: 0.3068 - val_acc: 0.9575Epoch 325/500236s 472ms/step - loss: 0.1485 - acc: 0.9991 - val_loss: 0.3066 - val_acc: 0.9567Epoch 326/500236s 471ms/step - loss: 0.1479 - acc: 0.9992 - val_loss: 0.3056 - val_acc: 0.9575Epoch 327/500236s 471ms/step - loss: 0.1475 - acc: 0.9992 - val_loss: 0.3074 - val_acc: 0.9576Epoch 328/500236s 472ms/step - loss: 0.1469 - acc: 0.9994 - val_loss: 0.3073 - val_acc: 0.9571Epoch 329/500236s 471ms/step - loss: 0.1472 - acc: 0.9991 - val_loss: 0.3074 - val_acc: 0.9563Epoch 330/500236s 471ms/step - loss: 0.1466 - acc: 0.9992 - val_loss: 0.3068 - val_acc: 0.9575Epoch 331/500236s 472ms/step - loss: 0.1461 - acc: 0.9993 - val_loss: 0.3067 - val_acc: 0.9570Epoch 332/500236s 472ms/step - loss: 0.1464 - acc: 0.9991 - val_loss: 0.3065 - val_acc: 0.9563Epoch 333/500236s 472ms/step - loss: 0.1456 - acc: 0.9991 - val_loss: 0.3081 - val_acc: 0.9572Epoch 334/500236s 471ms/step - loss: 0.1454 - acc: 0.9993 - val_loss: 0.3080 - val_acc: 0.9569Epoch 335/500236s 471ms/step - loss: 0.1451 - acc: 0.9992 - val_loss: 0.3069 - val_acc: 0.9569Epoch 336/500236s 471ms/step - loss: 0.1453 - acc: 0.9992 - val_loss: 0.3066 - val_acc: 0.9570Epoch 337/500236s 471ms/step - loss: 0.1450 - acc: 0.9992 - val_loss: 0.3060 - val_acc: 0.9572Epoch 338/500236s 472ms/step - loss: 0.1440 - acc: 0.9994 - val_loss: 0.3074 - val_acc: 0.9575Epoch 339/500236s 471ms/step - loss: 0.1441 - acc: 0.9993 - val_loss: 0.3071 - val_acc: 0.9574Epoch 340/500236s 472ms/step - loss: 0.1438 - acc: 0.9994 - val_loss: 0.3070 - val_acc: 0.9579Epoch 341/500236s 472ms/step - loss: 0.1435 - acc: 0.9993 - val_loss: 0.3061 - val_acc: 0.9576Epoch 342/500236s 472ms/step - loss: 0.1432 - acc: 0.9993 - val_loss: 0.3072 - val_acc: 0.9577Epoch 343/500236s 471ms/step - loss: 0.1431 - acc: 0.9992 - val_loss: 0.3061 - val_acc: 0.9573Epoch 344/500236s 471ms/step - loss: 0.1426 - acc: 0.9992 - val_loss: 0.3050 - val_acc: 0.9577Epoch 345/500236s 471ms/step - loss: 0.1426 - acc: 0.9994 - val_loss: 0.3051 - val_acc: 0.9577Epoch 346/500236s 472ms/step - loss: 0.1423 - acc: 0.9992 - val_loss: 0.3049 - val_acc: 0.9583Epoch 347/500235s 470ms/step - loss: 0.1421 - acc: 0.9993 - val_loss: 0.3044 - val_acc: 0.9581Epoch 348/500235s 469ms/step - loss: 0.1416 - acc: 0.9993 - val_loss: 0.3045 - val_acc: 0.9576Epoch 349/500234s 469ms/step - loss: 0.1414 - acc: 0.9994 - val_loss: 0.3044 - val_acc: 0.9573Epoch 350/500234s 469ms/step - loss: 0.1409 - acc: 0.9994 - val_loss: 0.3059 - val_acc: 