本文在调参记录9的基础上,在数据增强部分添加了shear_range = 30,测试Adaptively Parametric ReLU(APReLU)激活函数在Cifar10图像集上的效果。
Keras里ImageDataGenerator的用法见如下网址:
https://fairyonice.github.io/Learn-about-ImageDataGenerator.html
深度残差网络+自适应参数化ReLU激活函数(调参记录9)
https://blog.csdn.net/dangqing1988/article/details/105688144
自适应参数化ReLU激活函数的基本原理见下图:
Keras程序如下:
1 #!/usr/bin/env python3 2 # -*- coding: utf-8 -*- 3 """ 4 Created on Tue Apr 14 04:17:45 2020 5 Implemented using TensorFlow 1.0.1 and Keras 2.2.1 6 7 Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht, 8 Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis, 9 IEEE Transactions on Industrial Electronics, 2020, DOI: 10.1109/TIE.2020.2972458 10 11 @author: Minghang Zhao 12 """ 13 14 from __future__ import print_function 15 import keras 16 import numpy as np 17 from keras.datasets import cifar10 18 from keras.layers import Dense, Conv2D, BatchNormalization, Activation, Minimum 19 from keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D, Concatenate, Reshape 20 from keras.regularizers import l2 21 from keras import backend as K 22 from keras.models import Model 23 from keras import optimizers 24 from keras.preprocessing.image import ImageDataGenerator 25 from keras.callbacks import LearningRateScheduler 26 K.set_learning_phase(1) 27 28 # The data, split between train and test sets 29 (x_train, y_train), (x_test, y_test) = cifar10.load_data() 30 31 # Noised data 32 x_train = x_train.astype('float32') / 255. 33 x_test = x_test.astype('float32') / 255. 34 x_test = x_test-np.mean(x_train) 35 x_train = x_train-np.mean(x_train) 36 print('x_train shape:', x_train.shape) 37 print(x_train.shape[0], 'train samples') 38 print(x_test.shape[0], 'test samples') 39 40 # convert class vectors to binary class matrices 41 y_train = keras.utils.to_categorical(y_train, 10) 42 y_test = keras.utils.to_categorical(y_test, 10) 43 44 # Schedule the learning rate, multiply 0.1 every 300 epoches 45 def scheduler(epoch): 46 if epoch % 300 == 0 and epoch != 0: 47 lr = K.get_value(model.optimizer.lr) 48 K.set_value(model.optimizer.lr, lr * 0.1) 49 print("lr changed to {}".format(lr * 0.1)) 50 return K.get_value(model.optimizer.lr) 51 52 # An adaptively parametric rectifier linear unit (APReLU) 53 def aprelu(inputs): 54 # get the number of channels 55 channels = inputs.get_shape().as_list()[-1] 56 # get a zero feature map 57 zeros_input = keras.layers.subtract([inputs, inputs]) 58 # get a feature map with only positive features 59 pos_input = Activation('relu')(inputs) 60 # get a feature map with only negative features 61 neg_input = Minimum()([inputs,zeros_input]) 62 # define a network to obtain the scaling coefficients 63 scales_p = GlobalAveragePooling2D()(pos_input) 64 scales_n = GlobalAveragePooling2D()(neg_input) 65 scales = Concatenate()([scales_n, scales_p]) 66 scales = Dense(channels, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales) 67 scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales) 68 scales = Activation('relu')(scales) 69 scales = Dense(channels, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales) 70 scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales) 71 scales = Activation('sigmoid')(scales) 72 scales = Reshape((1,1,channels))(scales) 73 # apply a paramtetric relu 74 neg_part = keras.layers.multiply([scales, neg_input]) 75 return keras.layers.add([pos_input, neg_part]) 76 77 # Residual Block 78 def residual_block(incoming, nb_blocks, out_channels, downsample=False, 79 downsample_strides=2): 80 81 residual = incoming 82 in_channels = incoming.get_shape().as_list()[-1] 83 84 for i in range(nb_blocks): 85 86 identity = residual 87 88 if not downsample: 89 downsample_strides = 1 90 91 residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) 92 residual = aprelu(residual) 93 residual = Conv2D(out_channels, 3, strides=(downsample_strides, downsample_strides), 94 padding='same', kernel_initializer='he_normal', 95 kernel_regularizer=l2(1e-4))(residual) 96 97 residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) 98 residual = aprelu(residual) 99 residual = Conv2D(out_channels, 3, padding='same', kernel_initializer='he_normal', 100 kernel_regularizer=l2(1e-4))(residual) 101 102 # Downsampling 103 if downsample_strides > 1: 104 identity = AveragePooling2D(pool_size=(1,1), strides=(2,2))(identity) 105 106 # Zero_padding to match channels 107 if in_channels != out_channels: 108 zeros_identity = keras.layers.subtract([identity, identity]) 109 identity = keras.layers.concatenate([identity, zeros_identity]) 110 in_channels = out_channels 111 112 residual = keras.layers.add([residual, identity]) 113 114 return residual 115 116 117 # define and train a model 118 inputs = Input(shape=(32, 32, 3)) 119 net = Conv2D(16, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(inputs) 120 net = residual_block(net, 9, 16, downsample=False) 121 net = residual_block(net, 1, 32, downsample=True) 122 net = residual_block(net, 8, 32, downsample=False) 123 net = residual_block(net, 1, 64, downsample=True) 124 net = residual_block(net, 8, 64, downsample=False) 125 net = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(net) 126 net = Activation('relu')(net) 127 net = GlobalAveragePooling2D()(net) 128 outputs = Dense(10, activation='softmax', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(net) 129 model = Model(inputs=inputs, outputs=outputs) 130 sgd = optimizers.SGD(lr=0.1, decay=0., momentum=0.9, nesterov=True) 131 model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) 132 133 # data augmentation 134 datagen = ImageDataGenerator( 135 # randomly rotate images in the range (deg 0 to 180) 136 rotation_range=30, 137 # shear angle in counter-clockwise direction in degrees 138 shear_range = 30, 139 # randomly flip images 140 horizontal_flip=True, 141 # randomly shift images horizontally 142 width_shift_range=0.125, 143 # randomly shift images vertically 144 height_shift_range=0.125) 145 146 reduce_lr = LearningRateScheduler(scheduler) 147 # fit the model on the batches generated by datagen.flow(). 148 model.fit_generator(datagen.flow(x_train, y_train, batch_size=100), 149 validation_data=(x_test, y_test), epochs=1000, 150 verbose=1, callbacks=[reduce_lr], workers=4) 151 152 # get results 153 K.set_learning_phase(0) 154 DRSN_train_score = model.evaluate(x_train, y_train, batch_size=100, verbose=0) 155 print('Train loss:', DRSN_train_score[0]) 156 print('Train accuracy:', DRSN_train_score[1]) 157 DRSN_test_score = model.evaluate(x_test, y_test, batch_size=100, verbose=0) 158 print('Test loss:', DRSN_test_score[0]) 159 print('Test accuracy:', DRSN_test_score[1])
实验结果如下:
1 x_train shape: (50000, 32, 32, 3) 2 50000 train samples 3 10000 test samples 4 Epoch 1/1000 5 113s 225ms/step - loss: 3.2549 - acc: 0.4158 - val_loss: 2.7729 - val_acc: 0.5394 6 Epoch 2/1000 7 68s 137ms/step - loss: 2.6403 - acc: 0.5484 - val_loss: 2.3416 - val_acc: 0.6117 8 Epoch 3/1000 9 69s 138ms/step - loss: 2.2763 - acc: 0.6049 - val_loss: 2.0151 - val_acc: 0.6705 10 Epoch 4/1000 11 69s 137ms/step - loss: 2.0062 - acc: 0.6393 - val_loss: 1.8055 - val_acc: 0.6907 12 Epoch 5/1000 13 69s 137ms/step - loss: 1.7997 - acc: 0.6673 - val_loss: 1.6339 - val_acc: 0.7058 14 Epoch 6/1000 15 69s 138ms/step - loss: 1.6338 - acc: 0.6849 - val_loss: 1.4391 - val_acc: 0.7345 16 Epoch 7/1000 17 69s 138ms/step - loss: 1.4911 - acc: 0.7032 - val_loss: 1.3495 - val_acc: 0.7435 18 Epoch 8/1000 19 69s 138ms/step - loss: 1.3733 - acc: 0.7196 - val_loss: 1.2311 - val_acc: 0.7668 20 Epoch 9/1000 21 68s 137ms/step - loss: 1.2893 - acc: 0.7308 - val_loss: 1.1543 - val_acc: 0.7741 22 Epoch 10/1000 23 68s 137ms/step - loss: 1.2164 - acc: 0.7402 - val_loss: 1.0974 - val_acc: 0.7761 24 Epoch 11/1000 25 69s 137ms/step - loss: 1.1580 - acc: 0.7470 - val_loss: 1.0477 - val_acc: 0.7835 26 Epoch 12/1000 27 69s 137ms/step - loss: 1.1127 - acc: 0.7519 - val_loss: 1.0269 - val_acc: 0.7813 28 Epoch 13/1000 29 69s 138ms/step - loss: 1.0713 - acc: 0.7598 - val_loss: 0.9656 - val_acc: 0.7996 30 Epoch 14/1000 31 68s 136ms/step - loss: 1.0369 - acc: 0.7664 - val_loss: 0.9576 - val_acc: 0.7929 32 Epoch 15/1000 33 68s 135ms/step - loss: 1.0158 - acc: 0.7677 - val_loss: 0.9189 - val_acc: 0.8064 34 Epoch 16/1000 35 68s 135ms/step - loss: 0.9948 - acc: 0.7733 - val_loss: 0.9198 - val_acc: 0.8022 36 Epoch 17/1000 37 68s 136ms/step - loss: 0.9720 - acc: 0.7775 - val_loss: 0.9267 - val_acc: 0.7954 38 Epoch 18/1000 39 68s 135ms/step - loss: 0.9548 - acc: 0.7813 - val_loss: 0.8897 - val_acc: 0.8043 40 Epoch 19/1000 41 68s 135ms/step - loss: 0.9446 - acc: 0.7847 - val_loss: 0.8642 - val_acc: 0.8104 42 Epoch 20/1000 43 68s 135ms/step - loss: 0.9290 - acc: 0.7873 - val_loss: 0.8666 - val_acc: 0.8119 44 Epoch 21/1000 45 68s 135ms/step - loss: 0.9131 - acc: 0.7913 - val_loss: 0.8433 - val_acc: 0.8202 46 Epoch 22/1000 47 68s 135ms/step - loss: 0.9099 - acc: 0.7912 - val_loss: 0.8735 - val_acc: 0.8077 48 Epoch 23/1000 49 67s 135ms/step - loss: 0.9000 - acc: 0.7956 - val_loss: 0.8418 - val_acc: 0.8150 50 Epoch 24/1000 51 68s 135ms/step - loss: 0.8962 - acc: 0.7966 - val_loss: 0.8452 - val_acc: 0.8181 52 Epoch 25/1000 53 68s 135ms/step - loss: 0.8874 - acc: 0.7994 - val_loss: 0.8209 - val_acc: 0.8242 54 Epoch 26/1000 55 68s 136ms/step - loss: 0.8810 - acc: 0.8021 - val_loss: 0.8378 - val_acc: 0.8202 56 Epoch 27/1000 57 68s 135ms/step - loss: 0.8764 - acc: 0.8026 - val_loss: 0.8474 - val_acc: 0.8173 58 Epoch 28/1000 59 67s 135ms/step - loss: 0.8706 - acc: 0.8040 - val_loss: 0.8239 - val_acc: 0.8230 60 Epoch 29/1000 61 68s 135ms/step - loss: 0.8655 - acc: 0.8075 - val_loss: 0.8163 - val_acc: 0.8244 62 Epoch 30/1000 63 68s 135ms/step - loss: 0.8600 - acc: 0.8074 - val_loss: 0.8065 - val_acc: 0.8288 64 Epoch 31/1000 65 68s 135ms/step - loss: 0.8544 - acc: 0.8113 - val_loss: 0.8080 - val_acc: 0.8306 66 Epoch 32/1000 67 68s 135ms/step - loss: 0.8510 - acc: 0.8121 - val_loss: 0.8152 - val_acc: 0.8304 68 Epoch 33/1000 69 68s 135ms/step - loss: 0.8464 - acc: 0.8142 - val_loss: 0.7827 - val_acc: 0.8387 70 Epoch 34/1000 71 68s 135ms/step - loss: 0.8429 - acc: 0.8166 - val_loss: 0.7738 - val_acc: 0.8453 72 Epoch 35/1000 73 68s 135ms/step - loss: 0.8366 - acc: 0.8160 - val_loss: 0.7855 - val_acc: 0.8388 74 Epoch 36/1000 75 68s 135ms/step - loss: 0.8352 - acc: 0.8191 - val_loss: 0.7651 - val_acc: 0.8468 76 Epoch 37/1000 77 68s 135ms/step - loss: 0.8292 - acc: 0.8212 - val_loss: 0.7620 - val_acc: 0.8470 78 Epoch 38/1000 79 68s 135ms/step - loss: 0.8319 - acc: 0.8208 - val_loss: 0.7890 - val_acc: 0.8376 80 Epoch 39/1000 81 68s 136ms/step - loss: 0.8239 - acc: 0.8256 - val_loss: 