深度殘差網路+自適應引數化ReLU啟用函式(調參記錄19)Cifar10~93.96%
由於調參記錄18依然存在過擬合,本文將自適應引數化ReLU啟用函式中最後一層的神經元個數減少為1個,繼續測試深度殘差網路+自適應引數化ReLU啟用函式在Cifar10資料集上的效果。
同時,迭代次數從調參記錄18中的5000個epoch,減少到了500個epoch,因為5000次實在是太費時間了,差不多要四天才能跑完。
自適應引數化ReLU啟用函式的基本原理如下:
Keras程式如下:
#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Tue Apr 14 04:17:45 2020 Implemented using TensorFlow 1.10.0 and Keras 2.2.1 Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht, Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis, IEEE Transactions on Industrial Electronics, 2020, DOI: 10.1109/TIE.2020.2972458 @author: Minghang Zhao """ from __future__ import print_function import keras import numpy as np from keras.datasets import cifar10 from keras.layers import Dense, Conv2D, BatchNormalization, Activation, Minimum from keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D, Concatenate, Reshape from keras.regularizers import l2 from keras import backend as K from keras.models import Model from keras import optimizers from keras.preprocessing.image import ImageDataGenerator from keras.callbacks import LearningRateScheduler K.set_learning_phase(1) # The data, split between train and test sets (x_train, y_train), (x_test, y_test) = cifar10.load_data() # Noised data x_train = x_train.astype('float32') / 255. x_test = x_test.astype('float32') / 255. x_test = x_test-np.mean(x_train) x_train = x_train-np.mean(x_train) print('x_train shape:', x_train.shape) print(x_train.shape[0], 'train samples') print(x_test.shape[0], 'test samples') # convert class vectors to binary class matrices y_train = keras.utils.to_categorical(y_train, 10) y_test = keras.utils.to_categorical(y_test, 10) # Schedule the learning rate, multiply 0.1 every 150 epoches def 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(1, 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((1,1,1))(scales) # apply a paramtetric relu neg_part = keras.layers.multiply([scales, neg_input]) return keras.layers.add([pos_input, neg_part]) # Residual Block def residual_block(incoming, nb_blocks, out_channels, downsample=False, downsample_strides=2): residual = incoming in_channels = incoming.get_shape().as_list()[-1] for i in range(nb_blocks): identity = residual if not downsample: downsample_strides = 1 residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) residual = aprelu(residual) residual = Conv2D(out_channels, 3, strides=(downsample_strides, downsample_strides), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(residual) residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual) residual = aprelu(residual) residual = Conv2D(out_channels, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(residual) # Downsampling if downsample_strides > 1: identity = AveragePooling2D(pool_size=(1,1), strides=(2,2))(identity) # Zero_padding to match channels if in_channels != out_channels: zeros_identity = keras.layers.subtract([identity, identity]) identity = keras.layers.concatenate([identity, zeros_identity]) in_channels = out_channels residual = keras.layers.add([residual, identity]) return residual # define and train a model inputs = Input(shape=(32, 32, 3)) net = Conv2D(16, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(inputs) net = residual_block(net, 9, 32, downsample=False) net = residual_block(net, 1, 32, downsample=True) net = residual_block(net, 8, 32, downsample=False) net = residual_block(net, 1, 64, downsample=True) net = residual_block(net, 8, 64, downsample=False) net = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(net) net = aprelu(net) net = GlobalAveragePooling2D()(net) outputs = Dense(10, activation='softmax', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(net) model = Model(inputs=inputs, outputs=outputs) sgd = optimizers.SGD(lr=0.1, decay=0., momentum=0.9, nesterov=True) model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) # data augmentation datagen = ImageDataGenerator( # randomly rotate images in the range (deg 0 to 180) rotation_range=30, # Range for random zoom zoom_range = 0.2, # shear angle in counter-clockwise direction in degrees shear_range = 30, # randomly flip images horizontal_flip=True, # randomly shift images horizontally width_shift_range=0.125, # randomly shift images vertically height_shift_range=0.125) reduce_lr = LearningRateScheduler(scheduler) # fit the model on the batches generated by datagen.flow(). model.fit_generator(datagen.flow(x_train, y_train, batch_size=100), validation_data=(x_test, y_test), epochs=500, verbose=1, callbacks=[reduce_lr], workers=4) # get results K.set_learning_phase(0) DRSN_train_score = model.evaluate(x_train, y_train, batch_size=100, verbose=0) print('Train loss:', DRSN_train_score[0]) print('Train accuracy:', DRSN_train_score[1]) DRSN_test_score = model.evaluate(x_test, y_test, batch_size=100, verbose=0) print('Test loss:', DRSN_test_score[0]) print('Test accuracy:', DRSN_test_score[1])
實驗結果如下:
Using TensorFlow backend. x_train shape: (50000, 32, 32, 3) 50000 train samples 10000 test samples Epoch 1/500 107s 215ms/step - loss: 2.3702 - acc: 0.3922 - val_loss: 1.9601 - val_acc: 0.5235 Epoch 2/500 77s 154ms/step - loss: 1.9532 - acc: 0.5157 - val_loss: 1.6734 - val_acc: 0.5998 Epoch 3/500 77s 154ms/step - loss: 1.6989 - acc: 0.5797 - val_loss: 1.4728 - val_acc: 0.6495 Epoch 4/500 77s 154ms/step - loss: 1.5366 - acc: 0.6184 - val_loss: 1.3253 - val_acc: 0.6888 Epoch 5/500 77s 154ms/step - loss: 1.4110 - acc: 0.6444 - val_loss: 1.2022 - val_acc: 0.7197 Epoch 6/500 77s 154ms/step - loss: 1.3059 - acc: 0.6707 - val_loss: 1.1398 - val_acc: 0.7236 Epoch 7/500 77s 154ms/step - loss: 1.2295 - acc: 0.6873 - val_loss: 1.0509 - val_acc: 0.7515 Epoch 8/500 77s 154ms/step - loss: 1.1568 - acc: 0.7041 - val_loss: 0.9907 - val_acc: 0.7686 Epoch 9/500 77s 154ms/step - loss: 1.1016 - acc: 0.7207 - val_loss: 0.9470 - val_acc: 0.7863 Epoch 10/500 77s 154ms/step - loss: 1.0521 - acc: 0.7346 - val_loss: 0.9005 - val_acc: 0.7911 Epoch 11/500 77s 154ms/step - loss: 1.0246 - acc: 0.7423 - val_loss: 0.8991 - val_acc: 0.7881 Epoch 12/500 77s 154ms/step - loss: 0.9941 - acc: 0.7506 - val_loss: 0.8390 - val_acc: 0.8093 Epoch 13/500 77s 154ms/step - loss: 0.9642 - acc: 0.7602 - val_loss: 0.8239 - val_acc: 0.8147 Epoch 14/500 77s 154ms/step - loss: 0.9465 - acc: 0.7652 - val_loss: 0.8057 - val_acc: 0.8170 Epoch 15/500 77s 154ms/step - loss: 0.9296 - acc: 0.7701 - val_loss: 0.8180 - val_acc: 