0.9571Epoch 351/500234s 469ms/step - loss: 0.1407 - acc: 0.9996 - val_loss: 0.3051 - val_acc: 0.9569Epoch 352/500234s 469ms/step - loss: 0.1405 - acc: 0.9993 - val_loss: 0.3048 - val_acc: 0.9571Epoch 353/500235s 470ms/step - loss: 0.1405 - acc: 0.9993 - val_loss: 0.3034 - val_acc: 0.9575Epoch 354/500235s 469ms/step - loss: 0.1403 - acc: 0.9994 - val_loss: 0.3037 - val_acc: 0.9581Epoch 355/500234s 469ms/step - loss: 0.1401 - acc: 0.9993 - val_loss: 0.3037 - val_acc: 0.9583Epoch 356/500235s 470ms/step - loss: 0.1394 - acc: 0.9995 - val_loss: 0.3039 - val_acc: 0.9581Epoch 357/500235s 469ms/step - loss: 0.1393 - acc: 0.9993 - val_loss: 0.3009 - val_acc: 0.9589Epoch 358/500234s 469ms/step - loss: 0.1394 - acc: 0.9991 - val_loss: 0.3027 - val_acc: 0.9585Epoch 359/500234s 469ms/step - loss: 0.1389 - acc: 0.9995 - val_loss: 0.3031 - val_acc: 0.9582Epoch 360/500234s 469ms/step - loss: 0.1389 - acc: 0.9992 - val_loss: 0.3021 - val_acc: 0.9584Epoch 361/500234s 468ms/step - loss: 0.1387 - acc: 0.9994 - val_loss: 0.3027 - val_acc: 0.9595Epoch 362/500234s 468ms/step - loss: 0.1383 - acc: 0.9993 - val_loss: 0.3011 - val_acc: 0.9590Epoch 363/500234s 468ms/step - loss: 0.1381 - acc: 0.9994 - val_loss: 0.3017 - val_acc: 0.9583Epoch 364/500234s 468ms/step - loss: 0.1376 - acc: 0.9992 - val_loss: 0.3024 - val_acc: 0.9582Epoch 365/500234s 468ms/step - loss: 0.1372 - acc: 0.9995 - val_loss: 0.3016 - val_acc: 0.9580Epoch 366/500234s 468ms/step - loss: 0.1375 - acc: 0.9992 - val_loss: 0.3021 - val_acc: 0.9583Epoch 367/500234s 468ms/step - loss: 0.1370 - acc: 0.9994 - val_loss: 0.3022 - val_acc: 0.9576Epoch 368/500234s 469ms/step - loss: 0.1369 - acc: 0.9993 - val_loss: 0.3014 - val_acc: 0.9582Epoch 369/500234s 468ms/step - loss: 0.1363 - acc: 0.9994 - val_loss: 0.3031 - val_acc: 0.9576Epoch 370/500234s 469ms/step - loss: 0.1363 - acc: 0.9995 - val_loss: 0.3005 - val_acc: 0.9578Epoch 371/500235s 469ms/step - loss: 0.1358 - acc: 0.9995 - val_loss: 0.3020 - val_acc: 0.9574Epoch 372/500235s 469ms/step - loss: 0.1360 - acc: 0.9994 - val_loss: 0.3011 - val_acc: 0.9575Epoch 373/500235s 469ms/step - loss: 0.1359 - acc: 0.9994 - val_loss: 0.3002 - val_acc: 0.9576Epoch 374/500234s 469ms/step - loss: 0.1353 - acc: 0.9994 - val_loss: 0.3001 - val_acc: 0.9578Epoch 375/500234s 469ms/step - loss: 0.1351 - acc: 0.9995 - val_loss: 0.3004 - val_acc: 0.9575Epoch 376/500234s 469ms/step - loss: 0.1351 - acc: 0.9993 - val_loss: 0.3003 - val_acc: 0.9591Epoch 