0.7870 - val_acc: 0.8370 82 Epoch 40/1000 83 68s 135ms/step - loss: 0.8266 - acc: 0.8216 - val_loss: 0.7975 - val_acc: 0.8331 84 Epoch 41/1000 85 68s 135ms/step - loss: 0.8209 - acc: 0.8239 - val_loss: 0.7982 - val_acc: 0.8334 86 Epoch 42/1000 87 68s 135ms/step - loss: 0.8135 - acc: 0.8276 - val_loss: 0.7722 - val_acc: 0.8427 88 Epoch 43/1000 89 68s 135ms/step - loss: 0.8115 - acc: 0.8280 - val_loss: 0.7658 - val_acc: 0.8430 90 Epoch 44/1000 91 67s 135ms/step - loss: 0.8166 - acc: 0.8259 - val_loss: 0.7388 - val_acc: 0.8559 92 Epoch 45/1000 93 67s 135ms/step - loss: 0.8108 - acc: 0.8293 - val_loss: 0.7728 - val_acc: 0.8436 94 Epoch 46/1000 95 68s 135ms/step - loss: 0.8046 - acc: 0.8303 - val_loss: 0.7684 - val_acc: 0.8434 96 Epoch 47/1000 97 68s 136ms/step - loss: 0.8055 - acc: 0.8322 - val_loss: 0.7478 - val_acc: 0.8511 98 Epoch 48/1000 99 68s 135ms/step - loss: 0.8100 - acc: 0.8290 - val_loss: 0.7644 - val_acc: 0.8445 100 Epoch 49/1000 101 68s 135ms/step - loss: 0.8027 - acc: 0.8325 - val_loss: 0.7449 - val_acc: 0.8545 102 Epoch 50/1000 103 67s 135ms/step - loss: 0.8052 - acc: 0.8299 - val_loss: 0.7941 - val_acc: 0.8377 104 Epoch 51/1000 105 68s 135ms/step - loss: 0.7969 - acc: 0.8339 - val_loss: 0.7617 - val_acc: 0.8481 106 Epoch 52/1000 107 68s 135ms/step - loss: 0.7989 - acc: 0.8335 - val_loss: 0.7559 - val_acc: 0.8550 108 Epoch 53/1000 109 68s 136ms/step - loss: 0.7927 - acc: 0.8353 - val_loss: 0.7482 - val_acc: 0.8536 110 Epoch 54/1000 111 68s 135ms/step - loss: 0.7931 - acc: 0.8365 - val_loss: 0.7405 - val_acc: 0.8570 112 Epoch 55/1000 113 68s 135ms/step - loss: 0.7933 - acc: 0.8372 - val_loss: 0.7541 - val_acc: 0.8535 114 Epoch 56/1000 115 68s 135ms/step - loss: 0.7887 - acc: 0.8389 - val_loss: 0.7805 - val_acc: 0.8436 116 Epoch 57/1000 117 68s 135ms/step - loss: 0.7877 - acc: 0.8385 - val_loss: 0.7304 - val_acc: 0.8617 118 Epoch 58/1000 119 68s 135ms/step - loss: 0.7836 - acc: 0.8404 - val_loss: 0.7630 - val_acc: 0.8480 120 Epoch 59/1000 121 68s 135ms/step - loss: 0.7859 - acc: 0.8394 - val_loss: 0.7369 - val_acc: 0.8568 122 Epoch 60/1000 123 68s 135ms/step - loss: 0.7864 - acc: 0.8376 - val_loss: 0.7606 - val_acc: 0.8492 124 Epoch 61/1000 125 68s 135ms/step - loss: 0.7827 - acc: 0.8401 - val_loss: 0.7497 - val_acc: 0.8524 126 Epoch 62/1000 127 68s 135ms/step - loss: 0.7804 - acc: 0.8427 - val_loss: 0.7526 - val_acc: 0.8559 128 Epoch 63/1000 129 68s 135ms/step - loss: 0.7766 - acc: 0.8435 - val_loss: 0.7448 - val_acc: 0.8586 130 Epoch 64/1000 131 68s 135ms/step - loss: 0.7792 - acc: 0.8419 - val_loss: 0.7605 - val_acc: 0.8511 132 Epoch 65/1000 133 68s 135ms/step - loss: 0.7790 - acc: 0.8435 - val_loss: 0.7330 - val_acc: 0.8551 134 Epoch 66/1000 135 68s 135ms/step - loss: 0.7748 - acc: 0.8435 - val_loss: 0.7528 - val_acc: 0.8543 136 Epoch 67/1000 137 68s 135ms/step - loss: 0.7733 - acc: 0.8452 - val_loss: 0.7330 - val_acc: 0.8585 138 Epoch 68/1000 139 68s 135ms/step - loss: 0.7759 - acc: 0.8438 - val_loss: 0.7497 - val_acc: 0.8520 140 Epoch 69/1000 141 68s 135ms/step - loss: 0.7680 - acc: 0.8466 - val_loss: 0.7422 - val_acc: 0.8606 142 Epoch 70/1000 143 68s 135ms/step - loss: 0.7662 - acc: 0.8473 - val_loss: 0.7185 - val_acc: 0.8633 144 Epoch 71/1000 145 68s 135ms/step - loss: 0.7658 - acc: 0.8467 - val_loss: 0.7170 - val_acc: 0.8657 146 Epoch 72/1000 147 68s 135ms/step - loss: 0.7681 - acc: 0.8464 - val_loss: 0.7325 - val_acc: 0.8600 148 Epoch 73/1000 149 68s 135ms/step - loss: 0.7658 - acc: 0.8477 - val_loss: 0.7109 - val_acc: 0.8662 150 Epoch 74/1000 151 68s 135ms/step - loss: 0.7616 - acc: 0.8499 - val_loss: 0.7028 - val_acc: 0.8733 152 Epoch 75/1000 153 68s 135ms/step - loss: 0.7621 - acc: 0.8482 - val_loss: 0.7178 - val_acc: 0.8639 154 Epoch 76/1000 155 68s 135ms/step - loss: 0.7606 - acc: 0.8496 - val_loss: 0.7096 - val_acc: 0.8674 156 Epoch 77/1000 157 68s 135ms/step - loss: 0.7590 - acc: 0.8500 - val_loss: 0.7340 - val_acc: 0.8598 158 Epoch 78/1000 159 68s 135ms/step - loss: 0.7639 - acc: 0.8475 - val_loss: 0.7212 - val_acc: 0.8655 160 Epoch 79/1000 161 68s 135ms/step - loss: 0.7613 - acc: 0.8477 - val_loss: 0.7171 - val_acc: 0.8702 162 Epoch 80/1000 163 67s 135ms/step - loss: 0.7562 - acc: 0.8518 - val_loss: 0.7336 - val_acc: 0.8594 164 Epoch 81/1000 165 68s 136ms/step - loss: 0.7532 - acc: 0.8515 - val_loss: 0.7229 - val_acc: 0.8607 166 Epoch 82/1000 167 68s 135ms/step - loss: 0.7511 - acc: 0.8541 - val_loss: 0.7062 - val_acc: 0.8688 168 Epoch 83/1000 169 68s 135ms/step - loss: 0.7510 - acc: 0.8530 - val_loss: 0.6977 - val_acc: 0.8746 170 Epoch 84/1000 171 68s 135ms/step - loss: 0.7562 - acc: 0.8524 - val_loss: 0.7319 - val_acc: 0.8595 172 Epoch 85/1000 173 67s 135ms/step - loss: 0.7527 - acc: 0.8530 - val_loss: 0.7161 - val_acc: 0.8660 174 Epoch 86/1000 175 67s 135ms/step - loss: 0.7523 - acc: 0.8524 - val_loss: 0.7244 - val_acc: 0.8654 176 Epoch 87/1000 177 67s 135ms/step - loss: 0.7505 - acc: 0.8532 - val_loss: 0.7192 - val_acc: 0.8636 178 Epoch 88/1000 179 68s 135ms/step - loss: 0.7528 - acc: 0.8516 - val_loss: 0.7316 - val_acc: 0.8645 180 Epoch 89/1000 181 68s 135ms/step - loss: 0.7480 - acc: 0.8557 - val_loss: 0.7289 - val_acc: 0.8638 182 Epoch 90/1000 183 68s 135ms/step - loss: 0.7435 - acc: 0.8550 - val_loss: 0.7020 - val_acc: 0.8763 184 Epoch 91/1000 185 68s 135ms/step - loss: 0.7466 - acc: 0.8563 - val_loss: 0.6977 - val_acc: 0.8750 186 Epoch 92/1000 187 68s 135ms/step - loss: 0.7438 - acc: 0.8561 - val_loss: 0.7171 - val_acc: 0.8643 188 Epoch 93/1000 189 67s 135ms/step - loss: 0.7438 - acc: 0.8564 - val_loss: 0.7189 - val_acc: 0.8687 190 Epoch 94/1000 191 68s 135ms/step - loss: 0.7442 - acc: 0.8566 - val_loss: 0.7072 - val_acc: 0.8685 192 Epoch 95/1000 193 68s 135ms/step - loss: 0.7468 - acc: 0.8569 - val_loss: 0.7547 - val_acc: 0.8560 194 Epoch 96/1000 195 68s 135ms/step - loss: 0.7468 - acc: 0.8547 - val_loss: 0.7080 - val_acc: 0.8699 196 Epoch 97/1000 197 68s 135ms/step - loss: 0.7455 - acc: 0.8559 - val_loss: 0.7020 - val_acc: 0.8711 198 Epoch 98/1000 199 68s 135ms/step - loss: 0.7427 - acc: 0.8544 - val_loss: 0.7352 - val_acc: 0.8610 200 Epoch 99/1000 201 68s 136ms/step - loss: 0.7424 - acc: 0.8567 - val_loss: 0.7480 - val_acc: 0.8583 202 Epoch 100/1000 203 68s 135ms/step - loss: 0.7397 - acc: 0.8579 - val_loss: 0.7151 - val_acc: 0.8650 204 Epoch 101/1000 205 68s 135ms/step - loss: 0.7447 - acc: 0.8568 - val_loss: 0.7235 - val_acc: 0.8659 206 Epoch 102/1000 207 68s 135ms/step - loss: 0.7367 - acc: 0.8598 - val_loss: 0.7229 - val_acc: 0.8623 208 Epoch 103/1000 209 67s 135ms/step - loss: 0.7371 - acc: 0.8586 - val_loss: 0.6899 - val_acc: 0.8769 210 Epoch 104/1000 211 68s 135ms/step - loss: 0.7401 - acc: 0.8567 - val_loss: 0.7273 - val_acc: 0.8616 212 Epoch 105/1000 213 68s 135ms/step - loss: 0.7382 - acc: 0.8578 - val_loss: 0.7089 - val_acc: 0.8682 214 Epoch 106/1000 215 68s 135ms/step - loss: 0.7386 - acc: 0.8580 - val_loss: 0.7158 - val_acc: 0.8659 216 Epoch 107/1000 217 67s 135ms/step - loss: 0.7361 - acc: 0.8584 - val_loss: 0.7147 - val_acc: 0.8701 218 Epoch 108/1000 219 67s 135ms/step - loss: 0.7408 - acc: 0.8580 - val_loss: 0.7083 - val_acc: 0.8686 220 Epoch 109/1000 221 68s 135ms/step - loss: 0.7362 - acc: 0.8599 - val_loss: 0.7096 - val_acc: 0.8703 222 Epoch 110/1000 223 67s 135ms/step - loss: 0.7335 - acc: 0.8600 - val_loss: 0.7148 - val_acc: 0.8683 224 Epoch 111/1000 225 67s 135ms/step - loss: 0.7334 - acc: 0.8626 - val_loss: 0.7050 - val_acc: 0.8741 226 Epoch 112/1000 227 68s 135ms/step - loss: 0.7360 - acc: 0.8586 - val_loss: 0.7150 - val_acc: 0.8682 228 Epoch 113/1000 229 68s 136ms/step - loss: 0.7371 - acc: 0.8583 - val_loss: 0.7447 - val_acc: 0.8583 230 Epoch 114/1000 231 68s 135ms/step - loss: 0.7352 - acc: 0.8599 - val_loss: 0.6937 - val_acc: 0.8755 232 Epoch 115/1000 233 68s 135ms/step - loss: 0.7314 - acc: 0.8604 - val_loss: 0.7140 - val_acc: 0.8684 234 Epoch 116/1000 235 68s 135ms/step - loss: 0.7333 - acc: 0.8607 - val_loss: 0.7305 - val_acc: 0.8686 236 Epoch 117/1000 237 68s 135ms/step - loss: 0.7277 - acc: 0.8617 - val_loss: 0.7002 - val_acc: 0.8719 238 Epoch 118/1000 239 68s 135ms/step - loss: 0.7356 - acc: 0.8580 - val_loss: 0.6926 - val_acc: 0.8763 240 Epoch 119/1000 241 68s 135ms/step - loss: 0.7244 - acc: 0.8642 - val_loss: 0.7079 - val_acc: 0.8669 242 Epoch 120/1000 243 68s 136ms/step - loss: 0.7302 - acc: 0.8613 - val_loss: 0.7113 - val_acc: 0.8695 244 Epoch 121/1000 245 68s 135ms/step - loss: 0.7340 - acc: 0.8608 - val_loss: 0.7415 - val_acc: 0.8554 246 Epoch 122/1000 247 68s 135ms/step - loss: 0.7304 - acc: 0.8608 - val_loss: 0.6978 - val_acc: 0.8760 248 Epoch 123/1000 249 68s 135ms/step - loss: 0.7263 - acc: 0.8630 - val_loss: 0.6974 - val_acc: 0.8734 250 Epoch 124/1000 251 68s 135ms/step - loss: 0.7261 - acc: 0.8625 - val_loss: 0.7109 - val_acc: 0.8715 252 Epoch 125/1000 253 67s 135ms/step - loss: 0.7313 - acc: 0.8623 - val_loss: 0.6946 - val_acc: 0.8745 254 Epoch 126/1000 255 67s 135ms/step - loss: 0.7277 - acc: 0.8620 - val_loss: 0.7178 - val_acc: 0.8685 256 Epoch 127/1000 257 68s 135ms/step - loss: 0.7231 - acc: 0.8653 - val_loss: 0.6999 - val_acc: 0.8762 258 Epoch 128/1000 259 68s 135ms/step - loss: 0.7252 - acc: 0.8635 - val_loss: 0.7009 - val_acc: 0.8718 260 Epoch 129/1000 261 68s 135ms/step - loss: 0.7284 - acc: 0.8626 - val_loss: 0.7148 - val_acc: 0.8682 262 Epoch 130/1000 263 68s 135ms/step - loss: 0.7236 - acc: 0.8646 - val_loss: 0.6945 - val_acc: 0.8746 264 Epoch 131/1000 265 68s 135ms/step - loss: 0.7203 - acc: 0.8653 - val_loss: 0.7002 - val_acc: 0.8705 266 Epoch 132/1000 267 68s 135ms/step - loss: 0.7248 - acc: 0.8626 - val_loss: 0.7097 - val_acc: 0.8718 268 Epoch 133/1000 269 67s 135ms/step - loss: 0.7190 - acc: 0.8660 - val_loss: 0.6993 - val_acc: 0.8722 270 Epoch 134/1000 271 68s 136ms/step - loss: 0.7206 - acc: 0.8645 - val_loss: 0.7042 - val_acc: 0.8763 272 Epoch 135/1000 273 68s 135ms/step - loss: 0.7248 - acc: 0.8637 - val_loss: 0.6742 - val_acc: 0.8844 274 Epoch 136/1000 275 68s 135ms/step - loss: 0.7181 - acc: 0.8650 - val_loss: 0.6972 - val_acc: 0.8721 276 Epoch 137/1000 277 67s 135ms/step - loss: 0.7170 - acc: 0.8667 - val_loss: 0.7270 - val_acc: 0.8642 278 Epoch 138/1000 279 68s 135ms/step - loss: 0.7209 - acc: 0.8649 - val_loss: 0.7107 - val_acc: 0.8687 280 Epoch 139/1000 281 68s 136ms/step - loss: 0.7195 - acc: 0.8652 - val_loss: 0.6993 - val_acc: 0.8752 282 Epoch 140/1000 283 68s 135ms/step - loss: 0.7229 - acc: 0.8647 - val_loss: 0.6949 - val_acc: 0.8800 284 Epoch 141/1000 285 67s 135ms/step - loss: 0.7154 - acc: 0.8674 - val_loss: 0.6828 - val_acc: 0.8780 286 Epoch 142/1000 287 67s 