0.8114 Epoch 16/500 77s 154ms/step - loss: 0.9103 - acc: 0.7767 - val_loss: 0.7975 - val_acc: 0.8207 Epoch 17/500 77s 154ms/step - loss: 0.9027 - acc: 0.7801 - val_loss: 0.8048 - val_acc: 0.8186 Epoch 18/500 77s 154ms/step - loss: 0.8904 - acc: 0.7848 - val_loss: 0.7542 - val_acc: 0.8376 Epoch 19/500 77s 154ms/step - loss: 0.8765 - acc: 0.7889 - val_loss: 0.7633 - val_acc: 0.8313 Epoch 20/500 77s 154ms/step - loss: 0.8739 - acc: 0.7913 - val_loss: 0.7411 - val_acc: 0.8432 Epoch 21/500 77s 154ms/step - loss: 0.8587 - acc: 0.7976 - val_loss: 0.7357 - val_acc: 0.8466 Epoch 22/500 77s 154ms/step - loss: 0.8505 - acc: 0.7982 - val_loss: 0.7369 - val_acc: 0.8437 Epoch 23/500 77s 154ms/step - loss: 0.8495 - acc: 0.8014 - val_loss: 0.7507 - val_acc: 0.8415 Epoch 24/500 77s 154ms/step - loss: 0.8382 - acc: 0.8070 - val_loss: 0.7494 - val_acc: 0.8423 Epoch 25/500 77s 154ms/step - loss: 0.8339 - acc: 0.8097 - val_loss: 0.7374 - val_acc: 0.8441 Epoch 26/500 77s 154ms/step - loss: 0.8284 - acc: 0.8105 - val_loss: 0.7195 - val_acc: 0.8517 Epoch 27/500 77s 154ms/step - loss: 0.8244 - acc: 0.8139 - val_loss: 0.7054 - val_acc: 0.8611 Epoch 28/500 77s 154ms/step - loss: 0.8242 - acc: 0.8143 - val_loss: 0.6997 - val_acc: 0.8614 Epoch 29/500 77s 154ms/step - loss: 0.8145 - acc: 0.8186 - val_loss: 0.6966 - val_acc: 0.8598 Epoch 30/500 77s 154ms/step - loss: 0.8092 - acc: 0.8197 - val_loss: 0.7344 - val_acc: 0.8498 Epoch 31/500 77s 154ms/step - loss: 0.8048 - acc: 0.8219 - val_loss: 0.7232 - val_acc: 0.8574 Epoch 32/500 77s 154ms/step - loss: 0.8054 - acc: 0.8244 - val_loss: 0.6888 - val_acc: 0.8652 Epoch 33/500 77s 154ms/step - loss: 0.8000 - acc: 0.8231 - val_loss: 0.7236 - val_acc: 0.8533 Epoch 34/500 77s 154ms/step - loss: 0.7994 - acc: 0.8258 - val_loss: 0.7096 - val_acc: 0.8584 Epoch 35/500 77s 154ms/step - loss: 0.7933 - acc: 0.8291 - val_loss: 0.7063 - val_acc: 0.8602 Epoch 36/500 77s 154ms/step - loss: 0.7955 - acc: 0.8275 - val_loss: 0.7124 - val_acc: 0.8599 Epoch 37/500 77s 154ms/step - loss: 0.7961 - acc: 0.8280 - val_loss: 0.7020 - val_acc: 0.8650 Epoch 38/500 77s 154ms/step - loss: 0.7864 - acc: 0.8332 - val_loss: 0.7201 - val_acc: 0.8573 Epoch 39/500 77s 154ms/step - loss: 0.7949 - acc: 0.8303 - val_loss: 0.7009 - val_acc: 0.8648 Epoch 40/500 77s 154ms/step - loss: 0.7781 - acc: 0.8349 - val_loss: 0.6954 - val_acc: 0.8636 Epoch 41/500 77s 154ms/step - loss: 0.7821 - acc: 0.8352 - val_loss: 0.6819 - val_acc: 0.8736 Epoch 42/500 77s 154ms/step - loss: 0.7805 - acc: 0.8345 - val_loss: 0.7347 - val_acc: 0.8550 Epoch 43/500 77s 154ms/step - loss: 0.7749 - acc: 0.8384 - val_loss: 0.7029 - val_acc: 0.8642 Epoch 44/500 77s 154ms/step - loss: 0.7777 - acc: 0.8368 - val_loss: 0.6967 - val_acc: 0.8676 Epoch 45/500 77s 154ms/step - loss: 0.7725 - acc: 0.8393 - val_loss: 0.6867 - val_acc: 0.8722 Epoch 46/500 77s 154ms/step - loss: 0.7737 - acc: 0.8408 - val_loss: 0.7075 - val_acc: 0.8644 Epoch 47/500 77s 154ms/step - loss: 0.7734 - acc: 0.8395 - val_loss: 0.6958 - val_acc: 0.8667 Epoch 48/500 77s 154ms/step - loss: 0.7750 - acc: 0.8404 - val_loss: 0.6956 - val_acc: 0.8701 Epoch 49/500 77s 154ms/step - loss: 0.7691 - acc: 0.8417 - val_loss: 0.6977 - val_acc: 0.8677 Epoch 50/500 77s 154ms/step - loss: 0.7661 - acc: 0.8433 - val_loss: 0.7094 - val_acc: 0.8683 Epoch 51/500 77s 154ms/step - loss: 0.7638 - acc: 0.8469 - val_loss: 0.6972 - val_acc: 0.8678 Epoch 52/500 77s 154ms/step - loss: 0.7613 - acc: 0.8455 - val_loss: 0.7113 - val_acc: 0.8676 Epoch 53/500 77s 154ms/step - loss: 0.7647 - acc: 0.8460 - val_loss: 0.6946 - val_acc: 0.8692 Epoch 54/500 77s 154ms/step - loss: 0.7572 - acc: 0.8468 - val_loss: 0.7242 - val_acc: 0.8628 Epoch 55/500 77s 154ms/step - loss: 0.7560 - acc: 0.8504 - val_loss: 0.7084 - val_acc: 0.8671 Epoch 56/500 77s 154ms/step - loss: 0.7578 - acc: 0.8473 - val_loss: 0.6979 - val_acc: 0.8724 Epoch 57/500 77s 154ms/step - loss: 0.7635 - acc: 0.8468 - val_loss: 0.6928 - val_acc: 0.8722 Epoch 58/500 77s 154ms/step - loss: 0.7563 - acc: 0.8489 - val_loss: 0.6907 - val_acc: 0.8736 Epoch 59/500 77s 154ms/step - loss: 0.7578 - acc: 0.8495 - val_loss: 0.6854 - val_acc: 0.8757 Epoch 60/500 77s 154ms/step - loss: 0.7565 - acc: 0.8482 - val_loss: 0.6837 - val_acc: 0.8743 Epoch 61/500 77s 154ms/step - loss: 0.7570 - acc: 0.8499 - val_loss: 0.6821 - val_acc: 0.8742 Epoch 62/500 77s 154ms/step - loss: 0.7595 - acc: 0.8484 - val_loss: 0.6889 - val_acc: 0.8722 Epoch 63/500 77s 154ms/step - loss: 0.7536 - acc: 0.8512 - val_loss: 0.6748 - val_acc: 0.8800 Epoch 64/500 77s 154ms/step - loss: 0.7539 - acc: 0.8514 - val_loss: 0.6508 - val_acc: 0.8901 Epoch 65/500 77s 154ms/step - loss: 0.7483 - acc: 0.8535 - val_loss: 0.6852 - val_acc: 0.8777 Epoch 66/500 77s 154ms/step - loss: 0.7496 - acc: 0.8535 - val_loss: 0.6940 - val_acc: 0.8756 Epoch 67/500 77s 154ms/step - loss: 0.7568 - acc: 0.8505 - val_loss: 0.6830 - val_acc: 0.8805 Epoch 68/500 77s 154ms/step - loss: 0.7549 - acc: 0.8508 - val_loss: 0.6732 - val_acc: 0.8840 Epoch 69/500 77s 154ms/step - loss: 0.7479 - acc: 0.8549 - val_loss: 0.6955 - val_acc: 0.8744 Epoch 70/500 77s 154ms/step - loss: 0.7468 - acc: 0.8551 - val_loss: 0.6964 - val_acc: 0.8746 Epoch 71/500 77s 154ms/step - loss: 0.7499 - acc: 0.8553 - val_loss: 0.6850 - val_acc: 0.8784 Epoch 72/500 77s 154ms/step - loss: 0.7462 - acc: 0.8553 - val_loss: 0.6937 - val_acc: 0.8771 Epoch 73/500 77s 154ms/step - loss: 0.7467 - acc: 0.8559 - val_loss: 0.6876 - val_acc: 0.8761 Epoch 74/500 77s 154ms/step - loss: 0.7467 - acc: 0.8559 - val_loss: 0.7029 - val_acc: 0.8715 Epoch 75/500 77s 154ms/step - loss: 0.7435 - acc: 0.8561 - val_loss: 0.7184 - val_acc: 0.8663 Epoch 76/500 77s 154ms/step - loss: 0.7467 - acc: 0.8558 - val_loss: 0.6751 - val_acc: 0.8808 Epoch 77/500 77s 154ms/step - loss: 0.7398 - acc: 0.8575 - val_loss: 0.6843 - val_acc: 0.8812 Epoch 78/500 77s 154ms/step - loss: 0.7463 - acc: 0.8571 - val_loss: 0.6802 - val_acc: 0.8800 Epoch 79/500 77s 154ms/step - loss: 0.7395 - acc: 0.8568 - val_loss: 0.6877 - val_acc: 0.8769 Epoch 80/500 77s 154ms/step - loss: 0.7403 - acc: 0.8580 - val_loss: 0.6912 - val_acc: 0.8792 Epoch 81/500 77s 154ms/step - loss: 0.7429 - acc: 0.8555 - val_loss: 0.6887 - val_acc: 0.8787 Epoch 82/500 77s 154ms/step - loss: 0.7408 - acc: 0.8572 - val_loss: 0.7134 - val_acc: 0.8709 Epoch 83/500 77s 154ms/step - loss: 0.7413 - acc: 0.8573 - val_loss: 