377/500234s 469ms/step - loss: 0.1347 - acc: 0.9994 - val_loss: 0.2993 - val_acc: 0.9586Epoch 378/500234s 468ms/step - loss: 0.1344 - acc: 0.9995 - val_loss: 0.2989 - val_acc: 0.9583Epoch 379/500235s 469ms/step - loss: 0.1347 - acc: 0.9992 - val_loss: 0.2994 - val_acc: 0.9584Epoch 380/500235s 469ms/step - loss: 0.1338 - acc: 0.9995 - val_loss: 0.2987 - val_acc: 0.9591Epoch 381/500234s 468ms/step - loss: 0.1337 - acc: 0.9994 - val_loss: 0.2994 - val_acc: 0.9590Epoch 382/500234s 468ms/step - loss: 0.1333 - acc: 0.9995 - val_loss: 0.2998 - val_acc: 0.9585Epoch 383/500234s 468ms/step - loss: 0.1332 - acc: 0.9994 - val_loss: 0.3007 - val_acc: 0.9576Epoch 384/500234s 468ms/step - loss: 0.1329 - acc: 0.9994 - val_loss: 0.2996 - val_acc: 0.9575Epoch 385/500234s 468ms/step - loss: 0.1331 - acc: 0.9993 - val_loss: 0.2985 - val_acc: 0.9582Epoch 386/500234s 468ms/step - loss: 0.1327 - acc: 0.9993 - val_loss: 0.2962 - val_acc: 0.9579Epoch 387/500234s 468ms/step - loss: 0.1327 - acc: 0.9994 - val_loss: 0.2965 - val_acc: 0.9582Epoch 388/500234s 468ms/step - loss: 0.1319 - acc: 0.9995 - val_loss: 0.2953 - val_acc: 0.9579Epoch 389/500234s 468ms/step - loss: 0.1319 - acc: 0.9995 - val_loss: 0.2979 - val_acc: 0.9582Epoch 390/500234s 468ms/step - loss: 0.1317 - acc: 0.9995 - val_loss: 0.2983 - val_acc: 0.9568Epoch 391/500234s 468ms/step - loss: 0.1316 - acc: 0.9994 - val_loss: 0.2973 - val_acc: 0.9570Epoch 392/500234s 468ms/step - loss: 0.1313 - acc: 0.9995 - val_loss: 0.2975 - val_acc: 0.9572Epoch 393/500234s 468ms/step - loss: 0.1314 - acc: 0.9993 - val_loss: 0.2969 - val_acc: 0.9584Epoch 394/500234s 468ms/step - loss: 0.1310 - acc: 0.9994 - val_loss: 0.2972 - val_acc: 0.9568Epoch 395/500234s 468ms/step - loss: 0.1312 - acc: 0.9993 - val_loss: 0.2954 - val_acc: 0.9581Epoch 396/500234s 468ms/step - loss: 0.1310 - acc: 0.9993 - val_loss: 0.2926 - val_acc: 0.9582Epoch 397/500234s 468ms/step - loss: 0.1304 - acc: 0.9995 - val_loss: 0.2932 - val_acc: 0.9585Epoch 398/500234s 468ms/step - loss: 0.1304 - acc: 0.9992 - val_loss: 0.2946 - val_acc: 0.9587Epoch 399/500234s 468ms/step - loss: 0.1298 - acc: 0.9994 - val_loss: 0.2959 - val_acc: 0.9582Epoch 400/500235s 469ms/step - loss: 0.1295 - acc: 0.9996 - val_loss: 0.2945 - val_acc: 0.9581Epoch 401/500235s 469ms/step - loss: 0.1296 - acc: 0.9995 - val_loss: 0.2945 - val_acc: 0.9590Epoch 402/500235s 469ms/step - loss: 0.1293 - acc: 0.9996 - val_loss: 0.2921 - val_acc: 0.9584Epoch 403/500235s 469ms/step - loss: 0.1290 - acc: 0.9994 - val_loss: 0.2917 - val_acc: 0.9583Epoch 404/500234s 469ms/step - loss: 0.1287 - acc: 0.9995 - val_loss: 0.2918 - val_acc: 0.9594Epoch 405/500234s 469ms/step - loss: 0.1287 - acc: 0.9994 - val_loss: 0.2947 - val_acc: 0.9579Epoch 406/500234s 469ms/step - loss: 0.1284 - acc: 0.9995 - val_loss: 0.2959 - val_acc: 0.9577Epoch 407/500234s 469ms/step - loss: 0.1284 - acc: 0.9993 - val_loss: 0.2966 - val_acc: 0.9578Epoch 408/500234s 469ms/step - loss: 0.1284 - acc: 0.9993 - val_loss: 0.2959 - val_acc: 0.9572Epoch 409/500234s 469ms/step - loss: 0.1278 - acc: 0.9995 - val_loss: 0.2936 - val_acc: 0.9573Epoch 410/500234s 469ms/step - loss: 0.1278 - acc: 0.9994 - val_loss: 0.2942 - val_acc: 0.9569Epoch 411/500234s 469ms/step - loss: 0.1274 - acc: 0.9994 - val_loss: 0.2942 - val_acc: 0.9566Epoch 412/500234s 469ms/step - loss: 0.1271 - acc: 0.9994 - val_loss: 0.2928 - val_acc: 0.9579Epoch 413/500235s 469ms/step - loss: 0.1271 - acc: 0.9994 - val_loss: 0.2910 - val_acc: 0.9575Epoch 414/500234s 469ms/step - loss: 0.1267 - acc: 0.9994 - val_loss: 0.2889 - val_acc: 0.9581Epoch 415/500234s 469ms/step - loss: 0.1267 - acc: 0.9994 - val_loss: 0.2906 - val_acc: 0.9583Epoch 416/500234s 469ms/step - loss: 0.1263 - acc: 0.9995 - val_loss: 0.2907 - val_acc: 0.9575Epoch 417/500234s 469ms/step - loss: 0.1265 - acc: 0.9993 - val_loss: 0.2888 - val_acc: 0.9584Epoch 418/500234s 469ms/step - loss: 0.1261 - acc: 0.9994 - val_loss: 0.2894 - val_acc: 0.9584Epoch 419/500234s 469ms/step - loss: 0.1255 - acc: 0.9996 - val_loss: 0.2908 - val_acc: 0.9583Epoch 420/500234s 469ms/step - loss: 0.1257 - acc: 0.9993 - val_loss: 0.2925 - val_acc: 0.9583Epoch 421/500234s 469ms/step - loss: 0.1255 - acc: 0.9993 - val_loss: 0.2911 - val_acc: 0.9584Epoch 422/500235s 470ms/step - loss: 0.1253 - acc: 0.9995 - val_loss: 0.2907 - val_acc: 0.9574Epoch 423/500235s 469ms/step - loss: 0.1248 - acc: 0.9996 - val_loss: 0.2899 - val_acc: 0.9573Epoch 424/500235s 469ms/step - loss: 0.1251 - acc: 0.9993 - val_loss: 0.2932 - val_acc: 0.9582Epoch 425/500235s 469ms/step - loss: 0.1246 - acc: 0.9994 - val_loss: 0.2925 - val_acc: 0.9579Epoch 426/500234s 469ms/step - loss: 0.1245 - acc: 0.9993 - val_loss: 0.2902 - val_acc: 0.9574Epoch 427/500234s 469ms/step - loss: 0.1242 - acc: 0.9995 - val_loss: 0.2919 - val_acc: 0.9570Epoch 428/500234s 469ms/step - loss: 0.1237 - acc: 0.9995 - val_loss: 0.2930 - val_acc: 0.9577Epoch 429/500235s 469ms/step - loss: 0.1239 - acc: 0.9994 - val_loss: 0.2921 - val_acc: 0.9584Epoch 430/500234s 469ms/step - loss: 0.1239 - acc: 0.9994 - val_loss: 0.2924 - val_acc: 0.9575Epoch 431/500234s 469ms/step - loss: 0.1237 - acc: 0.9993 - val_loss: 0.2931 - val_acc: 0.9587Epoch 432/500235s 470ms/step - loss: 0.1232 - acc: 0.9996 - val_loss: 0.2933 - val_acc: 0.9585Epoch 433/500235s 470ms/step - loss: 0.1233 - acc: 0.9995 - val_loss: 0.2922 - val_acc: 0.9584Epoch 434/500235s 469ms/step - loss: 0.1226 - acc: 0.9996 - val_loss: 0.2936 - val_acc: 0.9582Epoch 435/500234s 469ms/step - loss: 0.1230 - acc: 0.9993 - val_loss: 0.2946 - val_acc: 0.9584Epoch 436/500234s 469ms/step - loss: 0.1224 - acc: 0.9996 - val_loss: 0.2939 - val_acc: 0.9573Epoch 437/500235s 470ms/step - loss: 0.1227 - acc: 0.9992 - val_loss: 0.2949 - val_acc: 0.9577Epoch 438/500235s 469ms/step - loss: 0.1222 - acc: 0.9995 - val_loss: 0.2933 - val_acc: 0.9581Epoch 439/500235s 469ms/step - loss: 0.1217 - acc: 0.9995 - val_loss: 0.2919 - val_acc: 0.9574Epoch 440/500234s 469ms/step - loss: 0.1215 - acc: 0.9995 - val_loss: 0.2917 - val_acc: 0.9583Epoch 441/500235s 469ms/step - loss: 0.1213 - acc: 0.9996 - val_loss: 0.2930 - val_acc: 0.9577Epoch 442/500234s 469ms/step - loss: 0.1217 - acc: 0.9993 - val_loss: 0.2951 - val_acc: 0.9571Epoch 443/500234s 469ms/step - loss: 0.1212 - acc: 0.9995 - val_loss: 0.2957 - val_acc: 0.9566Epoch 444/500234s 469ms/step - loss: 0.1207 - acc: 0.9996 - val_loss: 0.2949 - val_acc: 0.9569Epoch 445/500234s 469ms/step - loss: 0.1210 - acc: 0.9994 - val_loss: 0.2923 - val_acc: 0.9569Epoch 446/500234s 469ms/step - loss: 0.1206 - acc: 0.9994 - val_loss: 0.2919 - val_acc: 0.9573Epoch 447/500234s 469ms/step - loss: 0.1209 - acc: 0.9993 - val_loss: 0.2947 - val_acc: 0.9577Epoch 448/500234s 469ms/step - loss: 0.1203 - acc: 0.9995 - val_loss: 0.2923 - val_acc: 0.9581Epoch 449/500234s 469ms/step - loss: 0.1203 - acc: 0.9994 - val_loss: 0.2926 - val_acc: 0.9579Epoch 450/500235s 469ms/step - loss: 0.1199 - acc: 0.9995 - val_loss: 0.2888 - val_acc: 0.9591Epoch 451/500lr changed to 9.999999310821295e-05234s 469ms/step - loss: 0.1197 - acc: 0.9994 - val_loss: 0.2890 - val_acc: 0.9588Epoch 452/500235s 470ms/step - loss: 0.1196 - acc: 0.9996 - val_loss: 0.2891 - val_acc: 0.9587Epoch 453/500235s 469ms/step - loss: 0.1197 - acc: 0.9997 - val_loss: 0.2887 - val_acc: 0.9589Epoch 454/500235s 470ms/step - loss: 0.1197 - acc: 0.9994 - val_loss: 0.2888 - val_acc: 0.9588Epoch 455/500234s 469ms/step - loss: 0.1196 - acc: 0.9995 - val_loss: 0.2885 - val_acc: 0.9592Epoch 456/500234s 469ms/step - loss: 0.1196 - acc: 0.9994 - val_loss: 0.2887 - val_acc: 0.9586Epoch 457/500235s 469ms/step - loss: 0.1195 - acc: 0.9996 - val_loss: 0.2885 - val_acc: 0.9583Epoch 458/500234s 469ms/step - loss: 0.1194 - acc: 0.9997 - val_loss: 0.2886 - val_acc: 0.9585Epoch 459/500235s 471ms/step - loss: 0.1193 - acc: 0.9996 - val_loss: 0.2887 - val_acc: 0.9585Epoch 460/500235s 470ms/step - loss: 0.1191 - acc: 0.9997 - val_loss: 0.2885 - val_acc: 0.9581Epoch 461/500235s 470ms/step - loss: 0.1194 - acc: 0.9995 - val_loss: 0.2887 - val_acc: 0.9585Epoch 462/500235s 470ms/step - loss: 0.1192 - acc: 0.9996 - val_loss: 0.2886 - val_acc: 0.9584Epoch 463/500235s 469ms/step - loss: 0.1192 - acc: 0.9996 - val_loss: 0.2887 - val_acc: 0.9579Epoch 464/500234s 469ms/step - loss: 0.1194 - acc: 0.9996 - val_loss: 0.2891 - val_acc: 0.9583Epoch 465/500234s 469ms/step - loss: 0.1194 - acc: 0.9995 - val_loss: 0.2888 - val_acc: 0.9585Epoch 466/500234s 469ms/step - loss: 0.1189 - acc: 0.9998 - val_loss: 0.2889 - val_acc: 0.9586Epoch 467/500234s 469ms/step - loss: 0.1190 - acc: 0.9997 - val_loss: 0.2885 - val_acc: 0.9584Epoch 468/500234s 469ms/step - loss: 0.1192 - acc: 0.9995 - val_loss: 0.2882 - val_acc: 0.9582Epoch 469/500235s 469ms/step - loss: 0.1192 - acc: 0.9996 - val_loss: 0.2882 - val_acc: 0.9582Epoch 470/500235s 469ms/step - loss: 0.1191 - acc: 0.9996 - val_loss: 0.2885 - val_acc: 0.9579Epoch 471/500234s 469ms/step - loss: 0.1193 - acc: 0.9995 - val_loss: 0.2885 - val_acc: 0.9580Epoch 472/500235s 471ms/step - loss: 0.1195 - acc: 0.9994 - val_loss: 0.2885 - val_acc: 0.9579Epoch 473/500235s 470ms/step - loss: 0.1191 - acc: 0.9996 - val_loss: 0.2883 - val_acc: 0.9578Epoch 474/500235s 470ms/step - loss: 0.1195 - acc: 0.9994 - val_loss: 0.2887 - val_acc: 0.9579Epoch 475/500235s 469ms/step - loss: 0.1192 - acc: 0.9995 - val_loss: 0.2884 - val_acc: 0.9582Epoch 476/500234s 469ms/step - loss: 0.1190 - acc: 0.9996 - val_loss: 0.2885 - val_acc: 0.9581Epoch 477/500234s 469ms/step - loss: 0.1189 - acc: 0.9997 - val_loss: 0.2888 - val_acc: 0.9581Epoch 478/500234s 469ms/step - loss: 0.1190 - acc: 0.9996 - val_loss: 0.2889 - val_acc: 0.9582Epoch 479/500234s 469ms/step - loss: 0.1187 - acc: 0.9997 - val_loss: 0.2887 - val_acc: 0.9584Epoch 480/500234s 469ms/step - loss: 0.1188 - acc: 0.9996 - val_loss: 0.2882 - val_acc: 0.9581Epoch 481/500235s 469ms/step - loss: 0.1191 - acc: 