135ms/step - loss: 0.7146 - acc: 0.8675 - val_loss: 0.6799 - val_acc: 0.8818 288 Epoch 143/1000 289 68s 135ms/step - loss: 0.7131 - acc: 0.8679 - val_loss: 0.7237 - val_acc: 0.8655 290 Epoch 144/1000 291 68s 135ms/step - loss: 0.7167 - acc: 0.8662 - val_loss: 0.7140 - val_acc: 0.8696 292 Epoch 145/1000 293 68s 136ms/step - loss: 0.7131 - acc: 0.8677 - val_loss: 0.7086 - val_acc: 0.8696 294 Epoch 146/1000 295 67s 135ms/step - loss: 0.7184 - acc: 0.8665 - val_loss: 0.7058 - val_acc: 0.8729 296 Epoch 147/1000 297 68s 135ms/step - loss: 0.7179 - acc: 0.8654 - val_loss: 0.7021 - val_acc: 0.8741 298 Epoch 148/1000 299 67s 135ms/step - loss: 0.7176 - acc: 0.8671 - val_loss: 0.6892 - val_acc: 0.8795 300 Epoch 149/1000 301 68s 135ms/step - loss: 0.7123 - acc: 0.8685 - val_loss: 0.7027 - val_acc: 0.8700 302 Epoch 150/1000 303 68s 136ms/step - loss: 0.7146 - acc: 0.8671 - val_loss: 0.6926 - val_acc: 0.8755 304 Epoch 151/1000 305 68s 135ms/step - loss: 0.7122 - acc: 0.8651 - val_loss: 0.7179 - val_acc: 0.8685 306 Epoch 152/1000 307 68s 136ms/step - loss: 0.7149 - acc: 0.8675 - val_loss: 0.7136 - val_acc: 0.8690 308 Epoch 153/1000 309 68s 135ms/step - loss: 0.7141 - acc: 0.8669 - val_loss: 0.7193 - val_acc: 0.8672 310 Epoch 154/1000 311 68s 136ms/step - loss: 0.7084 - acc: 0.8684 - val_loss: 0.6779 - val_acc: 0.8826 312 Epoch 155/1000 313 67s 135ms/step - loss: 0.7143 - acc: 0.8671 - val_loss: 0.7092 - val_acc: 0.8685 314 Epoch 156/1000 315 68s 136ms/step - loss: 0.7118 - acc: 0.8674 - val_loss: 0.7010 - val_acc: 0.8732 316 Epoch 157/1000 317 69s 138ms/step - loss: 0.7126 - acc: 0.8677 - val_loss: 0.6918 - val_acc: 0.8766 318 Epoch 158/1000 319 68s 137ms/step - loss: 0.7064 - acc: 0.8701 - val_loss: 0.7253 - val_acc: 0.8636 320 Epoch 159/1000 321 68s 137ms/step - loss: 0.7107 - acc: 0.8674 - val_loss: 0.7008 - val_acc: 0.8745 322 Epoch 160/1000 323 68s 137ms/step - loss: 0.7097 - acc: 0.8698 - val_loss: 0.6922 - val_acc: 0.8771 324 Epoch 161/1000 325 68s 137ms/step - loss: 0.7091 - acc: 0.8675 - val_loss: 0.6786 - val_acc: 0.8813 326 Epoch 162/1000 327 69s 138ms/step - loss: 0.7117 - acc: 0.8680 - val_loss: 0.7017 - val_acc: 0.8740 328 Epoch 163/1000 329 69s 137ms/step - loss: 0.7110 - acc: 0.8681 - val_loss: 0.6862 - val_acc: 0.8800 330 Epoch 164/1000 331 68s 137ms/step - loss: 0.7099 - acc: 0.8693 - val_loss: 0.7053 - val_acc: 0.8709 332 Epoch 165/1000 333 69s 138ms/step - loss: 0.7104 - acc: 0.8694 - val_loss: 0.6846 - val_acc: 0.8828 334 Epoch 166/1000 335 68s 136ms/step - loss: 0.7078 - acc: 0.8715 - val_loss: 0.6968 - val_acc: 0.8749 336 Epoch 167/1000 337 68s 136ms/step - loss: 0.7076 - acc: 0.8719 - val_loss: 0.6872 - val_acc: 0.8782 338 Epoch 168/1000 339 68s 136ms/step - loss: 0.7099 - acc: 0.8679 - val_loss: 0.6928 - val_acc: 0.8755 340 Epoch 169/1000 341 68s 136ms/step - loss: 0.7101 - acc: 0.8678 - val_loss: 0.6947 - val_acc: 0.8786 342 Epoch 170/1000 343 68s 137ms/step - loss: 0.7097 - acc: 0.8717 - val_loss: 0.6886 - val_acc: 0.8789 344 Epoch 171/1000 345 69s 137ms/step - loss: 0.7070 - acc: 0.8702 - val_loss: 0.6878 - val_acc: 0.8793 346 Epoch 172/1000 347 69s 137ms/step - loss: 0.7117 - acc: 0.8679 - val_loss: 0.6783 - val_acc: 0.8836 348 Epoch 173/1000 349 68s 137ms/step - loss: 0.7102 - acc: 0.8687 - val_loss: 0.6709 - val_acc: 0.8865 350 Epoch 174/1000 351 69s 137ms/step - loss: 0.7038 - acc: 0.8717 - val_loss: 0.6839 - val_acc: 0.8804 352 Epoch 175/1000 353 68s 137ms/step - loss: 0.7062 - acc: 0.8713 - val_loss: 0.6934 - val_acc: 0.8780 354 Epoch 176/1000 355 68s 137ms/step - loss: 0.7092 - acc: 0.8684 - val_loss: 0.7045 - val_acc: 0.8737 356 Epoch 177/1000 357 68s 137ms/step - loss: 0.7048 - acc: 0.8703 - val_loss: 0.6935 - val_acc: 0.8764 358 Epoch 178/1000 359 68s 137ms/step - loss: 0.7056 - acc: 0.8713 - val_loss: 0.6825 - val_acc: 0.8800 360 Epoch 179/1000 361 69s 137ms/step - loss: 0.7027 - acc: 0.8722 - val_loss: 0.6860 - val_acc: 0.8812 362 Epoch 180/1000 363 67s 135ms/step - loss: 0.7056 - acc: 0.8699 - val_loss: 0.6882 - val_acc: 0.8762 364 Epoch 181/1000 365 67s 135ms/step - loss: 0.6974 - acc: 0.8745 - val_loss: 0.7030 - val_acc: 0.8704 366 Epoch 182/1000 367 67s 135ms/step - loss: 0.7028 - acc: 0.8714 - val_loss: 0.6754 - val_acc: 0.8860 368 Epoch 183/1000 369 67s 135ms/step - loss: 0.7022 - acc: 0.8715 - val_loss: 0.6635 - val_acc: 0.8842 370 Epoch 184/1000 371 68s 136ms/step - loss: 0.7034 - acc: 0.8704 - val_loss: 0.6905 - val_acc: 0.8762 372 Epoch 185/1000 373 67s 135ms/step - loss: 0.7058 - acc: 0.8709 - val_loss: 0.7066 - val_acc: 0.8740 374 Epoch 186/1000 375 67s 135ms/step - loss: 0.7016 - acc: 0.8726 - val_loss: 0.6842 - val_acc: 0.8784 376 Epoch 187/1000 377 67s 135ms/step - loss: 0.6999 - acc: 0.8719 - val_loss: 0.7051 - val_acc: 0.8731 378 Epoch 188/1000 379 67s 135ms/step - loss: 0.7026 - acc: 0.8710 - val_loss: 0.6811 - val_acc: 0.8811 380 Epoch 189/1000 381 68s 135ms/step - loss: 0.7040 - acc: 0.8711 - val_loss: 0.6794 - val_acc: 0.8786 382 Epoch 190/1000 383 67s 135ms/step - loss: 0.7004 - acc: 0.8728 - val_loss: 0.6594 - val_acc: 0.8916 384 Epoch 191/1000 385 68s 136ms/step - loss: 0.6982 - acc: 0.8747 - val_loss: 0.6616 - val_acc: 0.8850 386 Epoch 192/1000 387 68s 135ms/step - loss: 0.7036 - acc: 0.8718 - val_loss: 0.6959 - val_acc: 0.8730 388 Epoch 193/1000 389 67s 135ms/step - loss: 0.7017 - acc: 0.8708 - val_loss: 0.6671 - val_acc: 0.8862 390 Epoch 194/1000 391 67s 135ms/step - loss: 0.6982 - acc: 0.8738 - val_loss: 0.6885 - val_acc: 0.8790 392 Epoch 195/1000 393 68s 136ms/step - loss: 0.6996 - acc: 0.8714 - val_loss: 0.6892 - val_acc: 0.8770 394 Epoch 196/1000 395 68s 136ms/step - loss: 0.7026 - acc: 0.8706 - val_loss: 0.6824 - val_acc: 0.8792 396 Epoch 197/1000 397 68s 136ms/step - loss: 0.7061 - acc: 0.8695 - val_loss: 0.6893 - val_acc: 0.8793 398 Epoch 198/1000 399 68s 135ms/step - loss: 0.7023 - acc: 0.8714 - val_loss: 0.6797 - val_acc: 0.8819 400 Epoch 199/1000 401 67s 135ms/step - loss: 0.7021 - acc: 0.8726 - val_loss: 0.6969 - val_acc: 0.8754 402 Epoch 200/1000 403 68s 136ms/step - loss: 0.7023 - acc: 0.8711 - val_loss: 0.6922 - val_acc: 0.8758 404 Epoch 201/1000 405 68s 135ms/step - loss: 0.7050 - acc: 0.8705 - val_loss: 0.6879 - val_acc: 0.8792 406 Epoch 202/1000 407 68s 135ms/step - loss: 0.7012 - acc: 0.8713 - val_loss: 0.6756 - val_acc: 0.8845 408 Epoch 203/1000 409 68s 136ms/step - loss: 0.7021 - acc: 0.8726 - val_loss: 0.6542 - val_acc: 0.8904 410 Epoch 204/1000 411 68s 136ms/step - loss: 0.6981 - acc: 0.8741 - val_loss: 0.7060 - val_acc: 0.8739 412 Epoch 205/1000 413 68s 135ms/step - loss: 0.7008 - acc: 0.8718 - val_loss: 0.6938 - val_acc: 0.8741 414 Epoch 206/1000 415 68s 136ms/step - loss: 0.6974 - acc: 0.8725 - val_loss: 0.6786 - val_acc: 0.8833 416 Epoch 207/1000 417 67s 135ms/step - loss: 0.6938 - acc: 0.8739 - val_loss: 0.6928 - val_acc: 0.8750 418 Epoch 208/1000 419 68s 135ms/step - loss: 0.7075 - acc: 0.8690 - val_loss: 0.6770 - val_acc: 0.8806 420 Epoch 209/1000 421 68s 136ms/step - loss: 0.6978 - acc: 0.8723 - val_loss: 0.6913 - val_acc: 0.8812 422 Epoch 210/1000 423 67s 135ms/step - loss: 0.6974 - acc: 0.8727 - val_loss: 0.6764 - val_acc: 0.8827 424 Epoch 211/1000 425 68s 136ms/step - loss: 0.6998 - acc: 0.8724 - val_loss: 0.7139 - val_acc: 0.8700 426 Epoch 212/1000 427 68s 136ms/step - loss: 0.6975 - acc: 0.8740 - val_loss: 0.6851 - val_acc: 0.8805 428 Epoch 213/1000 429 68s 136ms/step - loss: 0.7032 - acc: 0.8704 - val_loss: 0.7101 - val_acc: 0.8712 430 Epoch 214/1000 431 68s 135ms/step - loss: 0.6979 - acc: 0.8732 - val_loss: 0.7108 - val_acc: 0.8756 432 Epoch 215/1000 433 68s 136ms/step - loss: 0.6986 - acc: 0.8749 - val_loss: 0.7092 - val_acc: 0.8701 434 Epoch 216/1000 435 68s 135ms/step - loss: 0.6921 - acc: 0.8757 - val_loss: 0.6868 - val_acc: 0.8792 436 Epoch 217/1000 437 68s 135ms/step - loss: 0.6930 - acc: 0.8755 - val_loss: 0.7097 - val_acc: 0.8721 438 Epoch 218/1000 439 68s 135ms/step - loss: 0.7039 - acc: 0.8713 - val_loss: 0.6901 - val_acc: 0.8789 440 Epoch 219/1000 441 68s 136ms/step - loss: 0.6931 - acc: 0.8757 - val_loss: 0.6927 - val_acc: 0.8793 442 Epoch 220/1000 443 68s 136ms/step - loss: 0.6991 - acc: 0.8734 - val_loss: 0.6946 - val_acc: 0.8777 444 Epoch 221/1000 445 68s 135ms/step - loss: 0.6950 - acc: 0.8739 - val_loss: 0.6740 - val_acc: 0.8819 446 Epoch 222/1000 447 68s 136ms/step - loss: 0.6970 - acc: 0.8739 - val_loss: 0.6847 - val_acc: 0.8787 448 Epoch 223/1000 449 68s 136ms/step - loss: 0.7006 - acc: 0.8719 - val_loss: 0.7139 - val_acc: 0.8707 450 Epoch 224/1000 451 68s 135ms/step - loss: 0.7014 - acc: 0.8720 - val_loss: 0.6901 - val_acc: 0.8768 452 Epoch 225/1000 453 68s 136ms/step - loss: 0.6981 - acc: 0.8739 - val_loss: 0.6758 - val_acc: 0.8853 454 Epoch 226/1000 455 68s 136ms/step - loss: 0.6921 - acc: 0.8739 - val_loss: 0.6743 - val_acc: 0.8844 456 Epoch 227/1000 457 68s 136ms/step - loss: 0.6983 - acc: 0.8734 - val_loss: 0.7031 - val_acc: 0.8736 458 Epoch 228/1000 459 68s 136ms/step - loss: 0.6954 - acc: 0.8734 - val_loss: 0.7181 - val_acc: 0.8663 460 Epoch 229/1000 461 68s 136ms/step - loss: 0.6893 - acc: 0.8759 - val_loss: 0.6982 - val_acc: 0.8740 462 Epoch 230/1000 463 68s 135ms/step - loss: 0.6964 - acc: 0.8736 - val_loss: 0.6927 - val_acc: 0.8748 464 Epoch 231/1000 465 68s 136ms/step - loss: 0.6987 - acc: 0.8742 - val_loss: 0.6898 - val_acc: 0.8772 466 Epoch 232/1000 467 67s 135ms/step - loss: 0.6980 - acc: 0.8731 - val_loss: 0.6862 - val_acc: 0.8810 468 Epoch 233/1000 469 68s 136ms/step - loss: 0.6975 - acc: 0.8749 - val_loss: 0.6987 - val_acc: 0.8783 470 Epoch 234/1000 471 67s 135ms/step - loss: 0.6892 - acc: 0.8778 - val_loss: 0.6902 - val_acc: 0.8773 472 Epoch 235/1000 473 68s 135ms/step - loss: 0.6925 - acc: 0.8762 - val_loss: 0.6787 - val_acc: 0.8799 474 Epoch 236/1000 475 68s 136ms/step - loss: 0.6954 - acc: 0.8735 - val_loss: 0.6910 - val_acc: 0.8797 476 Epoch 237/1000 477 68s 136ms/step - loss: 0.6963 - acc: 0.8746 - val_loss: 0.6886 - val_acc: 0.8785 478 Epoch 238/1000 479 68s 136ms/step - loss: 0.6950 - acc: 0.8764 - val_loss: 0.7008 - val_acc: 0.8766 480 Epoch 239/1000 481 67s 135ms/step - loss: 0.6969 - acc: 0.8749 - val_loss: 0.7100 - val_acc: 0.8736 482 Epoch 240/1000 483 68s 136ms/step - loss: 0.6905 - acc: 0.8757 - val_loss: 0.6971 - val_acc: 0.8733 484 Epoch 241/1000 485 68s 136ms/step - loss: 0.6912 - acc: 0.8740 - val_loss: 0.6809 - val_acc: 0.8805 486 Epoch 242/1000 487 68s 136ms/step - loss: 0.6949 - acc: 0.8729 - val_loss: 0.6903 - val_acc: 0.8760 488 Epoch 243/1000 489 69s 138ms/step - loss: 0.6938 - acc: 0.8753 - val_loss: 0.6809 - val_acc: 0.8823 490 Epoch 