0.6921 - val_acc: 0.8776 Epoch 84/500 77s 154ms/step - loss: 0.7393 - acc: 0.8588 - val_loss: 0.6965 - val_acc: 0.8737 Epoch 85/500 77s 154ms/step - loss: 0.7440 - acc: 0.8568 - val_loss: 0.6806 - val_acc: 0.8803 Epoch 86/500 77s 154ms/step - loss: 0.7407 - acc: 0.8589 - val_loss: 0.6658 - val_acc: 0.8871 Epoch 87/500 77s 154ms/step - loss: 0.7366 - acc: 0.8587 - val_loss: 0.6804 - val_acc: 0.8812 Epoch 88/500 77s 154ms/step - loss: 0.7406 - acc: 0.8582 - val_loss: 0.6686 - val_acc: 0.8869 Epoch 89/500 77s 154ms/step - loss: 0.7345 - acc: 0.8611 - val_loss: 0.6744 - val_acc: 0.8836 Epoch 90/500 77s 154ms/step - loss: 0.7318 - acc: 0.8614 - val_loss: 0.6715 - val_acc: 0.8852 Epoch 91/500 77s 154ms/step - loss: 0.7376 - acc: 0.8600 - val_loss: 0.6939 - val_acc: 0.8737 Epoch 92/500 77s 154ms/step - loss: 0.7420 - acc: 0.8586 - val_loss: 0.6890 - val_acc: 0.8763 Epoch 93/500 77s 154ms/step - loss: 0.7315 - acc: 0.8631 - val_loss: 0.6761 - val_acc: 0.8821 Epoch 94/500 77s 154ms/step - loss: 0.7341 - acc: 0.8610 - val_loss: 0.6902 - val_acc: 0.8801 Epoch 95/500 77s 154ms/step - loss: 0.7370 - acc: 0.8604 - val_loss: 0.6938 - val_acc: 0.8742 Epoch 96/500 77s 154ms/step - loss: 0.7345 - acc: 0.8619 - val_loss: 0.6785 - val_acc: 0.8803 Epoch 97/500 77s 154ms/step - loss: 0.7356 - acc: 0.8598 - val_loss: 0.6974 - val_acc: 0.8753 Epoch 98/500 77s 154ms/step - loss: 0.7340 - acc: 0.8622 - val_loss: 0.6847 - val_acc: 0.8821 Epoch 99/500 77s 154ms/step - loss: 0.7321 - acc: 0.8632 - val_loss: 0.6772 - val_acc: 0.8883 Epoch 100/500 77s 154ms/step - loss: 0.7301 - acc: 0.8650 - val_loss: 0.6659 - val_acc: 0.8881 Epoch 101/500 77s 154ms/step - loss: 0.7364 - acc: 0.8625 - val_loss: 0.7062 - val_acc: 0.8735 Epoch 102/500 77s 154ms/step - loss: 0.7360 - acc: 0.8613 - val_loss: 0.6749 - val_acc: 0.8819 Epoch 103/500 77s 154ms/step - loss: 0.7305 - acc: 0.8628 - val_loss: 0.6853 - val_acc: 0.8840 Epoch 104/500 77s 154ms/step - loss: 0.7333 - acc: 0.8638 - val_loss: 0.6813 - val_acc: 0.8800 Epoch 105/500 77s 154ms/step - loss: 0.7308 - acc: 0.8631 - val_loss: 0.6599 - val_acc: 0.8892 Epoch 106/500 77s 154ms/step - loss: 0.7355 - acc: 0.8643 - val_loss: 0.6833 - val_acc: 0.8816 Epoch 107/500 77s 154ms/step - loss: 0.7286 - acc: 0.8654 - val_loss: 0.6744 - val_acc: 0.8830 Epoch 108/500 77s 154ms/step - loss: 0.7278 - acc: 0.8653 - val_loss: 0.6870 - val_acc: 0.8807 Epoch 109/500 77s 154ms/step - loss: 0.7270 - acc: 0.8652 - val_loss: 0.6901 - val_acc: 0.8821 Epoch 110/500 77s 154ms/step - loss: 0.7260 - acc: 0.8646 - val_loss: 0.6908 - val_acc: 0.8820 Epoch 111/500 77s 154ms/step - loss: 0.7290 - acc: 0.8645 - val_loss: 0.6973 - val_acc: 0.8755 Epoch 112/500 77s 154ms/step - loss: 0.7336 - acc: 0.8615 - val_loss: 0.6845 - val_acc: 0.8812 Epoch 113/500 77s 154ms/step - loss: 0.7296 - acc: 0.8635 - val_loss: 0.6835 - val_acc: 0.8811 Epoch 114/500 77s 154ms/step - loss: 0.7310 - acc: 0.8647 - val_loss: 0.6822 - val_acc: 0.8820 Epoch 115/500 77s 154ms/step - loss: 0.7251 - acc: 0.8660 - val_loss: 0.6822 - val_acc: 0.8803 Epoch 116/500 77s 154ms/step - loss: 0.7313 - acc: 0.8633 - val_loss: 0.6572 - val_acc: 0.8908 Epoch 117/500 77s 154ms/step - loss: 0.7289 - acc: 0.8636 - val_loss: 0.6956 - val_acc: 0.8817 Epoch 118/500 77s 154ms/step - loss: 0.7233 - acc: 0.8670 - val_loss: 0.7052 - val_acc: 0.8738 Epoch 119/500 77s 154ms/step - loss: 0.7243 - acc: 0.8667 - val_loss: 0.6675 - val_acc: 0.8891 Epoch 120/500 77s 154ms/step - loss: 0.7269 - acc: 0.8658 - val_loss: 0.6815 - val_acc: 0.8834 Epoch 121/500 77s 154ms/step - loss: 0.7248 - acc: 0.8656 - val_loss: 0.6670 - val_acc: 0.8878 Epoch 122/500 77s 154ms/step - loss: 0.7223 - acc: 0.8690 - val_loss: 0.6658 - val_acc: 0.8892 Epoch 123/500 77s 154ms/step - loss: 0.7248 - acc: 0.8675 - val_loss: 0.6889 - val_acc: 0.8798 Epoch 124/500 77s 154ms/step - loss: 0.7209 - acc: 0.8675 - val_loss: 0.6703 - val_acc: 0.8857 Epoch 125/500 77s 154ms/step - loss: 0.7276 - acc: 0.8668 - val_loss: 0.6875 - val_acc: 0.8791 Epoch 126/500 77s 154ms/step - loss: 0.7251 - acc: 0.8659 - val_loss: 0.6836 - val_acc: 0.8829 Epoch 127/500 77s 154ms/step - loss: 0.7280 - acc: 0.8668 - val_loss: 0.6832 - val_acc: 0.8836 Epoch 128/500 77s 154ms/step - loss: 0.7242 - acc: 0.8672 - val_loss: 0.6848 - val_acc: 0.8847 Epoch 129/500 77s 154ms/step - loss: 0.7267 - acc: 0.8663 - val_loss: 0.6778 - val_acc: 0.8852 Epoch 130/500 77s 154ms/step - loss: 0.7289 - acc: 0.8648 - val_loss: 0.6786 - val_acc: 0.8837 Epoch 131/500 77s 154ms/step - loss: 0.7219 - acc: 0.8685 - val_loss: 0.6562 - val_acc: 0.8899 Epoch 132/500 77s 154ms/step - loss: 0.7186 - acc: 0.8678 - val_loss: 0.6765 - val_acc: 0.8854 Epoch 133/500 77s 154ms/step - loss: 0.7199 - acc: 0.8688 - val_loss: 0.6697 - val_acc: 0.8887 Epoch 134/500 77s 154ms/step - loss: 0.7163 - acc: 0.8687 - val_loss: 0.6692 - val_acc: 0.8881 Epoch 135/500 77s 154ms/step - loss: 0.7208 - acc: 0.8671 - val_loss: 0.6777 - val_acc: 0.8818 Epoch 136/500 77s 154ms/step - loss: 0.7257 - acc: 0.8666 - val_loss: 0.6726 - val_acc: 0.8896 Epoch 137/500 77s 154ms/step - loss: 0.7224 - acc: 0.8658 - val_loss: 0.7068 - val_acc: 0.8746 Epoch 138/500 77s 154ms/step - loss: 0.7202 - acc: 0.8686 - val_loss: 0.6746 - val_acc: 0.8850 Epoch 139/500 77s 154ms/step - loss: 0.7253 - acc: 0.8672 - val_loss: 0.6856 - val_acc: 0.8843 Epoch 140/500 77s 154ms/step - loss: 0.7216 - acc: 0.8681 - val_loss: 0.6837 - val_acc: 0.8835 Epoch 141/500 77s 154ms/step - loss: 0.7251 - acc: 0.8686 - val_loss: 0.6652 - val_acc: 0.8893 Epoch 142/500 77s 154ms/step - loss: 0.7200 - acc: 0.8697 - val_loss: 0.6572 - val_acc: 0.8915 Epoch 143/500 77s 154ms/step - loss: 0.7208 - acc: 0.8682 - val_loss: 0.6792 - val_acc: 0.8858 Epoch 144/500 77s 154ms/step - loss: 0.7231 - acc: 0.8691 - val_loss: 0.6885 - val_acc: 0.8835 Epoch 145/500 77s 154ms/step - loss: 0.7191 - acc: 0.8704 - val_loss: 0.6828 - val_acc: 0.8862 Epoch 146/500 77s 153ms/step - loss: 0.7209 - acc: 0.8689 - val_loss: 0.6849 - val_acc: 0.8812 Epoch 147/500 77s 154ms/step - loss: 0.7243 - acc: 0.8688 - val_loss: 0.6824 - val_acc: 0.8838 Epoch 148/500 77s 154ms/step - loss: 0.7194 - acc: 0.8700 - val_loss: 0.6714 - val_acc: 0.8889 Epoch 149/500 77s 154ms/step - loss: 0.7220 - acc: 0.8691 - val_loss: 0.6686 - val_acc: 0.8902 Epoch 150/500 77s 154ms/step - loss: 0.7181 - acc: 0.8700 - val_loss: 0.6723 - val_acc: 0.8851 Epoch 