0.9996 - val_loss: 0.2883 - val_acc: 0.9578Epoch 482/500235s 471ms/step - loss: 0.1189 - acc: 0.9996 - val_loss: 0.2880 - val_acc: 0.9581Epoch 483/500234s 469ms/step - loss: 0.1186 - acc: 0.9996 - val_loss: 0.2881 - val_acc: 0.9582Epoch 484/500234s 469ms/step - loss: 0.1188 - acc: 0.9996 - val_loss: 0.2881 - val_acc: 0.9577Epoch 485/500234s 469ms/step - loss: 0.1190 - acc: 0.9996 - val_loss: 0.2884 - val_acc: 0.9578Epoch 486/500234s 469ms/step - loss: 0.1186 - acc: 0.9997 - val_loss: 0.2884 - val_acc: 0.9579Epoch 487/500234s 469ms/step - loss: 0.1189 - acc: 0.9995 - val_loss: 0.2883 - val_acc: 0.9580Epoch 488/500237s 473ms/step - loss: 0.1183 - acc: 0.9997 - val_loss: 0.2883 - val_acc: 0.9580Epoch 489/500235s 469ms/step - loss: 0.1186 - acc: 0.9997 - val_loss: 0.2885 - val_acc: 0.9578Epoch 490/500234s 468ms/step - loss: 0.1186 - acc: 0.9997 - val_loss: 0.2887 - val_acc: 0.9579Epoch 491/500234s 468ms/step - loss: 0.1187 - acc: 0.9996 - val_loss: 0.2884 - val_acc: 0.9581Epoch 492/500234s 469ms/step - loss: 0.1187 - acc: 0.9994 - val_loss: 0.2881 - val_acc: 0.9579Epoch 493/500234s 469ms/step - loss: 0.1185 - acc: 0.9996 - val_loss: 0.2883 - val_acc: 0.9578Epoch 494/500234s 469ms/step - loss: 0.1187 - acc: 0.9997 - val_loss: 0.2881 - val_acc: 0.9579Epoch 495/500234s 468ms/step - loss: 0.1187 - acc: 0.9997 - val_loss: 0.2880 - val_acc: 0.9579Epoch 496/500234s 469ms/step - loss: 0.1185 - acc: 0.9996 - val_loss: 0.2881 - val_acc: 0.9579Epoch 497/500234s 469ms/step - loss: 0.1186 - acc: 0.9996 - val_loss: 0.2881 - val_acc: 0.9582Epoch 498/500235s 469ms/step - loss: 0.1187 - acc: 0.9995 - val_loss: 0.2883 - val_acc: 0.9581Epoch 499/500234s 469ms/step - loss: 0.1184 - acc: 0.9996 - val_loss: 0.2884 - val_acc: 0.9580Epoch 500/500234s 469ms/step - loss: 0.1187 - acc: 0.9996 - val_loss: 0.2881 - val_acc: 0.9580Train loss: 0.11700774446129798Train accuracy: 0.999960000038147Test loss: 0.2880836722254753Test accuracy: 0.9580000066757202

測(cè)試準(zhǔn)確率是95.80%，離96%還差一點(diǎn)。

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

POS機(jī)的EMV參數(shù)下載什么意思？

EMV 標(biāo)準(zhǔn)是由國(guó)際三大銀行卡組織--Europay(歐陸卡，已被萬(wàn)事達(dá)收購(gòu)）、MasterCard（萬(wàn)事達(dá)卡）和Visa（維薩）共同發(fā)起制定的銀行卡從磁條卡向智能IC卡轉(zhuǎn)移的技術(shù)標(biāo)準(zhǔn)，是基于IC卡的金融支付標(biāo)準(zhǔn)，已成為公認(rèn)的全球統(tǒng)一標(biāo)準(zhǔn)。

以上就是關(guān)于pos機(jī)上網(wǎng)參數(shù),深度殘差網(wǎng)絡(luò)+自適應(yīng)參數(shù)化ReLU的知識(shí)，后面我們會(huì)繼續(xù)為大家整理關(guān)于pos機(jī)上網(wǎng)參數(shù)的知識(shí)，希望能夠幫助到大家！