244/1000 491 68s 136ms/step - loss: 0.6912 - acc: 0.8754 - val_loss: 0.6700 - val_acc: 0.8829 492 Epoch 245/1000 493 69s 137ms/step - loss: 0.6939 - acc: 0.8766 - val_loss: 0.6691 - val_acc: 0.8847 494 Epoch 246/1000 495 69s 138ms/step - loss: 0.6885 - acc: 0.8756 - val_loss: 0.7018 - val_acc: 0.8782 496 Epoch 247/1000 497 69s 138ms/step - loss: 0.6916 - acc: 0.8766 - val_loss: 0.6896 - val_acc: 0.8789 498 Epoch 248/1000 499 69s 138ms/step - loss: 0.6918 - acc: 0.8751 - val_loss: 0.7025 - val_acc: 0.8735 500 Epoch 249/1000 501 69s 138ms/step - loss: 0.6944 - acc: 0.8756 - val_loss: 0.6754 - val_acc: 0.8811 502 Epoch 250/1000 503 69s 138ms/step - loss: 0.6845 - acc: 0.8766 - val_loss: 0.6937 - val_acc: 0.8776 504 Epoch 251/1000 505 69s 138ms/step - loss: 0.6915 - acc: 0.8753 - val_loss: 0.6944 - val_acc: 0.8773 506 Epoch 252/1000 507 69s 138ms/step - loss: 0.6923 - acc: 0.8751 - val_loss: 0.6830 - val_acc: 0.8790 508 Epoch 253/1000 509 69s 138ms/step - loss: 0.6889 - acc: 0.8756 - val_loss: 0.7251 - val_acc: 0.8658 510 Epoch 254/1000 511 69s 137ms/step - loss: 0.6963 - acc: 0.8741 - val_loss: 0.6919 - val_acc: 0.8777 512 Epoch 255/1000 513 69s 137ms/step - loss: 0.6920 - acc: 0.8759 - val_loss: 0.7098 - val_acc: 0.8706 514 Epoch 256/1000 515 69s 138ms/step - loss: 0.6896 - acc: 0.8750 - val_loss: 0.6964 - val_acc: 0.8772 516 Epoch 257/1000 517 69s 137ms/step - loss: 0.6891 - acc: 0.8757 - val_loss: 0.6604 - val_acc: 0.8871 518 Epoch 258/1000 519 69s 137ms/step - loss: 0.6932 - acc: 0.8753 - val_loss: 0.6820 - val_acc: 0.8803 520 Epoch 259/1000 521 69s 138ms/step - loss: 0.6863 - acc: 0.8767 - val_loss: 0.7197 - val_acc: 0.8710 522 Epoch 260/1000 523 68s 137ms/step - loss: 0.6900 - acc: 0.8762 - val_loss: 0.6588 - val_acc: 0.8907 524 Epoch 261/1000 525 68s 137ms/step - loss: 0.6912 - acc: 0.8750 - val_loss: 0.6815 - val_acc: 0.8833 526 Epoch 262/1000 527 69s 137ms/step - loss: 0.6893 - acc: 0.8750 - val_loss: 0.6795 - val_acc: 0.8831 528 Epoch 263/1000 529 69s 137ms/step - loss: 0.6920 - acc: 0.8755 - val_loss: 0.6830 - val_acc: 0.8822 530 Epoch 264/1000 531 68s 137ms/step - loss: 0.6924 - acc: 0.8743 - val_loss: 0.6989 - val_acc: 0.8762 532 Epoch 265/1000 533 69s 138ms/step - loss: 0.6905 - acc: 0.8763 - val_loss: 0.6836 - val_acc: 0.8806 534 Epoch 266/1000 535 69s 137ms/step - loss: 0.6883 - acc: 0.8759 - val_loss: 0.6731 - val_acc: 0.8855 536 Epoch 267/1000 537 69s 138ms/step - loss: 0.6852 - acc: 0.8768 - val_loss: 0.6898 - val_acc: 0.8794 538 Epoch 268/1000 539 69s 138ms/step - loss: 0.6901 - acc: 0.8754 - val_loss: 0.6825 - val_acc: 0.8804 540 Epoch 269/1000 541 69s 138ms/step - loss: 0.6929 - acc: 0.8742 - val_loss: 0.6916 - val_acc: 0.8745 542 Epoch 270/1000 543 69s 138ms/step - loss: 0.6870 - acc: 0.8772 - val_loss: 0.6772 - val_acc: 0.8804 544 Epoch 271/1000 545 68s 137ms/step - loss: 0.6891 - acc: 0.8761 - val_loss: 0.6891 - val_acc: 0.8756 546 Epoch 272/1000 547 68s 137ms/step - loss: 0.6863 - acc: 0.8768 - val_loss: 0.6851 - val_acc: 0.8813 548 Epoch 273/1000 549 68s 137ms/step - loss: 0.6891 - acc: 0.8765 - val_loss: 0.6921 - val_acc: 0.8776 550 Epoch 274/1000 551 69s 138ms/step - loss: 0.6853 - acc: 0.8779 - val_loss: 0.6785 - val_acc: 0.8820 552 Epoch 275/1000 553 69s 138ms/step - loss: 0.6879 - acc: 0.8767 - val_loss: 0.6994 - val_acc: 0.8728 554 Epoch 276/1000 555 69s 138ms/step - loss: 0.6869 - acc: 0.8767 - val_loss: 0.6949 - val_acc: 0.8732 556 Epoch 277/1000 557 69s 137ms/step - loss: 0.6796 - acc: 0.8793 - val_loss: 0.6813 - val_acc: 0.8820 558 Epoch 278/1000 559 69s 138ms/step - loss: 0.6909 - acc: 0.8746 - val_loss: 0.6745 - val_acc: 0.8841 560 Epoch 279/1000 561 69s 138ms/step - loss: 0.6837 - acc: 0.8777 - val_loss: 0.6951 - val_acc: 0.8761 562 Epoch 280/1000 563 69s 137ms/step - loss: 0.6882 - acc: 0.8769 - val_loss: 0.6828 - val_acc: 0.8805 564 Epoch 281/1000 565 69s 138ms/step - loss: 0.6909 - acc: 0.8767 - val_loss: 0.6801 - val_acc: 0.8836 566 Epoch 282/1000 567 69s 137ms/step - loss: 0.6890 - acc: 0.8743 - val_loss: 0.6931 - val_acc: 0.8757 568 Epoch 283/1000 569 69s 138ms/step - loss: 0.6871 - acc: 0.8772 - val_loss: 0.6791 - val_acc: 0.8837 570 Epoch 284/1000 571 69s 138ms/step - loss: 0.6846 - acc: 0.8796 - val_loss: 0.7228 - val_acc: 0.8674 572 Epoch 285/1000 573 69s 138ms/step - loss: 0.6857 - acc: 0.8792 - val_loss: 0.7068 - val_acc: 0.8735 574 Epoch 286/1000 575 69s 138ms/step - loss: 0.6891 - acc: 0.8759 - val_loss: 0.7089 - val_acc: 0.8735 576 Epoch 287/1000 577 69s 137ms/step - loss: 0.6927 - acc: 0.8770 - val_loss: 0.6755 - val_acc: 0.8823 578 Epoch 288/1000 579 69s 137ms/step - loss: 0.6878 - acc: 0.8770 - val_loss: 0.6939 - val_acc: 0.8761 580 Epoch 289/1000 581 68s 137ms/step - loss: 0.6858 - acc: 0.8795 - val_loss: 0.6844 - val_acc: 0.8829 582 Epoch 290/1000 583 69s 137ms/step - loss: 0.6901 - acc: 0.8774 - val_loss: 0.6603 - val_acc: 0.8877 584 Epoch 291/1000 585 69s 138ms/step - loss: 0.6827 - acc: 0.8805 - val_loss: 0.6700 - val_acc: 0.8877 586 Epoch 292/1000 587 69s 137ms/step - loss: 0.6875 - acc: 0.8770 - val_loss: 0.6843 - val_acc: 0.8802 588 Epoch 293/1000 589 69s 138ms/step - loss: 0.6861 - acc: 0.8795 - val_loss: 0.6889 - val_acc: 0.8812 590 Epoch 294/1000 591 68s 137ms/step - loss: 0.6896 - acc: 0.8759 - val_loss: 0.6688 - val_acc: 0.8874 592 Epoch 295/1000 593 69s 138ms/step - loss: 0.6792 - acc: 0.8805 - val_loss: 0.6813 - val_acc: 0.8802 594 Epoch 296/1000 595 69s 138ms/step - loss: 0.6946 - acc: 0.8733 - val_loss: 0.6697 - val_acc: 0.8858 596 Epoch 297/1000 597 69s 138ms/step - loss: 0.6887 - acc: 0.8755 - val_loss: 0.6707 - val_acc: 0.8848 598 Epoch 298/1000 599 69s 138ms/step - loss: 0.6875 - acc: 0.8765 - val_loss: 0.7025 - val_acc: 0.8718 600 Epoch 299/1000 601 69s 137ms/step - loss: 0.6853 - acc: 0.8789 - val_loss: 0.6842 - val_acc: 0.8805 602 Epoch 300/1000 603 69s 138ms/step - loss: 0.6806 - acc: 0.8809 - val_loss: 0.6948 - val_acc: 0.8809 604 Epoch 301/1000 605 lr changed to 0.010000000149011612 606 69s 138ms/step - loss: 0.5763 - acc: 0.9142 - val_loss: 0.5780 - val_acc: 0.9169 607 Epoch 302/1000 608 69s 138ms/step - loss: 0.5127 - acc: 0.9355 - val_loss: 0.5618 - val_acc: 0.9209 609 Epoch 303/1000 610 68s 137ms/step - loss: 0.4950 - acc: 0.9401 - val_loss: 0.5561 - val_acc: 0.9223 611 Epoch 304/1000 612 68s 137ms/step - loss: 0.4744 - acc: 0.9449 - val_loss: 0.5485 - val_acc: 0.9229 613 Epoch 305/1000 614 68s 137ms/step - loss: 0.4602 - acc: 0.9489 - val_loss: 0.5469 - val_acc: 0.9206 615 Epoch 306/1000 616 69s 137ms/step - loss: 0.4533 - acc: 0.9479 - val_loss: 0.5368 - val_acc: 0.9209 617 Epoch 307/1000 618 69s 137ms/step - loss: 0.4463 - acc: 0.9498 - val_loss: 0.5294 - val_acc: 0.9230 619 Epoch 308/1000 620 69s 137ms/step - loss: 0.4371 - acc: 0.9508 - val_loss: 0.5304 - val_acc: 0.9228 621 Epoch 309/1000 622 69s 137ms/step - loss: 0.4276 - acc: 0.9515 - val_loss: 0.5217 - val_acc: 0.9236 623 Epoch 310/1000 624 68s 136ms/step - loss: 0.4185 - acc: 0.9542 - val_loss: 0.5202 - val_acc: 0.9235 625 Epoch 311/1000 626 69s 138ms/step - loss: 0.4079 - acc: 0.9563 - val_loss: 0.5213 - val_acc: 0.9224 627 Epoch 312/1000 628 69s 137ms/step - loss: 0.4028 - acc: 0.9559 - val_loss: 0.5149 - val_acc: 0.9241 629 Epoch 313/1000 630 68s 136ms/step - loss: 0.3940 - acc: 0.9582 - val_loss: 0.5182 - val_acc: 0.9229 631 Epoch 314/1000 632 69s 138ms/step - loss: 0.3913 - acc: 0.9584 - val_loss: 0.5063 - val_acc: 0.9222 633 Epoch 315/1000 634 69s 138ms/step - loss: 0.3815 - acc: 0.9599 - val_loss: 0.5065 - val_acc: 0.9242 635 Epoch 316/1000 636 69s 138ms/step - loss: 0.3779 - acc: 0.9596 - val_loss: 0.5105 - val_acc: 0.9197 637 Epoch 317/1000 638 69s 138ms/step - loss: 0.3734 - acc: 0.9607 - val_loss: 0.4951 - val_acc: 0.9242 639 Epoch 318/1000 640 69s 138ms/step - loss: 0.3668 - acc: 0.9608 - val_loss: 0.4984 - val_acc: 0.9226 641 Epoch 319/1000 642 68s 137ms/step - loss: 0.3600 - acc: 0.9628 - val_loss: 0.5003 - val_acc: 0.9195 643 Epoch 320/1000 644 68s 137ms/step - loss: 0.3562 - acc: 0.9622 - val_loss: 0.4927 - val_acc: 0.9206 645 Epoch 321/1000 646 69s 138ms/step - loss: 0.3551 - acc: 0.9619 - val_loss: 0.4883 - val_acc: 0.9233 647 Epoch 322/1000 648 69s 138ms/step - loss: 0.3467 - acc: 0.9635 - val_loss: 0.4820 - val_acc: 0.9247 649 Epoch 323/1000 650 69s 138ms/step - loss: 0.3468 - acc: 0.9621 - val_loss: 0.4795 - val_acc: 0.9225 651 Epoch 324/1000 652 68s 136ms/step - loss: 0.3386 - acc: 0.9651 - val_loss: 0.4927 - val_acc: 0.9205 653 Epoch 325/1000 654 68s 135ms/step - loss: 0.3368 - acc: 0.9644 - val_loss: 0.4823 - val_acc: 0.9205 655 Epoch 326/1000 656 68s 136ms/step - loss: 0.3284 - acc: 0.9667 - val_loss: 0.4691 - val_acc: 0.9236 657 Epoch 327/1000 658 69s 138ms/step - loss: 0.3255 - acc: 0.9658 - val_loss: 0.4734 - val_acc: 0.9252 659 Epoch 328/1000 660 68s 136ms/step - loss: 0.3255 - acc: 0.9648 - val_loss: 0.4795 - val_acc: 0.9230 661 Epoch 329/1000 662 68s 136ms/step - loss: 0.3257 - acc: 0.9638 - val_loss: 0.4681 - val_acc: 0.9223 663 Epoch 330/1000 664 68s 136ms/step - loss: 0.3181 - acc: 0.9648 - val_loss: 0.4670 - val_acc: 0.9215 665 Epoch 331/1000 666 68s 136ms/step - loss: 0.3138 - acc: 0.9660 - val_loss: 0.4821 - val_acc: 0.9185 667 Epoch 332/1000 668 68s 136ms/step - loss: 0.3140 - acc: 0.9648 - val_loss: 0.4727 - val_acc: 0.9202 669 Epoch 333/1000 670 69s 137ms/step - loss: 0.3102 - acc: 0.9663 - val_loss: 0.4632 - val_acc: 0.9231 671 Epoch 334/1000 672 68s 137ms/step - loss: 0.3085 - acc: 0.9663 - val_loss: 0.4611 - val_acc: 0.9240 673 Epoch 335/1000 674 68s 137ms/step - loss: 0.3019 - acc: 0.9679 - val_loss: 0.4614 - val_acc: 0.9238 675 Epoch 336/1000 676 69s 138ms/step - loss: 0.3046 - acc: 0.9654 - val_loss: 0.4635 - val_acc: 0.9202 677 Epoch 337/1000 678 68s 137ms/step - loss: 0.3015 - acc: 0.9660 - val_loss: 0.4599 - val_acc: 0.9228 679 Epoch 338/1000 680 69s 137ms/step - loss: 0.2992 - acc: 0.9662 - val_loss: 0.4577 - val_acc: 0.9207 681 Epoch 339/1000 682 69s 138ms/step - loss: 0.2942 - acc: 0.9669 - val_loss: 0.4702 - val_acc: 0.9172 683 Epoch 340/1000 684 69s 137ms/step - loss: 0.2924 - acc: 0.9675 - val_loss: 0.4545 - val_acc: 0.9211 685 ... 