151/500 lr changed to 0.010000000149011612 77s 154ms/step - loss: 0.6046 - acc: 0.9093 - val_loss: 0.5729 - val_acc: 0.9191 Epoch 152/500 77s 154ms/step - loss: 0.5434 - acc: 0.9281 - val_loss: 0.5547 - val_acc: 0.9222 Epoch 153/500 77s 154ms/step - loss: 0.5269 - acc: 0.9317 - val_loss: 0.5470 - val_acc: 0.9232 Epoch 154/500 77s 154ms/step - loss: 0.5083 - acc: 0.9357 - val_loss: 0.5377 - val_acc: 0.9255 Epoch 155/500 77s 154ms/step - loss: 0.4961 - acc: 0.9395 - val_loss: 0.5305 - val_acc: 0.9254 Epoch 156/500 77s 154ms/step - loss: 0.4827 - acc: 0.9411 - val_loss: 0.5238 - val_acc: 0.9269 Epoch 157/500 77s 154ms/step - loss: 0.4718 - acc: 0.9440 - val_loss: 0.5187 - val_acc: 0.9289 Epoch 158/500 77s 154ms/step - loss: 0.4637 - acc: 0.9443 - val_loss: 0.5135 - val_acc: 0.9290 Epoch 159/500 77s 154ms/step - loss: 0.4554 - acc: 0.9453 - val_loss: 0.5119 - val_acc: 0.9291 Epoch 160/500 77s 154ms/step - loss: 0.4475 - acc: 0.9456 - val_loss: 0.5078 - val_acc: 0.9271 Epoch 161/500 77s 154ms/step - loss: 0.4393 - acc: 0.9484 - val_loss: 0.4957 - val_acc: 0.9317 Epoch 162/500 77s 154ms/step - loss: 0.4290 - acc: 0.9491 - val_loss: 0.4937 - val_acc: 0.9283 Epoch 163/500 77s 154ms/step - loss: 0.4224 - acc: 0.9501 - val_loss: 0.4897 - val_acc: 0.9293 Epoch 164/500 77s 154ms/step - loss: 0.4194 - acc: 0.9498 - val_loss: 0.4830 - val_acc: 0.9312 Epoch 165/500 77s 154ms/step - loss: 0.4101 - acc: 0.9529 - val_loss: 0.4823 - val_acc: 0.9309 Epoch 166/500 77s 154ms/step - loss: 0.4087 - acc: 0.9508 - val_loss: 0.4761 - val_acc: 0.9302 Epoch 167/500 77s 154ms/step - loss: 0.3993 - acc: 0.9528 - val_loss: 0.4733 - val_acc: 0.9307 Epoch 168/500 77s 154ms/step - loss: 0.3958 - acc: 0.9528 - val_loss: 0.4612 - val_acc: 0.9310 Epoch 169/500 77s 154ms/step - loss: 0.3904 - acc: 0.9536 - val_loss: 0.4725 - val_acc: 0.9294 Epoch 170/500 77s 154ms/step - loss: 0.3820 - acc: 0.9552 - val_loss: 0.4625 - val_acc: 0.9293 Epoch 171/500 77s 154ms/step - loss: 0.3769 - acc: 0.9553 - val_loss: 0.4596 - val_acc: 0.9292 Epoch 172/500 77s 154ms/step - loss: 0.3732 - acc: 0.9567 - val_loss: 0.4686 - val_acc: 0.9271 Epoch 173/500 77s 154ms/step - loss: 0.3692 - acc: 0.9566 - val_loss: 0.4595 - val_acc: 0.9275 Epoch 174/500 77s 154ms/step - loss: 0.3697 - acc: 0.9547 - val_loss: 0.4510 - val_acc: 0.9305 Epoch 175/500 77s 154ms/step - loss: 0.3592 - acc: 0.9577 - val_loss: 0.4485 - val_acc: 0.9294 Epoch 176/500 77s 154ms/step - loss: 0.3553 - acc: 0.9583 - val_loss: 0.4527 - val_acc: 0.9276 Epoch 177/500 77s 154ms/step - loss: 0.3519 - acc: 0.9588 - val_loss: 0.4501 - val_acc: 0.9269 Epoch 178/500 77s 154ms/step - loss: 0.3508 - acc: 0.9571 - val_loss: 0.4489 - val_acc: 0.9253 Epoch 179/500 77s 154ms/step - loss: 0.3461 - acc: 0.9577 - val_loss: 0.4484 - val_acc: 0.9260 Epoch 180/500 77s 154ms/step - loss: 0.3446 - acc: 0.9583 - val_loss: 0.4392 - val_acc: 0.9274 Epoch 181/500 77s 154ms/step - loss: 0.3375 - acc: 0.9591 - val_loss: 0.4435 - val_acc: 0.9287 Epoch 182/500 77s 154ms/step - loss: 0.3375 - acc: 0.9584 - val_loss: 0.4446 - val_acc: 0.9278 Epoch 183/500 77s 154ms/step - loss: 0.3358 - acc: 0.9586 - val_loss: 0.4434 - val_acc: 0.9268 Epoch 184/500 77s 154ms/step - loss: 0.3294 - acc: 0.9607 - val_loss: 0.4529 - val_acc: 0.9267 Epoch 185/500 77s 154ms/step - loss: 0.3352 - acc: 0.9571 - val_loss: 0.4392 - val_acc: 0.9272 Epoch 186/500 77s 154ms/step - loss: 0.3289 - acc: 0.9587 - val_loss: 0.4367 - val_acc: 0.9276 Epoch 187/500 77s 154ms/step - loss: 0.3267 - acc: 0.9595 - val_loss: 0.4333 - val_acc: 0.9257 Epoch 188/500 77s 154ms/step - loss: 0.3191 - acc: 0.9600 - val_loss: 0.4392 - val_acc: 0.9257 Epoch 189/500 77s 154ms/step - loss: 0.3169 - acc: 0.9608 - val_loss: 0.4366 - val_acc: 0.9261 Epoch 190/500 77s 154ms/step - loss: 0.3180 - acc: 0.9594 - val_loss: 0.4283 - val_acc: 0.9274 Epoch 191/500 77s 154ms/step - loss: 0.3128 - acc: 0.9605 - val_loss: 0.4351 - val_acc: 0.9228 Epoch 192/500 77s 154ms/step - loss: 0.3105 - acc: 0.9610 - val_loss: 0.4294 - val_acc: 0.9255 Epoch 193/500 77s 154ms/step - loss: 0.3096 - acc: 0.9605 - val_loss: 0.4258 - val_acc: 0.9272 Epoch 194/500 77s 154ms/step - loss: 0.3074 - acc: 0.9614 - val_loss: 0.4288 - val_acc: 0.9248 Epoch 195/500 77s 154ms/step - loss: 0.3120 - acc: 0.9587 - val_loss: 0.4296 - val_acc: 0.9237 Epoch 196/500 77s 154ms/step - loss: 0.3029 - acc: 0.9617 - val_loss: 0.4240 - val_acc: 0.9248 Epoch 197/500 77s 154ms/step - loss: 0.3020 - acc: 0.9620 - val_loss: 0.4250 - val_acc: 0.9236 Epoch 198/500 77s 154ms/step - loss: 0.2999 - acc: 0.9615 - val_loss: 0.4228 - val_acc: 0.9248 Epoch 199/500 77s 154ms/step - loss: 0.3062 - acc: 0.9591 - val_loss: 0.4214 - val_acc: 0.9238 Epoch 200/500 77s 154ms/step - loss: 0.2965 - acc: 0.9610 - val_loss: 0.4208 - val_acc: 0.9223 Epoch 201/500 77s 154ms/step - loss: 0.2991 - acc: 0.9598 - val_loss: 0.4235 - val_acc: 0.9234 Epoch 202/500 77s 154ms/step - loss: 0.2970 - acc: 0.9607 - val_loss: 0.4145 - val_acc: 0.9254 Epoch 203/500 77s 154ms/step - loss: 0.2957 - acc: 0.9615 - val_loss: 0.4259 - val_acc: 0.9258 Epoch 204/500 77s 154ms/step - loss: 0.2985 - acc: 0.9593 - val_loss: 0.4215 - val_acc: 0.9255 Epoch 205/500 77s 154ms/step - loss: 0.2997 - acc: 0.9586 - val_loss: 0.4152 - val_acc: 0.9226 Epoch 206/500 77s 154ms/step - loss: 0.2937 - acc: 0.9603 - val_loss: 0.4019 - val_acc: 0.9318 Epoch 207/500 77s 154ms/step - loss: 0.2948 - acc: 0.9596 - val_loss: 0.4118 - val_acc: 0.9257 Epoch 208/500 77s 154ms/step - loss: 0.2952 - acc: 0.9597 - val_loss: 0.4051 - val_acc: 0.9306 Epoch 209/500 77s 154ms/step - loss: 0.2870 - acc: 0.9616 - val_loss: 0.4115 - val_acc: 0.9262 Epoch 210/500 77s 154ms/step - loss: 0.2926 - acc: 0.9596 - val_loss: 0.4055 - val_acc: 0.9272 Epoch 211/500 77s 154ms/step - loss: 0.2872 - acc: 0.9613 - val_loss: 0.4165 - val_acc: 0.9229 Epoch 212/500 77s 154ms/step - loss: 0.2909 - acc: 0.9597 - val_loss: 0.4018 - val_acc: 0.9249 Epoch 213/500 77s 154ms/step - loss: 0.2857 - acc: 0.9614 - val_loss: 0.4119 - val_acc: 0.9219 Epoch 214/500 77s 154ms/step - loss: 0.2858 - acc: 0.9603 - val_loss: 0.4023 - val_acc: 0.9258 Epoch 215/500 77s 154ms/step - loss: 0.2858 - acc: 0.9609 - val_loss: 0.4176 - val_acc: 0.9231 Epoch 216/500 77s 154ms/step - loss: 0.2861 - acc: 0.9601 - val_loss: 0.4137 - val_acc: 0.9246 Epoch 217/500 77s 154ms/step - loss: 0.2869 - acc: 0.9604 - val_loss: 0.4088 - val_acc: 0.9245 Epoch 218/500 77s 154ms/step - loss: 0.2828 - acc: 0.9609 - val_loss: 0.4092 - val_acc: 0.9234 Epoch 219/500 77s 154ms/step - loss: 0.2807 - acc: 0.9616 - val_loss: 0.4026 - val_acc: 0.9278 Epoch 220/500 77s 154ms/step - loss: 0.2810 - acc: 0.9608 - val_loss: 0.4045 - val_acc: 0.9275 Epoch 221/500 77s 154ms/step - loss: 0.2804 - acc: 0.9612 - val_loss: 0.4012 - val_acc: 0.9247 Epoch 222/500 77s 154ms/step - loss: 0.2819 - acc: 0.9588 - val_loss: 0.4046 - val_acc: 0.9219 Epoch 223/500 77s 154ms/step - loss: 0.2805 - acc: 0.9599 - val_loss: 0.4007 - val_acc: 0.9247 Epoch 224/500 77s 154ms/step - loss: 0.2785 - acc: 0.9608 - val_loss: 0.4117 - val_acc: 0.9224 Epoch 225/500 77s 154ms/step - loss: 0.2783 - acc: 0.9610 - val_loss: 0.4073 - val_acc: 0.9204 Epoch 226/500 77s 154ms/step - loss: 0.2830 - acc: 0.9599 - val_loss: 0.4135 - val_acc: 0.9203 Epoch 227/500 77s 154ms/step - loss: 0.2798 - acc: 0.9601 - val_loss: 0.3977 - val_acc: 0.9254 Epoch 228/500 77s 154ms/step - loss: 0.2780 - acc: 0.9602 - val_loss: 0.3916 - val_acc: 0.9254 Epoch 229/500 77s 154ms/step - loss: 0.2812 - acc: 0.9589 - val_loss: 0.4020 - val_acc: 0.9254 Epoch 230/500 77s 154ms/step - loss: 0.2786 - acc: 0.9592 - val_loss: 0.3981 - val_acc: 0.9258 Epoch 231/500 77s 154ms/step - loss: 0.2787 - acc: 0.9603 - val_loss: 0.4021 - val_acc: 0.9221 Epoch 232/500 77s 154ms/step - loss: 0.2775 - acc: 0.9607 - val_loss: 0.3934 - val_acc: 0.9268 Epoch 233/500 77s 154ms/step - loss: 0.2787 - acc: 0.9592 - val_loss: 0.3829 - val_acc: 0.9275 Epoch 234/500 77s 154ms/step - loss: 0.2748 - acc: 0.9609 - val_loss: 0.3967 - val_acc: 0.9274 Epoch 235/500 77s 154ms/step - loss: 0.2781 - acc: 0.9589 - val_loss: 0.3909 - val_acc: 0.9275 Epoch 236/500 77s 154ms/step - loss: 0.2758 - acc: 0.9607 - val_loss: 0.3941 - val_acc: 0.9270 Epoch 237/500 77s 154ms/step - loss: 0.2767 - acc: 0.9600 - val_loss: 0.4121 - val_acc: 0.9195 Epoch 238/500 77s 154ms/step - loss: 0.2754 - acc: 0.9608 - val_loss: 0.3978 - val_acc: 0.9221 Epoch 239/500 77s 154ms/step - loss: 0.2722 - acc: 0.9616 - val_loss: 0.4039 - val_acc: 0.9238 Epoch 240/500 77s 154ms/step - loss: 0.2685 - acc: 0.9618 - val_loss: 0.3889 - val_acc: 0.9277 Epoch 241/500 77s 154ms/step - loss: 0.2751 - acc: 0.9596 - val_loss: 0.3960 - val_acc: 0.9274 Epoch 242/500 77s 154ms/step - loss: 0.2686 - acc: 0.9619 - val_loss: 0.3881 - val_acc: 0.9288 Epoch 243/500 77s 154ms/step - loss: 0.2744 - acc: 0.9600 - val_loss: 0.3929 - val_acc: 0.9235 Epoch 244/500 77s 154ms/step - loss: 0.2741 - acc: 0.9596 - val_loss: 0.3775 - val_acc: 0.9274 Epoch 245/500 77s 154ms/step - loss: 0.2694 - acc: 0.9619 - val_loss: 0.4006 - val_acc: 0.9213 Epoch 246/500 77s 154ms/step - loss: 0.2760 - acc: 0.9586 - val_loss: 0.3956 - val_acc: 0.9236 Epoch 247/500 77s 154ms/step - loss: 0.2694 - acc: 0.9612 - val_loss: 0.3956 - val_acc: 0.9232 Epoch 248/500 77s 154ms/step - loss: 0.2714 - acc: 0.9603 - val_loss: 0.3947 - val_acc: 0.9253 Epoch 249/500 77s 154ms/step - loss: 0.2718 - acc: 0.9608 - val_loss: 0.4027 - val_acc: 0.9232 Epoch 250/500 77s 154ms/step - loss: 0.2665 - acc: 0.9624 - val_loss: 0.3955 - val_acc: 0.9243 Epoch 251/500 77s 154ms/step - loss: 0.2666 - acc: 0.9632 - val_loss: 0.4009 - val_acc: 0.9219 Epoch 252/500 77s 154ms/step - loss: 0.2733 - acc: 0.9592 - val_loss: 0.4097 - val_acc: 0.9204 Epoch 253/500 77s 154ms/step - loss: 0.2702 - acc: 0.9602 - val_loss: 0.3962 - val_acc: 0.9213 Epoch 254/500 77s 154ms/step - loss: 0.2718 - acc: 0.9603 - val_loss: 0.3998 - val_acc: 0.9235 Epoch 255/500 77s 155ms/step - loss: 0.2679 - acc: 0.9613 - val_loss: 0.4113 - val_acc: 0.9217 Epoch 256/500 77s 155ms/step - loss: 0.2702 - acc: 0.9605 - val_loss: 0.3947 - val_acc: 0.9203 Epoch 257/500 77s 155ms/step - loss: 0.2728 - acc: 0.9593 - val_loss: 0.4031 - val_acc: 0.9234 Epoch 258/500 77s 154ms/step - loss: 0.2719 - acc: 0.9593 - val_loss: 0.3979 - val_acc: 0.9250 Epoch 259/500 77s 154ms/step - loss: 0.2683 - acc: 0.9620 - val_loss: 0.3881 - val_acc: 0.9264 Epoch 260/500 77s 154ms/step - loss: 0.2730 - acc: 0.9599 - val_loss: 0.3837 - val_acc: 0.9264 Epoch 261/500 77s 154ms/step - loss: 0.2681 - acc: 0.9614 - val_loss: 0.3945 - val_acc: 0.9251 Epoch 262/500 77s 154ms/step - loss: 0.2722 - acc: 0.9595 - val_loss: 0.3893 - val_acc: 0.9248 Epoch 263/500 77s 154ms/step - loss: 0.2695 - acc: 0.9613 - val_loss: 0.3948 - val_acc: 0.9241 Epoch 264/500 77s 154ms/step - loss: 0.2691 - acc: 0.9616 - val_loss: 0.3995 - val_acc: 0.9251 Epoch 265/500 77s 154ms/step - loss: 0.2722 - acc: 0.9601 - val_loss: 0.3898 - val_acc: 0.9248 Epoch 266/500 77s 154ms/step - loss: 0.2673 - acc: 0.9601 - val_loss: 0.3847 - val_acc: 0.9269 Epoch 267/500 77s 154ms/step - loss: 0.2641 - acc: 0.9629 - val_loss: 0.3892 - val_acc: 0.9258 Epoch 268/500 77s 154ms/step - loss: 0.2642 - acc: 0.9622 - val_loss: 0.3875 - val_acc: 0.9266 Epoch 269/500 77s 154ms/step - loss: 0.2709 - acc: 0.9604 - val_loss: 0.3991 - val_acc: 0.9236 Epoch 270/500 77s 154ms/step - loss: 0.2675 - acc: 0.9607 - val_loss: 0.3841 - val_acc: 0.9275 Epoch 271/500 77s 154ms/step - loss: 0.2672 - acc: 0.9618 - val_loss: 0.3863 - val_acc: 0.9254 Epoch 272/500 77s 154ms/step - loss: 0.2651 - acc: 0.9629 - val_loss: 0.3993 - val_acc: 0.9249 Epoch 273/500 77s 154ms/step - loss: 0.2675 - acc: 0.9618 - val_loss: 0.3959 - val_acc: 0.9230 Epoch 274/500 77s 154ms/step - loss: 0.2650 - acc: 0.9625 - val_loss: 0.3901 - val_acc: 0.9248 Epoch 275/500 77s 154ms/step - loss: 0.2685 - acc: 0.9611 - val_loss: 0.3998 - val_acc: 0.9206 Epoch 276/500 77s 154ms/step - loss: 0.2645 - acc: 0.9630 - val_loss: 0.3983 - val_acc: 0.9244 Epoch 277/500 77s 154ms/step - loss: 0.2675 - acc: 0.9614 - val_loss: 0.4014 - val_acc: 0.9227 Epoch 278/500 77s 154ms/step - loss: 0.2648 - acc: 0.9628 - val_loss: 0.3990 - val_acc: 0.9239 Epoch 279/500 77s 154ms/step - loss: 0.2648 - acc: 0.9624 - val_loss: 0.4027 - val_acc: 0.9215 Epoch 280/500 77s 154ms/step - loss: 0.2630 - acc: 0.9634 - val_loss: 0.4132 - val_acc: 0.9198 Epoch 281/500 77s 154ms/step - loss: 0.2673 - acc: 0.9620 - val_loss: 0.4117 - val_acc: 0.9200 Epoch 282/500 77s 154ms/step - loss: 0.2654 - acc: 0.9617 - val_loss: 0.4133 - val_acc: 0.9187 Epoch 283/500 77s 154ms/step - loss: 0.2661 - acc: 0.9621 - val_loss: 0.3970 - val_acc: 0.9250 Epoch 284/500 77s 154ms/step - loss: 0.2653 - acc: 0.9613 - val_loss: 0.3930 - val_acc: 0.9256 Epoch 