686 Epoch 597/1000 687 68s 135ms/step - loss: 0.2366 - acc: 0.9703 - val_loss: 0.4557 - val_acc: 0.9103 688 Epoch 598/1000 689 68s 135ms/step - loss: 0.2399 - acc: 0.9697 - val_loss: 0.4449 - val_acc: 0.9117 690 Epoch 599/1000 691 67s 135ms/step - loss: 0.2397 - acc: 0.9689 - val_loss: 0.4359 - val_acc: 0.9147 692 Epoch 600/1000 693 68s 136ms/step - loss: 0.2341 - acc: 0.9717 - val_loss: 0.4224 - val_acc: 0.9169 694 Epoch 601/1000 695 lr changed to 0.0009999999776482583 696 68s 136ms/step - loss: 0.2082 - acc: 0.9813 - val_loss: 0.3916 - val_acc: 0.9268 697 Epoch 602/1000 698 68s 136ms/step - loss: 0.1952 - acc: 0.9865 - val_loss: 0.3854 - val_acc: 0.9281 699 Epoch 603/1000 700 68s 136ms/step - loss: 0.1878 - acc: 0.9881 - val_loss: 0.3852 - val_acc: 0.9299 701 Epoch 604/1000 702 68s 136ms/step - loss: 0.1846 - acc: 0.9899 - val_loss: 0.3842 - val_acc: 0.9298 703 Epoch 605/1000 704 68s 135ms/step - loss: 0.1826 - acc: 0.9909 - val_loss: 0.3829 - val_acc: 0.9326 705 Epoch 606/1000 706 68s 136ms/step - loss: 0.1808 - acc: 0.9912 - val_loss: 0.3838 - val_acc: 0.9305 707 Epoch 607/1000 708 68s 136ms/step - loss: 0.1771 - acc: 0.9927 - val_loss: 0.3851 - val_acc: 0.9303 709 Epoch 608/1000 710 68s 136ms/step - loss: 0.1768 - acc: 0.9922 - val_loss: 0.3898 - val_acc: 0.9304 711 Epoch 609/1000 712 68s 135ms/step - loss: 0.1758 - acc: 0.9926 - val_loss: 0.3878 - val_acc: 0.9309 713 Epoch 610/1000 714 68s 136ms/step - loss: 0.1739 - acc: 0.9931 - val_loss: 0.3887 - val_acc: 0.9294 715 Epoch 611/1000 716 68s 136ms/step - loss: 0.1731 - acc: 0.9934 - val_loss: 0.3874 - val_acc: 0.9311 717 Epoch 612/1000 718 68s 136ms/step - loss: 0.1725 - acc: 0.9935 - val_loss: 0.3898 - val_acc: 0.9297 719 Epoch 613/1000 720 68s 135ms/step - loss: 0.1717 - acc: 0.9937 - val_loss: 0.3900 - val_acc: 0.9298 721 Epoch 614/1000 722 68s 136ms/step - loss: 0.1705 - acc: 0.9937 - val_loss: 0.3912 - val_acc: 0.9299 723 Epoch 615/1000 724 68s 136ms/step - loss: 0.1709 - acc: 0.9934 - val_loss: 0.3898 - val_acc: 0.9307 725 Epoch 616/1000 726 68s 136ms/step - loss: 0.1686 - acc: 0.9948 - val_loss: 0.3905 - val_acc: 0.9311 727 Epoch 617/1000 728 68s 136ms/step - loss: 0.1695 - acc: 0.9942 - val_loss: 0.3948 - val_acc: 0.9303 729 Epoch 618/1000 730 68s 136ms/step - loss: 0.1688 - acc: 0.9941 - val_loss: 0.3936 - val_acc: 0.9298 731 Epoch 619/1000 732 68s 136ms/step - loss: 0.1679 - acc: 0.9945 - val_loss: 0.3950 - val_acc: 0.9290 733 Epoch 620/1000 734 68s 136ms/step - loss: 0.1675 - acc: 0.9941 - val_loss: 0.3940 - val_acc: 0.9300 735 Epoch 621/1000 736 68s 136ms/step - loss: 0.1651 - acc: 0.9949 - val_loss: 0.3956 - val_acc: 0.9309 737 Epoch 622/1000 738 68s 136ms/step - loss: 0.1653 - acc: 0.9951 - val_loss: 0.3950 - val_acc: 0.9306 739 Epoch 623/1000 740 68s 136ms/step - loss: 0.1656 - acc: 0.9946 - val_loss: 0.3947 - val_acc: 0.9306 741 Epoch 624/1000 742 68s 136ms/step - loss: 0.1644 - acc: 0.9949 - val_loss: 0.3946 - val_acc: 0.9304 743 Epoch 625/1000 744 68s 136ms/step - loss: 0.1636 - acc: 0.9951 - val_loss: 0.3944 - val_acc: 0.9296 745 Epoch 626/1000 746 68s 136ms/step - loss: 0.1630 - acc: 0.9951 - val_loss: 0.3937 - val_acc: 0.9295 747 Epoch 627/1000 748 68s 136ms/step - loss: 0.1630 - acc: 0.9953 - val_loss: 0.3959 - val_acc: 0.9296 749 Epoch 628/1000 750 68s 136ms/step - loss: 0.1627 - acc: 0.9954 - val_loss: 0.3939 - val_acc: 0.9289 751 Epoch 629/1000 752 68s 136ms/step - loss: 0.1630 - acc: 0.9947 - val_loss: 0.3937 - val_acc: 0.9303 753 Epoch 630/1000 754 68s 135ms/step - loss: 0.1614 - acc: 0.9958 - val_loss: 0.3909 - val_acc: 0.9316 755 Epoch 631/1000 756 68s 137ms/step - loss: 0.1624 - acc: 0.9950 - val_loss: 0.3922 - val_acc: 0.9310 757 Epoch 632/1000 758 68s 135ms/step - loss: 0.1611 - acc: 0.9954 - val_loss: 0.3907 - val_acc: 0.9313 759 Epoch 633/1000 760 68s 136ms/step - loss: 0.1599 - acc: 0.9955 - val_loss: 0.3893 - val_acc: 0.9295 761 Epoch 634/1000 762 68s 136ms/step - loss: 0.1600 - acc: 0.9954 - val_loss: 0.3886 - val_acc: 0.9308 763 Epoch 635/1000 764 68s 136ms/step - loss: 0.1593 - acc: 0.9953 - val_loss: 0.3926 - val_acc: 0.9297 765 Epoch 636/1000 766 68s 136ms/step - loss: 0.1594 - acc: 0.9950 - val_loss: 0.3945 - val_acc: 0.9289 767 Epoch 637/1000 768 68s 136ms/step - loss: 0.1595 - acc: 0.9955 - val_loss: 0.3937 - val_acc: 0.9306 769 Epoch 638/1000 770 68s 136ms/step - loss: 0.1591 - acc: 0.9958 - val_loss: 0.3882 - val_acc: 0.9306 771 Epoch 639/1000 772 68s 135ms/step - loss: 0.1586 - acc: 0.9959 - val_loss: 0.3893 - val_acc: 0.9309 773 Epoch 640/1000 774 68s 136ms/step - loss: 0.1588 - acc: 0.9956 - val_loss: 0.3935 - val_acc: 0.9300 775 Epoch 641/1000 776 68s 135ms/step - loss: 0.1571 - acc: 0.9960 - val_loss: 0.3917 - val_acc: 0.9298 777 Epoch 642/1000 778 68s 136ms/step - loss: 0.1576 - acc: 0.9956 - val_loss: 0.3945 - val_acc: 0.9284 779 Epoch 643/1000 780 68s 136ms/step - loss: 0.1570 - acc: 0.9961 - val_loss: 0.3899 - val_acc: 0.9309 781 Epoch 644/1000 782 68s 136ms/step - loss: 0.1565 - acc: 0.9962 - val_loss: 0.3918 - val_acc: 0.9307 783 Epoch 645/1000 784 68s 136ms/step - loss: 0.1563 - acc: 0.9956 - val_loss: 0.3940 - val_acc: 0.9307 785 Epoch 646/1000 786 68s 136ms/step - loss: 0.1563 - acc: 0.9956 - val_loss: 0.3895 - val_acc: 0.9322 787 Epoch 647/1000 788 68s 136ms/step - loss: 0.1555 - acc: 0.9963 - val_loss: 0.3903 - val_acc: 0.9302 789 Epoch 648/1000 790 68s 135ms/step - loss: 0.1556 - acc: 0.9958 - val_loss: 0.3926 - val_acc: 0.9307 791 Epoch 649/1000 792 68s 135ms/step - loss: 0.1542 - acc: 0.9962 - val_loss: 0.3904 - val_acc: 0.9308 793 Epoch 650/1000 794 68s 136ms/step - loss: 0.1552 - acc: 0.9959 - val_loss: 0.3934 - val_acc: 0.9295 795 Epoch 651/1000 796 68s 136ms/step - loss: 0.1548 - acc: 0.9959 - val_loss: 0.3921 - val_acc: 0.9307 797 Epoch 652/1000 798 68s 136ms/step - loss: 0.1537 - acc: 0.9964 - val_loss: 0.3973 - val_acc: 0.9293 799 Epoch 653/1000 800 68s 136ms/step - loss: 0.1540 - acc: 0.9958 - val_loss: 0.3950 - val_acc: 0.9287 801 Epoch 654/1000 802 68s 136ms/step - loss: 0.1523 - acc: 0.9965 - val_loss: 0.3956 - val_acc: 0.9296 803 Epoch 655/1000 804 68s 137ms/step - loss: 0.1532 - acc: 0.9964 - val_loss: 0.3991 - val_acc: 0.9292 805 Epoch 656/1000 806 68s 136ms/step - loss: 0.1538 - acc: 0.9957 - val_loss: 0.3995 - val_acc: 0.9296 807 Epoch 657/1000 808 68s 136ms/step - loss: 0.1520 - acc: 0.9966 - val_loss: 0.3988 - val_acc: 0.9310 809 Epoch 658/1000 810 68s 136ms/step - loss: 0.1532 - acc: 0.9959 - val_loss: 0.3961 - val_acc: 0.9307 811 Epoch 659/1000 812 68s 136ms/step - loss: 0.1526 - acc: 0.9958 - val_loss: 0.3948 - val_acc: 0.9306 813 Epoch 660/1000 814 68s 136ms/step - loss: 0.1512 - acc: 0.9965 - val_loss: 0.3947 - val_acc: 0.9309 815 Epoch 661/1000 816 68s 136ms/step - loss: 0.1519 - acc: 0.9962 - val_loss: 0.3959 - val_acc: 0.9315 817 Epoch 662/1000 818 68s 136ms/step - loss: 0.1510 - acc: 0.9963 - val_loss: 0.3962 - val_acc: 0.9312 819 Epoch 663/1000 820 68s 136ms/step - loss: 0.1517 - acc: 0.9960 - val_loss: 0.3939 - val_acc: 0.9304 821 Epoch 664/1000 822 68s 135ms/step - loss: 0.1494 - acc: 0.9964 - val_loss: 0.3928 - val_acc: 0.9309 823 Epoch 665/1000 824 68s 135ms/step - loss: 0.1492 - acc: 0.9966 - val_loss: 0.3900 - val_acc: 0.9320 825 Epoch 666/1000 826 68s 136ms/step - loss: 0.1493 - acc: 0.9963 - val_loss: 0.3907 - val_acc: 0.9312 827 Epoch 667/1000 828 68s 136ms/step - loss: 0.1491 - acc: 0.9967 - val_loss: 0.3930 - val_acc: 0.9309 829 Epoch 668/1000 830 68s 136ms/step - loss: 0.1494 - acc: 0.9960 - val_loss: 0.3923 - val_acc: 0.9301 831 Epoch 669/1000 832 68s 136ms/step - loss: 0.1485 - acc: 0.9966 - val_loss: 0.3941 - val_acc: 0.9308 833 Epoch 670/1000 834 68s 135ms/step - loss: 0.1486 - acc: 0.9963 - val_loss: 0.3927 - val_acc: 0.9314 835 Epoch 671/1000 836 68s 135ms/step - loss: 0.1481 - acc: 0.9965 - val_loss: 0.3939 - val_acc: 0.9322 837 Epoch 672/1000 838 68s 136ms/step - loss: 0.1474 - acc: 0.9968 - val_loss: 0.3950 - val_acc: 0.9309 839 Epoch 673/1000 840 68s 136ms/step - loss: 0.1471 - acc: 0.9967 - val_loss: 0.3931 - val_acc: 0.9322 841 Epoch 674/1000 842 68s 136ms/step - loss: 0.1470 - acc: 0.9968 - val_loss: 0.3934 - val_acc: 0.9319 843 Epoch 675/1000 844 68s 136ms/step - loss: 0.1469 - acc: 0.9965 - val_loss: 0.3920 - val_acc: 0.9319 845 Epoch 676/1000 846 68s 136ms/step - loss: 0.1469 - acc: 0.9967 - val_loss: 0.3923 - val_acc: 0.9309 847 Epoch 677/1000 848 68s 136ms/step - loss: 0.1461 - acc: 0.9968 - val_loss: 0.3940 - val_acc: 0.9297 849 Epoch 678/1000 850 68s 135ms/step - loss: 0.1462 - acc: 0.9969 - val_loss: 0.3924 - val_acc: 0.9309 851 Epoch 679/1000 852 68s 136ms/step - loss: 0.1443 - acc: 0.9971 - val_loss: 0.3930 - val_acc: 0.9317 853 Epoch 680/1000 854 68s 135ms/step - loss: 0.1458 - acc: 0.9966 - val_loss: 0.3978 - val_acc: 0.9296 855 Epoch 681/1000 856 68s 135ms/step - loss: 0.1453 - acc: 0.9970 - val_loss: 0.3978 - val_acc: 0.9286 857 Epoch 682/1000 858 68s 136ms/step - loss: 0.1444 - acc: 0.9972 - val_loss: 0.3968 - val_acc: 0.9285 859 Epoch 683/1000 860 68s 136ms/step - loss: 0.1444 - acc: 0.9969 - val_loss: 0.3922 - val_acc: 0.9299 861 Epoch 684/1000 862 68s 136ms/step - loss: 0.1447 - acc: 0.9970 - val_loss: 0.3907 - val_acc: 0.9297 863 Epoch 685/1000 864 68s 136ms/step - loss: 0.1441 - acc: 0.9966 - val_loss: 0.3925 - val_acc: 0.9285 865 Epoch 686/1000 866 68s 135ms/step - loss: 0.1454 - acc: 0.9964 - val_loss: 0.3939 - val_acc: 0.9296 867 Epoch 687/1000 868 68s 135ms/step - loss: 0.1433 - acc: 0.9968 - val_loss: 0.3955 - val_acc: 0.9293 869 Epoch 688/1000 870 68s 136ms/step - loss: 0.1435 - acc: 0.9969 - val_loss: 0.3958 - val_acc: 0.9295 871 Epoch 689/1000 872 68s 136ms/step - loss: 0.1423 - acc: 0.9972 - val_loss: 0.3981 - val_acc: 0.9305 873 Epoch 690/1000 874 68s 136ms/step - loss: 0.1438 - acc: 0.9965 - val_loss: 0.3986 - val_acc: 0.9299 875 Epoch 691/1000 876 68s 136ms/step - loss: 0.1422 - acc: 0.9972 - val_loss: 0.3956 - val_acc: 0.9302 877 Epoch 692/1000 878 68s 136ms/step - loss: 0.1425 - acc: 0.9968 - val_loss: 0.3962 - val_acc: 0.9309 879 Epoch 693/1000 880 68s 136ms/step - loss: 0.1420 - acc: 0.9968 - val_loss: 0.3972 - val_acc: 0.9300 881 Epoch 694/1000 882 68s 136ms/step - loss: 0.1422 - acc: 0.9967 - val_loss: 0.3947 - val_acc: 0.9301 883 Epoch 695/1000 884 68s 136ms/step - loss: 0.1420 - acc: 0.9970 - val_loss: 0.3945 - val_acc: 0.9306 885 Epoch 696/1000 886 68s 136ms/step - loss: 0.1412 - acc: 0.9970 - val_loss: 0.3942 - val_acc: 0.9313 887 Epoch 697/1000 888 68s 136ms/step - loss: 0.1402 - acc: 0.9972 - val_loss: 0.3950 - val_acc: 0.9309 889 Epoch 698/1000 890 68s 136ms/step - loss: 0.1408 - acc: 0.9969 - val_loss: 0.3931 - val_acc: 0.9307 891 Epoch 699/1000 892 68s 136ms/step - loss: 0.1409 - acc: 0.9970 - val_loss: 0.3936 - val_acc: 0.9297 893 Epoch 700/1000 894 68s 136ms/step - loss: 0.1404 - acc: 0.9970 - val_loss: 0.3930 - val_acc: 0.9289 895 Epoch 701/1000 896 68s 136ms/step - loss: 0.1403 - acc: 0.9972 - val_loss: 0.3905 - val_acc: 0.9308 897 Epoch 702/1000 898 68s 136ms/step - loss: 0.1387 - acc: 0.9976 - val_loss: 0.3957 - val_acc: 0.9295 