285/500 77s 154ms/step - loss: 0.2615 - acc: 0.9632 - val_loss: 0.4035 - val_acc: 0.9252 Epoch 286/500 77s 154ms/step - loss: 0.2701 - acc: 0.9606 - val_loss: 0.3921 - val_acc: 0.9264 Epoch 287/500 77s 154ms/step - loss: 0.2663 - acc: 0.9619 - val_loss: 0.3858 - val_acc: 0.9287 Epoch 288/500 77s 154ms/step - loss: 0.2623 - acc: 0.9632 - val_loss: 0.3950 - val_acc: 0.9235 Epoch 289/500 77s 154ms/step - loss: 0.2636 - acc: 0.9625 - val_loss: 0.3869 - val_acc: 0.9281 Epoch 290/500 77s 154ms/step - loss: 0.2625 - acc: 0.9636 - val_loss: 0.3885 - val_acc: 0.9272 Epoch 291/500 77s 154ms/step - loss: 0.2623 - acc: 0.9630 - val_loss: 0.3900 - val_acc: 0.9252 Epoch 292/500 77s 154ms/step - loss: 0.2650 - acc: 0.9615 - val_loss: 0.3916 - val_acc: 0.9264 Epoch 293/500 77s 154ms/step - loss: 0.2627 - acc: 0.9624 - val_loss: 0.3935 - val_acc: 0.9259 Epoch 294/500 77s 154ms/step - loss: 0.2664 - acc: 0.9621 - val_loss: 0.3898 - val_acc: 0.9264 Epoch 295/500 77s 154ms/step - loss: 0.2624 - acc: 0.9629 - val_loss: 0.3937 - val_acc: 0.9264 Epoch 296/500 77s 154ms/step - loss: 0.2606 - acc: 0.9633 - val_loss: 0.3959 - val_acc: 0.9252 Epoch 297/500 77s 154ms/step - loss: 0.2621 - acc: 0.9626 - val_loss: 0.3978 - val_acc: 0.9245 Epoch 298/500 77s 153ms/step - loss: 0.2616 - acc: 0.9624 - val_loss: 0.3976 - val_acc: 0.9245 Epoch 299/500 77s 154ms/step - loss: 0.2610 - acc: 0.9626 - val_loss: 0.3952 - val_acc: 0.9239 Epoch 300/500 77s 154ms/step - loss: 0.2659 - acc: 0.9620 - val_loss: 0.4040 - val_acc: 0.9214 Epoch 301/500 lr changed to 0.0009999999776482583 77s 154ms/step - loss: 0.2382 - acc: 0.9722 - val_loss: 0.3640 - val_acc: 0.9314 Epoch 302/500 77s 154ms/step - loss: 0.2191 - acc: 0.9797 - val_loss: 0.3560 - val_acc: 0.9333 Epoch 303/500 77s 154ms/step - loss: 0.2131 - acc: 0.9809 - val_loss: 0.3548 - val_acc: 0.9346 Epoch 304/500 77s 154ms/step - loss: 0.2059 - acc: 0.9836 - val_loss: 0.3561 - val_acc: 0.9340 Epoch 305/500 77s 154ms/step - loss: 0.2049 - acc: 0.9843 - val_loss: 0.3526 - val_acc: 0.9366 Epoch 306/500 77s 154ms/step - loss: 0.2019 - acc: 0.9852 - val_loss: 0.3509 - val_acc: 0.9373 Epoch 307/500 77s 154ms/step - loss: 0.2028 - acc: 0.9843 - val_loss: 0.3527 - val_acc: 0.9362 Epoch 308/500 77s 154ms/step - loss: 0.2023 - acc: 0.9846 - val_loss: 0.3534 - val_acc: 0.9363 Epoch 309/500 77s 154ms/step - loss: 0.1995 - acc: 0.9855 - val_loss: 0.3533 - val_acc: 0.9367 Epoch 310/500 77s 154ms/step - loss: 0.1957 - acc: 0.9871 - val_loss: 0.3547 - val_acc: 0.9369 Epoch 311/500 77s 154ms/step - loss: 0.1947 - acc: 0.9877 - val_loss: 0.3532 - val_acc: 0.9380 Epoch 312/500 77s 154ms/step - loss: 0.1928 - acc: 0.9878 - val_loss: 0.3533 - val_acc: 0.9380 Epoch 313/500 77s 154ms/step - loss: 0.1920 - acc: 0.9879 - val_loss: 0.3522 - val_acc: 0.9391 Epoch 314/500 77s 154ms/step - loss: 0.1923 - acc: 0.9871 - val_loss: 0.3523 - val_acc: 0.9385 Epoch 315/500 77s 154ms/step - loss: 0.1901 - acc: 0.9885 - val_loss: 0.3517 - val_acc: 0.9375 Epoch 316/500 77s 154ms/step - loss: 0.1903 - acc: 0.9879 - val_loss: 0.3518 - val_acc: 0.9391 Epoch 317/500 77s 154ms/step - loss: 0.1883 - acc: 0.9885 - val_loss: 0.3539 - val_acc: 0.9384 Epoch 318/500 77s 154ms/step - loss: 0.1884 - acc: 0.9883 - val_loss: 0.3568 - val_acc: 0.9376 Epoch 319/500 77s 154ms/step - loss: 0.1888 - acc: 0.9887 - val_loss: 0.3560 - val_acc: 0.9382 Epoch 320/500 77s 154ms/step - loss: 0.1862 - acc: 0.9893 - val_loss: 0.3573 - val_acc: 0.9371 Epoch 321/500 77s 154ms/step - loss: 0.1874 - acc: 0.9880 - val_loss: 0.3561 - val_acc: 0.9386 Epoch 322/500 77s 154ms/step - loss: 0.1855 - acc: 0.9895 - val_loss: 0.3553 - val_acc: 0.9395 Epoch 323/500 77s 154ms/step - loss: 0.1846 - acc: 0.9897 - val_loss: 0.3543 - val_acc: 0.9396 Epoch 324/500 77s 154ms/step - loss: 0.1860 - acc: 0.9890 - val_loss: 0.3560 - val_acc: 0.9382 Epoch 325/500 77s 154ms/step - loss: 0.1834 - acc: 0.9894 - val_loss: 0.3539 - val_acc: 0.9383 Epoch 326/500 77s 154ms/step - loss: 0.1847 - acc: 0.9894 - val_loss: 0.3555 - val_acc: 0.9375 Epoch 327/500 77s 154ms/step - loss: 0.1830 - acc: 0.9896 - val_loss: 0.3559 - val_acc: 0.9370 Epoch 328/500 77s 154ms/step - loss: 0.1839 - acc: 0.9894 - val_loss: 0.3584 - val_acc: 0.9363 Epoch 329/500 77s 154ms/step - loss: 0.1808 - acc: 0.9902 - val_loss: 0.3571 - val_acc: 0.9381 Epoch 330/500 77s 154ms/step - loss: 0.1818 - acc: 0.9899 - val_loss: 0.3556 - val_acc: 0.9377 Epoch 331/500 77s 154ms/step - loss: 0.1800 - acc: 0.9903 - val_loss: 0.3584 - val_acc: 0.9380 Epoch 332/500 77s 154ms/step - loss: 0.1811 - acc: 0.9898 - val_loss: 0.3571 - val_acc: 0.9399 Epoch 333/500 77s 154ms/step - loss: 0.1801 - acc: 0.9900 - val_loss: 0.3574 - val_acc: 0.9390 Epoch 334/500 77s 154ms/step - loss: 0.1802 - acc: 0.9900 - val_loss: 0.3582 - val_acc: 0.9381 Epoch 335/500 77s 154ms/step - loss: 0.1797 - acc: 0.9902 - val_loss: 0.3629 - val_acc: 0.9369 Epoch 336/500 77s 154ms/step - loss: 0.1783 - acc: 0.9908 - val_loss: 0.3563 - val_acc: 0.9390 Epoch 337/500 77s 154ms/step - loss: 0.1787 - acc: 0.9901 - val_loss: 0.3549 - val_acc: 0.9380 Epoch 338/500 77s 154ms/step - loss: 0.1780 - acc: 0.9907 - val_loss: 0.3594 - val_acc: 0.9368 Epoch 339/500 77s 154ms/step - loss: 0.1776 - acc: 0.9905 - val_loss: 0.3556 - val_acc: 0.9384 Epoch 340/500 77s 154ms/step - loss: 0.1763 - acc: 0.9912 - val_loss: 0.3543 - val_acc: 0.9397 Epoch 341/500 77s 154ms/step - loss: 0.1760 - acc: 0.9911 - val_loss: 0.3552 - val_acc: 0.9380 Epoch 342/500 77s 154ms/step - loss: 0.1754 - acc: 0.9911 - val_loss: 0.3567 - val_acc: 0.9387 Epoch 343/500 77s 154ms/step - loss: 0.1762 - acc: 0.9908 - val_loss: 0.3547 - val_acc: 0.9386 Epoch 344/500 77s 154ms/step - loss: 0.1746 - acc: 0.9913 - val_loss: 0.3569 - val_acc: 0.9377 Epoch 345/500 77s 154ms/step - loss: 0.1736 - acc: 0.9920 - val_loss: 0.3596 - val_acc: 0.9381 Epoch 346/500 77s 154ms/step - loss: 0.1730 - acc: 0.9915 - val_loss: 0.3580 - val_acc: 0.9382 Epoch 347/500 77s 154ms/step - loss: 0.1727 - acc: 0.9910 - val_loss: 0.3569 - val_acc: 0.9386 Epoch 348/500 77s 154ms/step - loss: 0.1750 - acc: 0.9907 - val_loss: 0.3595 - val_acc: 0.9379 Epoch 349/500 77s 154ms/step - loss: 0.1736 - acc: 0.9911 - val_loss: 0.3579 - val_acc: 0.9382 Epoch 350/500 77s 154ms/step - loss: 0.1740 - acc: 0.9910 - val_loss: 0.3560 - val_acc: 0.9394 Epoch 351/500 77s 154ms/step - loss: 0.1710 - acc: 0.9919 - val_loss: 0.3584 - val_acc: 0.9381 Epoch 352/500 77s 154ms/step - loss: 0.1724 - acc: 0.9914 - val_loss: 0.3606 - val_acc: 0.9377 Epoch 353/500 77s 154ms/step - loss: 0.1704 - acc: 0.9922 - val_loss: 0.3589 - val_acc: 0.9369 Epoch 354/500 77s 154ms/step - loss: 0.1696 - acc: 0.9928 - val_loss: 0.3549 - val_acc: 0.9397 Epoch 355/500 77s 154ms/step - loss: 0.1710 - acc: 0.9914 - val_loss: 0.3568 - val_acc: 0.9397 Epoch 356/500 77s 154ms/step - loss: 0.1690 - acc: 0.9919 - val_loss: 0.3574 - val_acc: 0.9390 Epoch 357/500 77s 154ms/step - loss: 0.1692 - acc: 0.9919 - val_loss: 0.3604 - val_acc: 0.9363 Epoch 358/500 77s 154ms/step - loss: 0.1689 - acc: 0.9920 - val_loss: 0.3587 - val_acc: 0.9385 Epoch 359/500 77s 154ms/step - loss: 0.1680 - acc: 0.9922 - val_loss: 0.3629 - val_acc: 0.9363 Epoch 360/500 77s 154ms/step - loss: 0.1690 - acc: 0.9923 - val_loss: 0.3575 - val_acc: 0.9385 Epoch 361/500 77s 154ms/step - loss: 0.1683 - acc: 0.9920 - val_loss: 0.3560 - val_acc: 0.9389 Epoch 362/500 77s 154ms/step - loss: 0.1699 - acc: 0.9913 - val_loss: 0.3572 - val_acc: 0.9366 Epoch 363/500 77s 154ms/step - loss: 0.1657 - acc: 0.9925 - val_loss: 0.3546 - val_acc: 0.9385 Epoch 364/500 77s 154ms/step - loss: 0.1675 - acc: 0.9920 - val_loss: 0.3581 - val_acc: 0.9381 Epoch 365/500 77s 154ms/step - loss: 0.1661 - acc: 0.9926 - val_loss: 0.3595 - val_acc: 0.9390 Epoch 366/500 77s 154ms/step - loss: 0.1664 - acc: 0.9927 - val_loss: 0.3576 - val_acc: 0.9391 Epoch 367/500 77s 154ms/step - loss: 0.1659 - acc: 0.9920 - val_loss: 0.3575 - val_acc: 0.9395 Epoch 368/500 77s 154ms/step - loss: 0.1662 - acc: 0.9920 - val_loss: 0.3577 - val_acc: 0.9383 Epoch 369/500 77s 154ms/step - loss: 0.1658 - acc: 0.9923 - val_loss: 0.3596 - val_acc: 0.9383 Epoch 370/500 77s 154ms/step - loss: 0.1634 - acc: 0.9933 - val_loss: 0.3575 - val_acc: 0.9386 Epoch 371/500 77s 154ms/step - loss: 0.1657 - acc: 0.9919 - val_loss: 0.3587 - val_acc: 0.9372 Epoch 372/500 77s 154ms/step - loss: 0.1651 - acc: 0.9922 - val_loss: 0.3546 - val_acc: 0.9371 Epoch 373/500 77s 154ms/step - loss: 0.1644 - acc: 0.9923 - val_loss: 0.3551 - val_acc: 0.9401 Epoch 374/500 77s 154ms/step - loss: 0.1643 - acc: 0.9922 - val_loss: 0.3585 - val_acc: 0.9374 Epoch 375/500 77s 154ms/step - loss: 0.1634 - acc: 0.9926 - val_loss: 0.3567 - val_acc: 0.9373 Epoch 376/500 77s 154ms/step - loss: 0.1637 - acc: 0.9925 - val_loss: 0.3590 - val_acc: 0.9364 Epoch 377/500 77s 154ms/step - loss: 0.1636 - acc: 0.9922 - val_loss: 0.3615 - val_acc: 0.9365 Epoch 378/500 77s 154ms/step - loss: 0.1607 - acc: 0.9934 - val_loss: 0.3587 - val_acc: 0.9380 Epoch 379/500 77s 154ms/step - loss: 0.1614 - acc: 0.9932 - val_loss: 0.3595 - val_acc: 0.9379 Epoch 380/500 77s 154ms/step - loss: 0.1634 - acc: 0.9919 - val_loss: 0.3587 - val_acc: 0.9384 Epoch 381/500 77s 154ms/step - loss: 0.1604 - acc: 0.9932 - val_loss: 0.3607 - val_acc: 0.9367 Epoch 382/500 77s 154ms/step - loss: 0.1603 - acc: 0.9931 - val_loss: 0.3577 - val_acc: 0.9359 Epoch 383/500 77s 154ms/step - loss: 0.1620 - acc: 0.9922 - val_loss: 0.3560 - val_acc: 0.9391 Epoch 384/500 77s 154ms/step - loss: 0.1622 - acc: 0.9923 - val_loss: 0.3579 - val_acc: 0.9363 Epoch 385/500 76s 153ms/step - loss: 0.1603 - acc: 0.9927 - val_loss: 0.3572 - val_acc: 0.9379 Epoch 386/500 76s 153ms/step - loss: 0.1602 - acc: 0.9928 - val_loss: 0.3571 - val_acc: 0.9377 Epoch 387/500 76s 153ms/step - loss: 0.1592 - acc: 0.9929 - val_loss: 0.3576 - val_acc: 0.9366 Epoch 388/500 76s 153ms/step - loss: 0.1603 - acc: 0.9925 - val_loss: 0.3547 - val_acc: 0.9383 Epoch 389/500 76s 153ms/step - loss: 0.1589 - acc: 0.9934 - val_loss: 0.3555 - val_acc: 0.9383 Epoch 390/500 77s 153ms/step - loss: 0.1599 - acc: 0.9930 - val_loss: 0.3567 - val_acc: 0.9386 Epoch 391/500 77s 153ms/step - loss: 0.1581 - acc: 0.9930 - val_loss: 0.3517 - val_acc: 0.9387 Epoch 392/500 77s 153ms/step - loss: 0.1583 - acc: 0.9933 - val_loss: 0.3577 - val_acc: 0.9391 Epoch 393/500 77s 154ms/step - loss: 0.1588 - acc: 0.9933 - val_loss: 0.3571 - val_acc: 0.9400 Epoch 394/500 77s 153ms/step - loss: 0.1575 - acc: 0.9936 - val_loss: 0.3574 - val_acc: 0.9382 Epoch 395/500 77s 153ms/step - loss: 0.1566 - acc: 0.9937 - val_loss: 0.3566 - val_acc: 0.9375 Epoch 396/500 77s 153ms/step - loss: 0.1567 - acc: 0.9937 - val_loss: 0.3607 - val_acc: 0.9374 Epoch 397/500 77s 153ms/step - loss: 0.1569 - acc: 0.9932 - val_loss: 0.3584 - val_acc: 0.9378 Epoch 398/500 76s 153ms/step - loss: 0.1569 - acc: 0.9930 - val_loss: 0.3587 - val_acc: 0.9380 Epoch 399/500 76s 153ms/step - loss: 0.1562 - acc: 0.9934 - val_loss: 0.3573 - val_acc: 0.9392 Epoch 400/500 76s 153ms/step - loss: 0.1562 - acc: 0.9932 - val_loss: 0.3558 - val_acc: 0.9381 Epoch 401/500 76s 153ms/step - loss: 0.1558 - acc: 0.9933 - val_loss: 0.3549 - val_acc: 0.9367 Epoch 402/500 77s 153ms/step - loss: 0.1555 - acc: 0.9933 - val_loss: 0.3580 - val_acc: 0.9343 Epoch 403/500 76s 153ms/step - loss: 0.1547 - acc: 0.9936 - val_loss: 0.3553 - val_acc: 0.9378 Epoch 404/500 77s 153ms/step - loss: 0.1557 - acc: 0.9932 - val_loss: 0.3526 - val_acc: 0.9384 Epoch 405/500 76s 153ms/step - loss: 0.1537 - acc: 0.9939 - val_loss: 0.3525 - val_acc: 0.9390 Epoch 406/500 76s 153ms/step - loss: 0.1538 - acc: 0.9941 - val_loss: 0.3605 - val_acc: 0.9359 Epoch 407/500 76s 153ms/step - loss: 0.1530 - acc: 0.9942 - val_loss: 0.3579 - val_acc: 0.9371 Epoch 408/500 77s 153ms/step - loss: 0.1536 - acc: 0.9937 - val_loss: 0.3553 - val_acc: 0.9374 Epoch 409/500 77s 154ms/step - loss: 0.1532 - acc: 0.9938 - val_loss: 0.3601 - val_acc: 0.9373 Epoch 410/500 77s 154ms/step - loss: 0.1539 - acc: 0.9933 - val_loss: 0.3582 - val_acc: 0.9374 Epoch 411/500 77s 154ms/step - loss: 0.1548 - acc: 0.9930 - val_loss: 0.3574 - val_acc: 0.9394 Epoch 412/500 77s 153ms/step - loss: 0.1514 - acc: 0.9942 - val_loss: 0.3578 - val_acc: 0.9357 Epoch 413/500 77s 153ms/step - loss: 0.1542 - acc: 0.9931 - val_loss: 0.3551 - val_acc: 0.9371 Epoch 414/500 77s 153ms/step - loss: 0.1527 - acc: 0.9935 - val_loss: 0.3562 - val_acc: 0.9379 Epoch 415/500 77s 153ms/step - loss: 0.1529 - acc: 0.9930 - val_loss: 0.3584 - val_acc: 0.9356 Epoch 416/500 76s 153ms/step - loss: 0.1520 - acc: 0.9936 - val_loss: 0.3609 - val_acc: 0.9349 Epoch 417/500 77s 153ms/step - loss: 0.1503 - acc: 0.9941 - val_loss: 0.3589 - val_acc: 0.9369 Epoch 418/500 77s 153ms/step - loss: 0.1512 - acc: 0.9937 - val_loss: 0.3585 - val_acc: 0.9363 