899 Epoch 703/1000 900 68s 135ms/step - loss: 0.1402 - acc: 0.9967 - val_loss: 0.3950 - val_acc: 0.9294 901 Epoch 704/1000 902 68s 136ms/step - loss: 0.1393 - acc: 0.9971 - val_loss: 0.3950 - val_acc: 0.9298 903 Epoch 705/1000 904 68s 136ms/step - loss: 0.1386 - acc: 0.9969 - val_loss: 0.3950 - val_acc: 0.9302 905 Epoch 706/1000 906 68s 136ms/step - loss: 0.1384 - acc: 0.9973 - val_loss: 0.3936 - val_acc: 0.9303 907 Epoch 707/1000 908 68s 135ms/step - loss: 0.1386 - acc: 0.9970 - val_loss: 0.3974 - val_acc: 0.9290 909 Epoch 708/1000 910 68s 136ms/step - loss: 0.1392 - acc: 0.9968 - val_loss: 0.3938 - val_acc: 0.9295 911 Epoch 709/1000 912 68s 136ms/step - loss: 0.1383 - acc: 0.9970 - val_loss: 0.3931 - val_acc: 0.9288 913 Epoch 710/1000 914 68s 135ms/step - loss: 0.1383 - acc: 0.9970 - val_loss: 0.3905 - val_acc: 0.9305 915 Epoch 711/1000 916 68s 136ms/step - loss: 0.1381 - acc: 0.9970 - val_loss: 0.3904 - val_acc: 0.9286 917 Epoch 712/1000 918 68s 136ms/step - loss: 0.1375 - acc: 0.9971 - val_loss: 0.3923 - val_acc: 0.9302 919 Epoch 713/1000 920 68s 136ms/step - loss: 0.1370 - acc: 0.9972 - val_loss: 0.3931 - val_acc: 0.9308 921 Epoch 714/1000 922 68s 136ms/step - loss: 0.1364 - acc: 0.9974 - val_loss: 0.3883 - val_acc: 0.9322 923 Epoch 715/1000 924 68s 136ms/step - loss: 0.1364 - acc: 0.9974 - val_loss: 0.3894 - val_acc: 0.9306 925 Epoch 716/1000 926 68s 135ms/step - loss: 0.1365 - acc: 0.9972 - val_loss: 0.3894 - val_acc: 0.9290 927 Epoch 717/1000 928 68s 135ms/step - loss: 0.1358 - acc: 0.9973 - val_loss: 0.3908 - val_acc: 0.9294 929 Epoch 718/1000 930 68s 136ms/step - loss: 0.1360 - acc: 0.9971 - val_loss: 0.3899 - val_acc: 0.9297 931 Epoch 719/1000 932 68s 135ms/step - loss: 0.1370 - acc: 0.9969 - val_loss: 0.3880 - val_acc: 0.9311 933 Epoch 720/1000 934 68s 135ms/step - loss: 0.1348 - acc: 0.9971 - val_loss: 0.3884 - val_acc: 0.9308 935 Epoch 721/1000 936 68s 135ms/step - loss: 0.1354 - acc: 0.9973 - val_loss: 0.3946 - val_acc: 0.9299 937 Epoch 722/1000 938 68s 136ms/step - loss: 0.1346 - acc: 0.9973 - val_loss: 0.3890 - val_acc: 0.9313 939 Epoch 723/1000 940 68s 136ms/step - loss: 0.1355 - acc: 0.9972 - val_loss: 0.3914 - val_acc: 0.9313 941 Epoch 724/1000 942 68s 136ms/step - loss: 0.1353 - acc: 0.9970 - val_loss: 0.3956 - val_acc: 0.9308 943 Epoch 725/1000 944 68s 136ms/step - loss: 0.1349 - acc: 0.9972 - val_loss: 0.3914 - val_acc: 0.9303 945 Epoch 726/1000 946 68s 136ms/step - loss: 0.1338 - acc: 0.9975 - val_loss: 0.3917 - val_acc: 0.9297 947 Epoch 727/1000 948 68s 136ms/step - loss: 0.1335 - acc: 0.9977 - val_loss: 0.3877 - val_acc: 0.9318 949 Epoch 728/1000 950 68s 135ms/step - loss: 0.1329 - acc: 0.9977 - val_loss: 0.3830 - val_acc: 0.9324 951 Epoch 729/1000 952 68s 136ms/step - loss: 0.1332 - acc: 0.9973 - val_loss: 0.3870 - val_acc: 0.9314 953 Epoch 730/1000 954 68s 136ms/step - loss: 0.1330 - acc: 0.9976 - val_loss: 0.3870 - val_acc: 0.9321 955 Epoch 731/1000 956 68s 136ms/step - loss: 0.1324 - acc: 0.9978 - val_loss: 0.3841 - val_acc: 0.9308 957 Epoch 732/1000 958 68s 136ms/step - loss: 0.1329 - acc: 0.9971 - val_loss: 0.3853 - val_acc: 0.9316 959 Epoch 733/1000 960 68s 137ms/step - loss: 0.1323 - acc: 0.9975 - val_loss: 0.3868 - val_acc: 0.9310 961 Epoch 734/1000 962 68s 136ms/step - loss: 0.1322 - acc: 0.9975 - val_loss: 0.3882 - val_acc: 0.9301 963 Epoch 735/1000 964 68s 135ms/step - loss: 0.1314 - acc: 0.9975 - val_loss: 0.3880 - val_acc: 0.9289 965 Epoch 736/1000 966 68s 136ms/step - loss: 0.1327 - acc: 0.9971 - val_loss: 0.3891 - val_acc: 0.9295 967 Epoch 737/1000 968 68s 135ms/step - loss: 0.1308 - acc: 0.9978 - val_loss: 0.3862 - val_acc: 0.9303 969 Epoch 738/1000 970 68s 136ms/step - loss: 0.1314 - acc: 0.9975 - val_loss: 0.3872 - val_acc: 0.9294 971 Epoch 739/1000 972 68s 136ms/step - loss: 0.1305 - acc: 0.9979 - val_loss: 0.3864 - val_acc: 0.9309 973 Epoch 740/1000 974 68s 136ms/step - loss: 0.1310 - acc: 0.9973 - val_loss: 0.3896 - val_acc: 0.9307 975 Epoch 741/1000 976 68s 136ms/step - loss: 0.1311 - acc: 0.9974 - val_loss: 0.3883 - val_acc: 0.9312 977 Epoch 742/1000 978 68s 136ms/step - loss: 0.1315 - acc: 0.9968 - val_loss: 0.3888 - val_acc: 0.9304 979 Epoch 743/1000 980 68s 136ms/step - loss: 0.1297 - acc: 0.9977 - val_loss: 0.3892 - val_acc: 0.9307 981 Epoch 744/1000 982 68s 136ms/step - loss: 0.1298 - acc: 0.9976 - val_loss: 0.3864 - val_acc: 0.9297 983 Epoch 745/1000 984 68s 136ms/step - loss: 0.1299 - acc: 0.9974 - val_loss: 0.3883 - val_acc: 0.9306 985 Epoch 746/1000 986 68s 135ms/step - loss: 0.1301 - acc: 0.9972 - val_loss: 0.3892 - val_acc: 0.9290 987 Epoch 747/1000 988 68s 136ms/step - loss: 0.1290 - acc: 0.9977 - val_loss: 0.3860 - val_acc: 0.9301 989 Epoch 748/1000 990 68s 136ms/step - loss: 0.1299 - acc: 0.9972 - val_loss: 0.3846 - val_acc: 0.9308 991 Epoch 749/1000 992 68s 136ms/step - loss: 0.1292 - acc: 0.9973 - val_loss: 0.3888 - val_acc: 0.9293 993 Epoch 750/1000 994 68s 135ms/step - loss: 0.1297 - acc: 0.9973 - val_loss: 0.3864 - val_acc: 0.9289 995 Epoch 751/1000 996 68s 135ms/step - loss: 0.1296 - acc: 0.9969 - val_loss: 0.3886 - val_acc: 0.9305 997 Epoch 752/1000 998 68s 136ms/step - loss: 0.1288 - acc: 0.9972 - val_loss: 0.3893 - val_acc: 0.9285 999 Epoch 753/1000 1000 68s 136ms/step - loss: 0.1281 - acc: 0.9977 - val_loss: 0.3824 - val_acc: 0.9308 1001 Epoch 754/1000 1002 68s 136ms/step - loss: 0.1288 - acc: 0.9973 - val_loss: 0.3817 - val_acc: 0.9300 1003 Epoch 755/1000 1004 68s 136ms/step - loss: 0.1274 - acc: 0.9978 - val_loss: 0.3818 - val_acc: 0.9290 1005 Epoch 756/1000 1006 68s 136ms/step - loss: 0.1282 - acc: 0.9971 - val_loss: 0.3843 - val_acc: 0.9277 1007 Epoch 757/1000 1008 68s 136ms/step - loss: 0.1276 - acc: 0.9975 - val_loss: 0.3822 - val_acc: 0.9285 1009 Epoch 758/1000 1010 68s 135ms/step - loss: 0.1274 - acc: 0.9974 - val_loss: 0.3837 - val_acc: 0.9301 1011 Epoch 759/1000 1012 68s 136ms/step - loss: 0.1274 - acc: 0.9971 - val_loss: 0.3819 - val_acc: 0.9290 1013 Epoch 760/1000 1014 68s 136ms/step - loss: 0.1261 - acc: 0.9977 - val_loss: 0.3803 - val_acc: 0.9308 1015 Epoch 761/1000 1016 68s 136ms/step - loss: 0.1274 - acc: 0.9970 - val_loss: 0.3834 - val_acc: 0.9297 1017 Epoch 762/1000 1018 68s 136ms/step - loss: 0.1264 - acc: 0.9977 - val_loss: 0.3845 - val_acc: 0.9300 1019 Epoch 763/1000 1020 68s 136ms/step - loss: 0.1271 - acc: 0.9969 - val_loss: 0.3827 - val_acc: 0.9296 1021 Epoch 764/1000 1022 68s 136ms/step - loss: 0.1264 - acc: 0.9974 - val_loss: 0.3772 - val_acc: 0.9316 1023 Epoch 765/1000 1024 68s 136ms/step - loss: 0.1255 - acc: 0.9976 - val_loss: 0.3735 - val_acc: 0.9323 1025 Epoch 766/1000 1026 68s 135ms/step - loss: 0.1253 - acc: 0.9977 - val_loss: 0.3743 - val_acc: 0.9325 1027 Epoch 767/1000 1028 68s 136ms/step - loss: 0.1252 - acc: 0.9977 - val_loss: 0.3774 - val_acc: 0.9319 1029 Epoch 768/1000 1030 68s 136ms/step - loss: 0.1251 - acc: 0.9975 - val_loss: 0.3778 - val_acc: 0.9324 1031 Epoch 769/1000 1032 68s 136ms/step - loss: 0.1261 - acc: 0.9971 - val_loss: 0.3811 - val_acc: 0.9310 1033 Epoch 770/1000 1034 68s 136ms/step - loss: 0.1242 - acc: 0.9979 - val_loss: 0.3808 - val_acc: 0.9295 1035 Epoch 771/1000 1036 68s 136ms/step - loss: 0.1249 - acc: 0.9975 - val_loss: 0.3780 - val_acc: 0.9304 1037 Epoch 772/1000 1038 68s 136ms/step - loss: 0.1247 - acc: 0.9974 - val_loss: 0.3779 - val_acc: 0.9312 1039 Epoch 773/1000 1040 68s 136ms/step - loss: 0.1246 - acc: 0.9974 - val_loss: 0.3811 - val_acc: 0.9314 1041 Epoch 774/1000 1042 68s 135ms/step - loss: 0.1244 - acc: 0.9976 - val_loss: 0.3798 - val_acc: 0.9303 1043 Epoch 775/1000 1044 68s 136ms/step - loss: 0.1243 - acc: 0.9974 - val_loss: 0.3804 - val_acc: 0.9307 1045 Epoch 776/1000 1046 68s 135ms/step - loss: 0.1235 - acc: 0.9975 - val_loss: 0.3800 - val_acc: 0.9310 1047 Epoch 777/1000 1048 68s 136ms/step - loss: 0.1240 - acc: 0.9973 - val_loss: 0.3795 - val_acc: 0.9304 1049 Epoch 778/1000 1050 68s 136ms/step - loss: 0.1234 - acc: 0.9975 - val_loss: 0.3760 - val_acc: 0.9320 1051 Epoch 779/1000 1052 68s 136ms/step - loss: 0.1235 - acc: 0.9976 - val_loss: 0.3750 - val_acc: 0.9312 1053 Epoch 780/1000 1054 68s 136ms/step - loss: 0.1226 - acc: 0.9976 - val_loss: 0.3721 - val_acc: 0.9332 1055 Epoch 781/1000 1056 68s 136ms/step - loss: 0.1227 - acc: 0.9976 - val_loss: 0.3753 - val_acc: 0.9322 1057 Epoch 782/1000 1058 68s 135ms/step - loss: 0.1226 - acc: 0.9975 - val_loss: 0.3756 - val_acc: 0.9316 1059 Epoch 783/1000 1060 68s 135ms/step - loss: 0.1228 - acc: 0.9975 - val_loss: 0.3761 - val_acc: 0.9302 1061 Epoch 784/1000 1062 68s 136ms/step - loss: 0.1216 - acc: 0.9978 - val_loss: 0.3711 - val_acc: 0.9329 1063 Epoch 785/1000 1064 68s 136ms/step - loss: 0.1221 - acc: 0.9975 - val_loss: 0.3750 - val_acc: 0.9300 1065 Epoch 786/1000 1066 68s 136ms/step - loss: 0.1213 - acc: 0.9978 - val_loss: 0.3739 - val_acc: 0.9305 1067 Epoch 787/1000 1068 68s 136ms/step - loss: 0.1211 - acc: 0.9978 - val_loss: 0.3744 - val_acc: 0.9315 1069 Epoch 788/1000 1070 68s 136ms/step - loss: 0.1209 - acc: 0.9978 - val_loss: 0.3730 - val_acc: 0.9321 1071 Epoch 789/1000 1072 68s 136ms/step - loss: 0.1219 - acc: 0.9975 - val_loss: 0.3719 - val_acc: 0.9329 1073 Epoch 790/1000 1074 68s 135ms/step - loss: 0.1212 - acc: 0.9975 - val_loss: 0.3753 - val_acc: 0.9318 1075 Epoch 791/1000 1076 68s 136ms/step - loss: 0.1208 - acc: 0.9974 - val_loss: 0.3744 - val_acc: 0.9310 1077 Epoch 792/1000 1078 68s 135ms/step - loss: 0.1222 - acc: 0.9969 - val_loss: 0.3804 - val_acc: 0.9291 1079 Epoch 793/1000 1080 68s 136ms/step - loss: 0.1209 - acc: 0.9977 - val_loss: 0.3806 - val_acc: 0.9295 1081 Epoch 794/1000 1082 68s 136ms/step - loss: 0.1203 - acc: 0.9977 - val_loss: 0.3809 - val_acc: 0.9282 1083 Epoch 795/1000 1084 68s 136ms/step - loss: 0.1203 - acc: 0.9975 - val_loss: 0.3785 - val_acc: 0.9286 1085 Epoch 796/1000 1086 68s 136ms/step - loss: 0.1199 - acc: 0.9978 - val_loss: 0.3783 - val_acc: 0.9274 1087 Epoch 797/1000 1088 68s 136ms/step - loss: 0.1196 - acc: 0.9977 - val_loss: 0.3780 - val_acc: 0.9281 1089 Epoch 798/1000 1090 68s 135ms/step - loss: 0.1195 - acc: 0.9976 - val_loss: 0.3763 - val_acc: 0.9311 1091 Epoch 799/1000 1092 67s 135ms/step - loss: 0.1193 - acc: 0.9977 - val_loss: 0.3820 - val_acc: 0.9303 1093 Epoch 800/1000 1094 68s 136ms/step - loss: 0.1200 - acc: 0.9972 - val_loss: 0.3833 - val_acc: 0.9296 1095 Epoch 801/1000 1096 68s 135ms/step - loss: 0.1185 - acc: 0.9978 - val_loss: 0.3774 - val_acc: 0.9300 1097 Epoch 802/1000 1098 68s 136ms/step - loss: 0.1195 - acc: 0.9974 - val_loss: 0.3775 - val_acc: 0.9305 1099 Epoch 803/1000 1100 68s 136ms/step - loss: 0.1183 - acc: 0.9976 - val_loss: 0.3759 - val_acc: 0.9308 1101 Epoch 804/1000 1102 68s 136ms/step - loss: 0.1182 - acc: 0.9979 - val_loss: 0.3728 - val_acc: 0.9316 1103 Epoch 805/1000 1104 68s 136ms/step - loss: 0.1191 - acc: 0.9974 - val_loss: 0.3771 - val_acc: 0.9311 1105 Epoch 806/1000 1106 68s 136ms/step - loss: 0.1179 - acc: 0.9977 - val_loss: 0.3768 - val_acc: 0.9299 1107 Epoch 807/1000 1108 68s 136ms/step - loss: 0.1185 - acc: 0.9972 - val_loss: 0.3765 - val_acc: 0.9302 1109 Epoch 808/1000 1110 68s 136ms/step - loss: 0.1173 - acc: 0.9978 - val_loss: 0.3794 - val_acc: 0.9291 1111 Epoch 809/1000 1112 68s 136ms/step - loss: 0.1172 - acc: 0.9978 - val_loss: 0.3773 - val_acc: 0.9297 1113 Epoch 810/1000 1114 68s 136ms/step - loss: 0.1181 - acc: 0.9975 - val_loss: 0.3811 - val_acc: 0.9306 1115 Epoch 811/1000 1116 68s 136ms/step - loss: 0.1173 - acc: 0.9975 - val_loss: 0.3753 - val_acc: 0.9302 1117 Epoch 812/1000 1118 68s 136ms/step - loss: 0.1171 - acc: 0.9975 - val_loss: 0.3812 - val_acc: 0.9285 1119 Epoch 813/1000 1120 68s 136ms/step - loss: 0.1171 - acc: 0.9976 - val_loss: 0.3845 - val_acc: 0.9297 1121 Epoch 814/1000 1122 68s 136ms/step - loss: 0.1163 - acc: 0.9978 - val_loss: 0.3829 - val_acc: 0.9295 1123 Epoch 815/1000 1124 68s 136ms/step - loss: 0.1166 - acc: 0.9979 - val_loss: 0.3807 - val_acc: 0.9284 1125 Epoch 816/1000 1126 68s 136ms/step - loss: 0.1165 - acc: 0.9976 - val_loss: 0.3813 - val_acc: 0.9286 1127 Epoch 817/1000 1128 68s 135ms/step - loss: 0.1170 - acc: 0.9972 - val_loss: 0.3840 - val_acc: 0.9283 1129 Epoch 818/1000 1130 68s 136ms/step - loss: 0.1160 - acc: 0.9973 - val_loss: 0.3826 - val_acc: 0.9274 1131 Epoch 819/1000 1132 68s 136ms/step - loss: 0.1157 - acc: 0.9977 - val_loss: 0.3755 - val_acc: 0.9312 1133 Epoch 820/1000 1134 68s 136ms/step - loss: 0.1155 - acc: 0.9978 - val_loss: 0.3794 - val_acc: 0.9291 1135 Epoch 821/1000 1136 68s 136ms/step - loss: 0.1163 - acc: 0.9973 - val_loss: 0.3751 - val_acc: 0.9293 1137 Epoch 822/1000 1138 68s 137ms/step - loss: 0.1154 - acc: 0.9977 - val_loss: 0.3764 - val_acc: 0.9298 1139 Epoch 823/1000 1140 69s 137ms/step - loss: 0.1143 - acc: 0.9980 - val_loss: 0.3754 - val_acc: 0.9293 1141 Epoch 824/1000 1142 69s 138ms/step - loss: 0.1142 - acc: 0.9979 - val_loss: 0.3743 - val_acc: 0.9304 1143 Epoch 825/1000 1144 69s 138ms/step - loss: 0.1153 - acc: 0.9974 - val_loss: 0.3772 - val_acc: 0.9307 1145 Epoch 826/1000 1146 69s 138ms/step - loss: 0.1149 - acc: 0.9976 - val_loss: 0.3718 - val_acc: 0.9312 1147 Epoch 827/1000 1148 68s 137ms/step - loss: 0.1148 - acc: 0.9976 - val_loss: 0.3777 - val_acc: 0.9317 1149 Epoch 828/1000 1150 69s 138ms/step - loss: 0.1147 - acc: 0.9976 - val_loss: 0.3769 - val_acc: 0.9303 1151 Epoch 829/1000 1152 69s 138ms/step - loss: 0.1137 - acc: 0.9978 - val_loss: 0.3748 - val_acc: 0.9309 1153 Epoch 830/1000 1154 69s 138ms/step - loss: 0.1139 - acc: 0.9978 - val_loss: 0.3728 - val_acc: 0.9308 1155 Epoch 831/1000 1156 68s 137ms/step - loss: 0.1138 - acc: 0.9976 - val_loss: 0.3724 - val_acc: 0.9296 1157 Epoch 832/1000 1158 69s 138ms/step - loss: 0.1132 - acc: 0.9978 - val_loss: 0.3807 - val_acc: 0.9288 1159 Epoch 833/1000 1160 68s 137ms/step - loss: 0.1140 - acc: 0.9975 - val_loss: 0.3810 - val_acc: 0.9290 1161 Epoch 834/1000 1162 69s 138ms/step - loss: 0.1135 - acc: 0.9975 - val_loss: 0.3816 - val_acc: 0.9291 1163 Epoch 835/1000 1164 69s 138ms/step - loss: 0.1130 - acc: 0.9979 - val_loss: 0.3830 - val_acc: 0.9284 1165 Epoch 836/1000 1166 69s 138ms/step - loss: 0.1131 - acc: 0.9976 - val_loss: 0.3792 - val_acc: 0.9278 1167 Epoch 837/1000 1168 69s 137ms/step - loss: 0.1126 - acc: 0.9978 - val_loss: 0.3712 - val_acc: 0.9306 1169 Epoch 838/1000 1170 69s 137ms/step - loss: 0.1126 - acc: 0.9979 - val_loss: 0.3771 - val_acc: 0.9293 1171 Epoch 839/1000 1172 69s 138ms/step - loss: 0.1119 - acc: 0.9981 - val_loss: 0.3768 - val_acc: 0.9288 1173 Epoch 840/1000 1174 69s 138ms/step - loss: 0.1120 - acc: 0.9980 - val_loss: 0.3769 - val_acc: 0.9289 1175 Epoch 841/1000 1176 69s 137ms/step - loss: 0.1120 - acc: 0.9977 - val_loss: 0.3774 - val_acc: 0.9285 1177 Epoch 842/1000 1178 68s 136ms/step - loss: 0.1120 - acc: 0.9975 - val_loss: 0.3718 - val_acc: 0.9312 1179 Epoch 843/1000 1180 68s 136ms/step - loss: 0.1115 - acc: 0.9976 - val_loss: 0.3707 - val_acc: 0.9312 1181 Epoch 844/1000 1182 68s 136ms/step - loss: 0.1120 - acc: 0.9978 - val_loss: 0.3777 - val_acc: 0.9285 1183 Epoch 845/1000 1184 69s 137ms/step - loss: 0.1115 - acc: 0.9978 - val_loss: 0.3777 - val_acc: 0.9284 1185 Epoch 846/1000 1186 69s 138ms/step - loss: 0.1115 - acc: 0.9978 - val_loss: 0.3742 - val_acc: 0.9303 1187 Epoch 847/1000 1188 68s 137ms/step - loss: 0.1113 - acc: 0.9974 - val_loss: 0.3749 - val_acc: 0.9300 1189 Epoch 848/1000 1190 69s 138ms/step - loss: 0.1114 - acc: 0.9976 - val_loss: 0.3795 - val_acc: 0.9286 1191 Epoch 849/1000 1192 69s 138ms/step - loss: 0.1115 - acc: 0.9975 - val_loss: 0.3754 - val_acc: 0.9284 1193 Epoch 850/1000 1194 69s 138ms/step - loss: 0.1105 - acc: 0.9978 - val_loss: 0.3705 - val_acc: 0.9305 1195 Epoch 851/1000 1196 69s 138ms/step - loss: 0.1098 - acc: 0.9978 - val_loss: 0.3752 - val_acc: 0.9290 1197 Epoch 852/1000 1198 69s 138ms/step - loss: 0.1118 - acc: 0.9971 - val_loss: 0.3773 - val_acc: 0.9280 1199 Epoch 853/1000 1200 68s 137ms/step - loss: 0.1103 - acc: 0.9978 - val_loss: 0.3732 - val_acc: 0.9303 1201 Epoch 854/1000 1202 69s 137ms/step - loss: 0.1109 - acc: 0.9977 - val_loss: 0.3715 - val_acc: 0.9302 1203 Epoch 855/1000 1204 69s 137ms/step - loss: 0.1096 - acc: 0.9977 - val_loss: 0.3780 - val_acc: 0.9306 1205 Epoch 856/1000 1206 69s 137ms/step - loss: 0.1100 - acc: 0.9977 - val_loss: 0.3764 - val_acc: 0.9290 1207 Epoch 857/1000 1208 69s 137ms/step - loss: 0.1093 - acc: 0.9981 - val_loss: 0.3750 - val_acc: 0.9291 1209 Epoch 858/1000 1210 69s 138ms/step - loss: 0.1088 - acc: 0.9980 - val_loss: 0.3738 - val_acc: 0.9287 1211 Epoch 859/1000 1212 69s 138ms/step - loss: 0.1098 - acc: 0.9975 - val_loss: 0.3711 - val_acc: 0.9291 1213 Epoch 860/1000 1214 69s 138ms/step - loss: 0.1091 - acc: 0.9979 - val_loss: 0.3636 - val_acc: 0.9302 1215 Epoch 861/1000 1216 69s 138ms/step - loss: 0.1094 - acc: 0.9976 - val_loss: 0.3689 - val_acc: 0.9303 1217 Epoch 862/1000 1218 68s 137ms/step - loss: 0.1088 - acc: 0.9978 - val_loss: 0.3687 - val_acc: 0.9306 1219 Epoch 863/1000 1220 69s 137ms/step - loss: 0.1083 - acc: 0.9978 - val_loss: 0.3720 - val_acc: 0.9318 1221 Epoch 864/1000 1222 69s 138ms/step - loss: 0.1080 - acc: 0.9978 - val_loss: 0.3695 - val_acc: 0.9302 1223 Epoch 865/1000 1224 69s 138ms/step - loss: 0.1093 - acc: 0.9973 - val_loss: 0.3733 - val_acc: 0.9297 1225 Epoch 866/1000 1226 69s 138ms/step - loss: 0.1092 - acc: 0.9974 - val_loss: 0.3713 - val_acc: 0.9296 1227 Epoch 867/1000 1228 69s 137ms/step - loss: 0.1082 - acc: 0.9978 - val_loss: 0.3674 - val_acc: 0.9306 1229 Epoch 868/1000 1230 69s 138ms/step - loss: 0.1087 - acc: 0.9974 - val_loss: 0.3684 - val_acc: 0.9296 1231 Epoch 869/1000 1232 69s 138ms/step - loss: 0.1072 - acc: 0.9982 - val_loss: 0.3684 - val_acc: 0.9307 1233 Epoch 870/1000 1234 68s 137ms/step - loss: 0.1080 - acc: 0.9976 - val_loss: 0.3695 - val_acc: 0.9294 1235 Epoch 871/1000 1236 69s 138ms/step - loss: 0.1075 - acc: 0.9977 - val_loss: 0.3655 - val_acc: 0.9306 1237 Epoch 872/1000 1238 69s 138ms/step - loss: 0.1073 - acc: 0.9979 - val_loss: 0.3667 - val_acc: 0.9303 1239 Epoch 873/1000 1240 69s 138ms/step - loss: 0.1079 - acc: 0.9977 - val_loss: 0.3717 - val_acc: 0.9278 1241 Epoch 874/1000 1242 68s 137ms/step - loss: 0.1081 - acc: 0.9973 - val_loss: 0.3722 - val_acc: 0.9292 1243 Epoch 875/1000 1244 69s 138ms/step - loss: 0.1072 - acc: 0.9975 - val_loss: 0.3716 - val_acc: 0.9298 1245 Epoch 876/1000 1246 69s 137ms/step - loss: 0.1070 - acc: 0.9977 - val_loss: 0.3721 - val_acc: 0.9311 1247 Epoch 877/1000 1248 69s 137ms/step - loss: 0.1066 - acc: 0.9978 - val_loss: 0.3722 - val_acc: 0.9289 1249 Epoch 878/1000 1250 69s 137ms/step - loss: 0.1068 - acc: 0.9977 - val_loss: 0.3736 - val_acc: 0.9296 1251 Epoch 879/1000 1252 68s 137ms/step - loss: 0.1065 - acc: 0.9977 - val_loss: 0.3767 - val_acc: 0.9280 1253 Epoch 880/1000 1254 69s 138ms/step - loss: 0.1055 - acc: 0.9979 - val_loss: 0.3741 - val_acc: 0.9285 1255 Epoch 881/1000 1256 68s 137ms/step - loss: 0.1056 - acc: 0.9979 - val_loss: 0.3716 - val_acc: 0.9290 1257 Epoch 882/1000 1258 69s 138ms/step - loss: 0.1061 - acc: 0.9977 - val_loss: 0.3736 - val_acc: 0.9295 1259 Epoch 883/1000 1260 69s 138ms/step - loss: 0.1066 - acc: 0.9976 - val_loss: 0.3745 - val_acc: 0.9307 1261 Epoch 884/1000 1262 69s 137ms/step - loss: 0.1059 - acc: 0.9975 - val_loss: 0.3702 - val_acc: 0.9302 1263 Epoch 885/1000 1264 69s 138ms/step - loss: 0.1051 - acc: 0.9979 - val_loss: 0.3656 - val_acc: 0.9311 1265 Epoch 886/1000 1266 68s 137ms/step - loss: 0.1051 - acc: 0.9978 - val_loss: 0.3677 - val_acc: 0.9305 1267 Epoch 887/1000 1268 68s 137ms/step - loss: 0.1062 - acc: 0.9974 - val_loss: 0.3636 - val_acc: 0.9315 1269 Epoch 888/1000 1270 69s 137ms/step - loss: 0.1052 - acc: 0.9977 - val_loss: 0.3710 - val_acc: 0.9295 1271 Epoch 889/1000 1272 68s 137ms/step - loss: 0.1046 - acc: 0.9979 - val_loss: 0.3642 - val_acc: 0.9318 1273 Epoch 890/1000 1274 69s 138ms/step - loss: 0.1051 - acc: 0.9975 - val_loss: 0.3673 - val_acc: 0.9306 1275 Epoch 891/1000 1276 69s 138ms/step - loss: 0.1045 - acc: 0.9978 - val_loss: 0.3681 - val_acc: 0.9299 1277 Epoch 892/1000 1278 68s 137ms/step - loss: 0.1043 - acc: 0.9979 - val_loss: 0.3659 - val_acc: 0.9320 1279 Epoch 893/1000 1280 69s 137ms/step - loss: 0.1040 - acc: 0.9979 - val_loss: 0.3627 - val_acc: 0.9326 1281 Epoch 894/1000 1282 69s 138ms/step - loss: 0.1041 - acc: 0.9976 - val_loss: 0.3698 - val_acc: 0.9301 1283 Epoch 895/1000 1284 68s 137ms/step - loss: 0.1039 - acc: 0.9978 - val_loss: 0.3659 - val_acc: 0.9321 1285 Epoch 896/1000 1286 69s 137ms/step - loss: 0.1040 - acc: 0.9978 - val_loss: 0.3718 - val_acc: 0.9300 1287 Epoch 897/1000 1288 68s 137ms/step - loss: 0.1039 - acc: 0.9977 - val_loss: 0.3728 - val_acc: 0.9311 1289 Epoch 898/1000 1290 68s 137ms/step - loss: 0.1044 - acc: 0.9973 - val_loss: 0.3743 - val_acc: 0.9313 1291 Epoch 899/1000 1292 69s 137ms/step - loss: 0.1036 - acc: 0.9976 - val_loss: 0.3675 - val_acc: 0.9312 1293 Epoch 900/1000 1294 69s 138ms/step - loss: 0.1030 - acc: 0.9979 - val_loss: 0.3730 - val_acc: 0.9313 1295 Epoch 901/1000 1296 lr changed to 9.999999310821295e-05 1297 69s 138ms/step - loss: 0.1023 - acc: 0.9982 - val_loss: 0.3709 - val_acc: 0.9310 1298 Epoch 902/1000 1299 69s 137ms/step - loss: 0.1025 - acc: 0.9979 - val_loss: 0.3690 - val_acc: 0.9311 1300 Epoch 903/1000 1301 68s 137ms/step - loss: 0.1024 - acc: 0.9980 - val_loss: 0.3679 - val_acc: 0.9311 1302 Epoch 904/1000 1303 69s 137ms/step - loss: 0.1020 - acc: 0.9982 - val_loss: 0.3673 - val_acc: 0.9315 1304 Epoch 905/1000 1305 69s 138ms/step - loss: 0.1027 - acc: 0.9979 - val_loss: 0.3672 - val_acc: 0.9310 1306 Epoch 906/1000 1307 69s 138ms/step - loss: 0.1015 - acc: 0.9984 - val_loss: 0.3678 - val_acc: 0.9304 1308 Epoch 907/1000 1309 69s 138ms/step - loss: 0.1016 - acc: 0.9984 - val_loss: 0.3673 - val_acc: 0.9302 1310 Epoch 908/1000 1311 69s 138ms/step - loss: 0.1031 - acc: 0.9977 - val_loss: 0.3667 - val_acc: 0.9307 1312 Epoch 909/1000 1313 69s 139ms/step - loss: 0.1019 - acc: 0.9983 - val_loss: 0.3672 - val_acc: 0.9317 1314 Epoch 910/1000 1315 69s 137ms/step - loss: 0.1018 - acc: 0.9983 - val_loss: 0.3671 - val_acc: 0.9313 1316 Epoch 911/1000 1317 69s 137ms/step - loss: 0.1018 - acc: 0.9982 - val_loss: 0.3669 - val_acc: 0.9309 1318 Epoch 912/1000 1319 69s 137ms/step - loss: 0.1014 - acc: 0.9986 - val_loss: 0.3677 - val_acc: 0.9303 1320 Epoch 913/1000 1321 68s 137ms/step - loss: 0.1015 - acc: 0.9982 - val_loss: 0.3666 - val_acc: 0.9303 1322 Epoch 914/1000 1323 69s 138ms/step - loss: 0.1015 - acc: 0.9984 - val_loss: 0.3659 - val_acc: 0.9309 1324 Epoch 915/1000 1325 69s 138ms/step - loss: 0.1013 - acc: 0.9983 - val_loss: 0.3651 - val_acc: 0.9318 1326 Epoch 916/1000 1327 69s 138ms/step - loss: 0.1014 - acc: 0.9983 - val_loss: 0.3652 - val_acc: 0.9322 1328 Epoch 917/1000 1329 69s 137ms/step - loss: 0.1010 - acc: 0.9984 - val_loss: 0.3648 - val_acc: 0.9322 1330 Epoch 918/1000 1331 68s 137ms/step - loss: 0.1016 - acc: 0.9981 - val_loss: 0.3644 - val_acc: 0.9324 1332 Epoch 919/1000 1333 69s 138ms/step - loss: 0.1013 - acc: 0.9983 - val_loss: 0.3635 - val_acc: 0.9319 1334 Epoch 920/1000 1335 69s 138ms/step - loss: 0.1008 - acc: 0.9984 - val_loss: 0.3629 - val_acc: 0.9318 1336 Epoch 921/1000 1337 69s 138ms/step - loss: 0.1006 - acc: 0.9986 - val_loss: 0.3627 - val_acc: 0.9319 1338 Epoch 922/1000 1339 69s 137ms/step - loss: 0.1007 - acc: 0.9985 - val_loss: 0.3632 - val_acc: 0.9314 1340 Epoch 923/1000 1341 69s 137ms/step - loss: 0.1004 - acc: 0.9987 - val_loss: 0.3626 - val_acc: 0.9319 1342 Epoch 924/1000 1343 69s 138ms/step - loss: 0.1012 - acc: 0.9985 - val_loss: 0.3629 - val_acc: 0.9319 1344 Epoch 925/1000 1345 69s 138ms/step - loss: 0.1011 - acc: 0.9983 - val_loss: 0.3620 - val_acc: 0.9318 1346 Epoch 926/1000 1347 69s 138ms/step - loss: 0.1005 - acc: 0.9987 - val_loss: 0.3617 - val_acc: 0.9322 1348 Epoch 927/1000 1349 69s 138ms/step - loss: 0.1013 - acc: 0.9983 - val_loss: 0.3618 - val_acc: 0.9330 1350 Epoch 928/1000 1351 69s 138ms/step - loss: 0.1005 - acc: 0.9985 - val_loss: 0.3614 - val_acc: 0.9321 1352 Epoch 929/1000 1353 69s 137ms/step - loss: 0.1006 - acc: 0.9985 - val_loss: 0.3616 - val_acc: 0.9319 1354 Epoch 930/1000 1355 69s 138ms/step - loss: 0.1006 - acc: 0.9985 - val_loss: 0.3613 - val_acc: 0.9321 1356 Epoch 931/1000 1357 69s 138ms/step - loss: 0.1009 - acc: 0.9985 - val_loss: 0.3612 - val_acc: 0.9328 1358 Epoch 932/1000 1359 69s 138ms/step - loss: 0.1004 - acc: 0.9985 - val_loss: 0.3612 - val_acc: 0.9319 1360 Epoch 933/1000 1361 69s 138ms/step - loss: 0.1004 - acc: 0.9987 - val_loss: 0.3618 - val_acc: 0.9314 1362 Epoch 934/1000 1363 69s 137ms/step - loss: 0.1008 - acc: 0.9983 - val_loss: 0.3615 - val_acc: 0.9316 1364 Epoch 935/1000 1365 69s 138ms/step - loss: 0.1011 - acc: 0.9983 - val_loss: 0.3621 - val_acc: 0.9317 1366 Epoch 936/1000 1367 68s 137ms/step - loss: 0.1008 - acc: 0.9985 - val_loss: 0.3617 - val_acc: 0.9320 1368 Epoch 937/1000 1369 69s 138ms/step - loss: 0.1006 - acc: 0.9984 - val_loss: 0.3613 - val_acc: 0.9322 1370 Epoch 938/1000 1371 69s 137ms/step - loss: 0.1008 - acc: 0.9985 - val_loss: 0.3613 - val_acc: 0.9325 1372 Epoch 939/1000 1373 68s 137ms/step - loss: 0.1006 - acc: 0.9984 - val_loss: 0.3614 - val_acc: 0.9326 1374 Epoch 940/1000 1375 69s 137ms/step - loss: 0.1006 - acc: 0.9983 - val_loss: 0.3612 - val_acc: 0.9320 1376 Epoch 941/1000 1377 69s 137ms/step - loss: 0.1005 - acc: 0.9984 - val_loss: 0.3612 - val_acc: 0.9322 1378 Epoch 942/1000 1379 69s 138ms/step - loss: 0.1001 - acc: 0.9986 - val_loss: 0.3615 - val_acc: 0.9318 1380 Epoch 943/1000 1381 68s 137ms/step - loss: 0.0998 - acc: 0.9987 - val_loss: 0.3613 - val_acc: 0.9320 1382 Epoch 944/1000 1383 69s 137ms/step - loss: 0.1006 - acc: 0.9985 - val_loss: 0.3613 - val_acc: 0.9323 1384 Epoch 945/1000 1385 69s 138ms/step - loss: 0.1000 - acc: 0.9985 - val_loss: 0.3608 - val_acc: 0.9319 1386 Epoch 946/1000 1387 69s 138ms/step - loss: 0.1001 - acc: 0.9987 - val_loss: 0.3608 - val_acc: 0.9313 1388 Epoch 947/1000 1389 69s 138ms/step - loss: 0.0998 - acc: 0.9987 - val_loss: 0.3606 - val_acc: 0.9314 1390 Epoch 948/1000 1391 69s 138ms/step - loss: 0.1000 - acc: 0.9986 - val_loss: 0.3609 - val_acc: 0.9311 1392 Epoch 949/1000 1393 69s 138ms/step - loss: 0.0995 - acc: 0.9988 - val_loss: 0.3610 - val_acc: 0.9316 1394 Epoch 950/1000 1395 69s 137ms/step - loss: 0.0999 - acc: 0.9986 - val_loss: 0.3609 - val_acc: 0.9317 1396 Epoch 951/1000 1397 69s 137ms/step - loss: 0.1002 - acc: 0.9986 - val_loss: 0.3612 - val_acc: 0.9314 1398 Epoch 952/1000 1399 68s 137ms/step - loss: 0.0992 - acc: 0.9989 - val_loss: 0.3618 - val_acc: 0.9312 1400 Epoch 953/1000 1401 68s 137ms/step - loss: 0.0996 - acc: 0.9988 - val_loss: 0.3617 - val_acc: 0.9317 1402 Epoch 954/1000 1403 69s 138ms/step - loss: 0.0994 - acc: 0.9987 - val_loss: 0.3617 - val_acc: 0.9323 1404 Epoch 955/1000 1405 69s 138ms/step - loss: 0.1004 - acc: 0.9984 - val_loss: 0.3610 - val_acc: 0.9320 1406 Epoch 956/1000 1407 69s 138ms/step - loss: 0.1000 - acc: 0.9986 - val_loss: 0.3616 - val_acc: 0.9318 1408 Epoch 957/1000 1409 68s 137ms/step - loss: 0.1000 - acc: 0.9985 - val_loss: 0.3617 - val_acc: 0.9319 1410 Epoch 958/1000 1411 69s 138ms/step - loss: 0.0996 - acc: 0.9985 - val_loss: 0.3627 - val_acc: 0.9323 1412 Epoch 959/1000 1413 69s 137ms/step - loss: 0.0995 - acc: 0.9987 - val_loss: 0.3625 - val_acc: 0.9316 1414 Epoch 960/1000 1415 69s 137ms/step - loss: 0.0995 - acc: 0.9987 - val_loss: 0.3634 - val_acc: 0.9317 1416 Epoch 961/1000 1417 69s 138ms/step - loss: 0.0998 - acc: 0.9985 - val_loss: 0.3636 - val_acc: 0.9318 1418 Epoch 962/1000 1419 69s 138ms/step - loss: 0.0997 - acc: 0.9986 - val_loss: 0.3645 - val_acc: 0.9319 1420 Epoch 963/1000 1421 68s 137ms/step - loss: 0.1001 - acc: 0.9984 - val_loss: 0.3637 - val_acc: 0.9316 1422 Epoch 964/1000 1423 69s 138ms/step - loss: 0.0998 - acc: 0.9985 - val_loss: 0.3631 - val_acc: 0.9317 1424 Epoch 965/1000 1425 69s 137ms/step - loss: 0.0995 - acc: 0.9988 - val_loss: 0.3625 - val_acc: 0.9316 1426 Epoch 966/1000 1427 68s 137ms/step - loss: 0.0998 - acc: 0.9986 - val_loss: 0.3622 - val_acc: 0.9324 1428 Epoch 967/1000 1429 68s 137ms/step - loss: 0.1002 - acc: 0.9985 - val_loss: 0.3623 - val_acc: 0.9327 1430 Epoch 968/1000 1431 68s 137ms/step - loss: 0.0993 - acc: 0.9987 - val_loss: 0.3627 - val_acc: 0.9324 1432 Epoch 969/1000 1433 69s 137ms/step - loss: 0.0996 - acc: 0.9985 - val_loss: 0.3624 - val_acc: 0.9327 1434 Epoch 970/1000 1435 69s 138ms/step - loss: 0.0999 - acc: 0.9985 - val_loss: 0.3618 - val_acc: 0.9323 1436 Epoch 971/1000 1437 69s 137ms/step - loss: 0.1001 - acc: 0.9983 - val_loss: 0.3616 - val_acc: 0.9324 1438 Epoch 972/1000 1439 68s 136ms/step - loss: 0.0994 - acc: 0.9986 - val_loss: 0.3620 - val_acc: 0.9320 1440 Epoch 973/1000 1441 68s 136ms/step - loss: 0.0997 - acc: 0.9985 - val_loss: 0.3627 - val_acc: 0.9324 1442 Epoch 974/1000 1443 68s 136ms/step - loss: 0.1000 - acc: 0.9985 - val_loss: 0.3623 - val_acc: 0.9321 1444 Epoch 975/1000 1445 68s 135ms/step - loss: 0.0989 - acc: 0.9990 - val_loss: 0.3619 - val_acc: 0.9321 1446 Epoch 976/1000 1447 68s 136ms/step - loss: 0.0992 - acc: 0.9987 - val_loss: 0.3612 - val_acc: 0.9323 1448 Epoch 977/1000 1449 68s 136ms/step - loss: 0.0996 - acc: 0.9986 - val_loss: 0.3612 - val_acc: 0.9317 1450 Epoch 978/1000 1451 68s 136ms/step - loss: 0.0997 - acc: 0.9986 - val_loss: 0.3610 - val_acc: 0.9326 1452 Epoch 979/1000 1453 68s 136ms/step - loss: 0.0991 - acc: 0.9987 - val_loss: 0.3611 - val_acc: 0.9327 1454 Epoch 980/1000 1455 69s 137ms/step - loss: 0.0988 - acc: 0.9989 - val_loss: 0.3615 - val_acc: 0.9326 1456 Epoch 981/1000 1457 69s 137ms/step - loss: 0.0992 - acc: 0.9987 - val_loss: 0.3619 - val_acc: 0.9324 1458 Epoch 982/1000 1459 68s 137ms/step - loss: 0.0994 - acc: 0.9986 - val_loss: 0.3619 - val_acc: 0.9332 1460 Epoch 983/1000 1461 69s 137ms/step - loss: 0.0995 - acc: 0.9986 - val_loss: 0.3617 - val_acc: 0.9329 1462 Epoch 984/1000 1463 68s 137ms/step - loss: 0.0991 - acc: 0.9987 - val_loss: 0.3622 - val_acc: 0.9328 1464 Epoch 985/1000 1465 68s 137ms/step - loss: 0.0991 - acc: 0.9987 - val_loss: 0.3628 - val_acc: 0.9322 1466 Epoch 986/1000 1467 68s 137ms/step - loss: 0.0993 - acc: 0.9987 - val_loss: 0.3625 - val_acc: 0.9319 1468 Epoch 987/1000 1469 68s 137ms/step - loss: 0.0995 - acc: 0.9986 - val_loss: 0.3629 - val_acc: 0.9317 1470 Epoch 988/1000 1471 69s 137ms/step - loss: 0.0993 - acc: 0.9985 - val_loss: 0.3628 - val_acc: 0.9319 1472 Epoch 989/1000 1473 69s 137ms/step - loss: 0.0997 - acc: 0.9984 - val_loss: 0.3624 - val_acc: 0.9322 1474 Epoch 990/1000 1475 69s 138ms/step - loss: 0.0993 - acc: 0.9986 - val_loss: 0.3622 - val_acc: 0.9323 1476 Epoch 991/1000 1477 68s 137ms/step - loss: 0.0993 - acc: 0.9986 - val_loss: 0.3625 - val_acc: 0.9327 1478 Epoch 992/1000 1479 69s 137ms/step - loss: 0.0993 - acc: 0.9988 - val_loss: 0.3630 - val_acc: 0.9325 1480 Epoch 993/1000 1481 68s 137ms/step - loss: 0.0992 - acc: 0.9984 - val_loss: 0.3634 - val_acc: 0.9320 1482 Epoch 994/1000 1483 69s 138ms/step - loss: 0.0991 - acc: 0.9988 - val_loss: 0.3627 - val_acc: 0.9328 1484 Epoch 995/1000 1485 69s 138ms/step - loss: 0.0989 - acc: 0.9989 - val_loss: 0.3637 - val_acc: 0.9321 1486 Epoch 996/1000 1487 69s 138ms/step - loss: 0.0994 - acc: 0.9986 - val_loss: 0.3623 - val_acc: 0.9319 1488 Epoch 997/1000 1489 69s 138ms/step - loss: 0.0987 - acc: 0.9987 - val_loss: 0.3622 - val_acc: 0.9322 1490 Epoch 998/1000 1491 69s 138ms/step - loss: 0.0989 - acc: 0.9988 - val_loss: 0.3621 - val_acc: 0.9325 1492 Epoch 999/1000 1493 69s 138ms/step - loss: 0.0993 - acc: 0.9984 - val_loss: 0.3615 - val_acc: 0.9326 1494 Epoch 1000/1000 1495 69s 138ms/step - loss: 0.0986 - acc: 0.9988 - val_loss: 0.3614 - val_acc: 0.9323 1496 Train loss: 0.09943642792105675 1497 Train accuracy: 0.9982600016593933 1498 Test loss: 0.3614072059094906 1499 Test accuracy: 0.9322999995946885
在使用了shear_range = 30的数据增强以后,准确率降了呢。。
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