Epoch 419/500 76s 153ms/step - loss: 0.1518 - acc: 0.9931 - val_loss: 0.3581 - val_acc: 0.9379 Epoch 420/500 76s 153ms/step - loss: 0.1514 - acc: 0.9935 - val_loss: 0.3608 - val_acc: 0.9369 Epoch 421/500 76s 153ms/step - loss: 0.1502 - acc: 0.9941 - val_loss: 0.3618 - val_acc: 0.9366 Epoch 422/500 77s 153ms/step - loss: 0.1503 - acc: 0.9935 - val_loss: 0.3566 - val_acc: 0.9362 Epoch 423/500 77s 153ms/step - loss: 0.1510 - acc: 0.9933 - val_loss: 0.3574 - val_acc: 0.9362 Epoch 424/500 77s 153ms/step - loss: 0.1506 - acc: 0.9932 - val_loss: 0.3583 - val_acc: 0.9382 Epoch 425/500 76s 153ms/step - loss: 0.1504 - acc: 0.9935 - val_loss: 0.3590 - val_acc: 0.9373 Epoch 426/500 76s 153ms/step - loss: 0.1500 - acc: 0.9937 - val_loss: 0.3567 - val_acc: 0.9360 Epoch 427/500 76s 153ms/step - loss: 0.1487 - acc: 0.9938 - val_loss: 0.3536 - val_acc: 0.9388 Epoch 428/500 76s 153ms/step - loss: 0.1476 - acc: 0.9943 - val_loss: 0.3533 - val_acc: 0.9391 Epoch 429/500 77s 153ms/step - loss: 0.1490 - acc: 0.9936 - val_loss: 0.3537 - val_acc: 0.9401 Epoch 430/500 76s 153ms/step - loss: 0.1488 - acc: 0.9937 - val_loss: 0.3524 - val_acc: 0.9391 Epoch 431/500 77s 153ms/step - loss: 0.1482 - acc: 0.9937 - val_loss: 0.3483 - val_acc: 0.9399 Epoch 432/500 76s 153ms/step - loss: 0.1487 - acc: 0.9935 - val_loss: 0.3526 - val_acc: 0.9377 Epoch 433/500 77s 153ms/step - loss: 0.1481 - acc: 0.9940 - val_loss: 0.3494 - val_acc: 0.9394 Epoch 434/500 76s 153ms/step - loss: 0.1483 - acc: 0.9936 - val_loss: 0.3542 - val_acc: 0.9378 Epoch 435/500 76s 153ms/step - loss: 0.1470 - acc: 0.9936 - val_loss: 0.3503 - val_acc: 0.9394 Epoch 436/500 76s 153ms/step - loss: 0.1456 - acc: 0.9942 - val_loss: 0.3514 - val_acc: 0.9387 Epoch 437/500 76s 153ms/step - loss: 0.1472 - acc: 0.9935 - val_loss: 0.3498 - val_acc: 0.9392 Epoch 438/500 77s 153ms/step - loss: 0.1470 - acc: 0.9936 - val_loss: 0.3485 - val_acc: 0.9386 Epoch 439/500 77s 153ms/step - loss: 0.1469 - acc: 0.9935 - val_loss: 0.3474 - val_acc: 0.9378 Epoch 440/500 77s 153ms/step - loss: 0.1467 - acc: 0.9932 - val_loss: 0.3487 - val_acc: 0.9381 Epoch 441/500 76s 153ms/step - loss: 0.1455 - acc: 0.9939 - val_loss: 0.3450 - val_acc: 0.9383 Epoch 442/500 77s 153ms/step - loss: 0.1453 - acc: 0.9941 - val_loss: 0.3518 - val_acc: 0.9370 Epoch 443/500 76s 153ms/step - loss: 0.1450 - acc: 0.9939 - val_loss: 0.3510 - val_acc: 0.9360 Epoch 444/500 76s 153ms/step - loss: 0.1458 - acc: 0.9942 - val_loss: 0.3553 - val_acc: 0.9366 Epoch 445/500 76s 153ms/step - loss: 0.1447 - acc: 0.9942 - val_loss: 0.3484 - val_acc: 0.9375 Epoch 446/500 77s 153ms/step - loss: 0.1431 - acc: 0.9945 - val_loss: 0.3522 - val_acc: 0.9386 Epoch 447/500 76s 153ms/step - loss: 0.1448 - acc: 0.9939 - val_loss: 0.3548 - val_acc: 0.9359 Epoch 448/500 76s 153ms/step - loss: 0.1434 - acc: 0.9939 - val_loss: 0.3514 - val_acc: 0.9379 Epoch 449/500 76s 153ms/step - loss: 0.1439 - acc: 0.9939 - val_loss: 0.3488 - val_acc: 0.9389 Epoch 450/500 76s 153ms/step - loss: 0.1445 - acc: 0.9937 - val_loss: 0.3523 - val_acc: 0.9380 Epoch 451/500 lr changed to 9.999999310821295e-05 76s 153ms/step - loss: 0.1442 - acc: 0.9938 - val_loss: 0.3510 - val_acc: 0.9385 Epoch 452/500 77s 154ms/step - loss: 0.1436 - acc: 0.9941 - val_loss: 0.3507 - val_acc: 0.9394 Epoch 453/500 76s 153ms/step - loss: 0.1423 - acc: 0.9948 - val_loss: 0.3503 - val_acc: 0.9387 Epoch 454/500 77s 153ms/step - loss: 0.1430 - acc: 0.9942 - val_loss: 0.3499 - val_acc: 0.9391 Epoch 455/500 77s 153ms/step - loss: 0.1430 - acc: 0.9941 - val_loss: 0.3489 - val_acc: 0.9396 Epoch 456/500 77s 153ms/step - loss: 0.1418 - acc: 0.9947 - val_loss: 0.3487 - val_acc: 0.9393 Epoch 457/500 77s 153ms/step - loss: 0.1417 - acc: 0.9949 - val_loss: 0.3478 - val_acc: 0.9395 Epoch 458/500 76s 153ms/step - loss: 0.1423 - acc: 0.9946 - val_loss: 0.3476 - val_acc: 0.9393 Epoch 459/500 76s 153ms/step - loss: 0.1408 - acc: 0.9949 - val_loss: 0.3474 - val_acc: 0.9398 Epoch 460/500 77s 153ms/step - loss: 0.1415 - acc: 0.9947 - val_loss: 0.3482 - val_acc: 0.9397 Epoch 461/500 76s 153ms/step - loss: 0.1406 - acc: 0.9956 - val_loss: 0.3482 - val_acc: 0.9394 Epoch 462/500 77s 153ms/step - loss: 0.1409 - acc: 0.9951 - val_loss: 0.3475 - val_acc: 0.9396 Epoch 463/500 76s 153ms/step - loss: 0.1406 - acc: 0.9950 - val_loss: 0.3471 - val_acc: 0.9395 Epoch 464/500 76s 153ms/step - loss: 0.1406 - acc: 0.9951 - val_loss: 0.3474 - val_acc: 0.9390 Epoch 465/500 76s 153ms/step - loss: 0.1408 - acc: 0.9950 - val_loss: 0.3477 - val_acc: 0.9396 Epoch 466/500 77s 153ms/step - loss: 0.1418 - acc: 0.9948 - val_loss: 0.3478 - val_acc: 0.9385 Epoch 467/500 76s 153ms/step - loss: 0.1412 - acc: 0.9950 - val_loss: 0.3474 - val_acc: 0.9388 Epoch 468/500 77s 153ms/step - loss: 0.1400 - acc: 0.9954 - val_loss: 0.3476 - val_acc: 0.9387 Epoch 469/500 76s 153ms/step - loss: 0.1405 - acc: 0.9957 - val_loss: 0.3474 - val_acc: 0.9384 Epoch 470/500 77s 153ms/step - loss: 0.1399 - acc: 0.9950 - val_loss: 0.3468 - val_acc: 0.9388 Epoch 471/500 77s 153ms/step - loss: 0.1400 - acc: 0.9957 - val_loss: 0.3468 - val_acc: 0.9390 Epoch 472/500 76s 153ms/step - loss: 0.1408 - acc: 0.9949 - val_loss: 0.3473 - val_acc: 0.9390 Epoch 473/500 76s 153ms/step - loss: 0.1410 - acc: 0.9947 - val_loss: 0.3476 - val_acc: 0.9392 Epoch 474/500 76s 153ms/step - loss: 0.1401 - acc: 0.9954 - val_loss: 0.3477 - val_acc: 0.9396 Epoch 475/500 77s 153ms/step - loss: 0.1400 - acc: 0.9952 - val_loss: 0.3478 - val_acc: 0.9397 Epoch 476/500 76s 153ms/step - loss: 0.1389 - acc: 0.9955 - val_loss: 0.3471 - val_acc: 0.9391 Epoch 477/500 76s 153ms/step - loss: 0.1404 - acc: 0.9950 - val_loss: 0.3474 - val_acc: 0.9392 Epoch 478/500 77s 153ms/step - loss: 0.1398 - acc: 0.9953 - val_loss: 0.3475 - val_acc: 0.9390 Epoch 479/500 77s 153ms/step - loss: 0.1400 - acc: 0.9951 - val_loss: 0.3468 - val_acc: 0.9394 Epoch 480/500 77s 153ms/step - loss: 0.1394 - acc: 0.9954 - val_loss: 0.3471 - val_acc: 0.9392 Epoch 481/500 76s 153ms/step - loss: 0.1404 - acc: 0.9951 - val_loss: 0.3467 - val_acc: 0.9393 Epoch 482/500 76s 153ms/step - loss: 0.1395 - acc: 0.9951 - val_loss: 0.3464 - val_acc: 0.9395 Epoch 483/500 76s 153ms/step - loss: 0.1392 - acc: 0.9954 - val_loss: 0.3466 - val_acc: 0.9396 Epoch 484/500 76s 153ms/step - loss: 0.1394 - acc: 0.9952 - val_loss: 0.3467 - val_acc: 0.9395 Epoch 485/500 76s 153ms/step - loss: 0.1397 - acc: 0.9952 - val_loss: 0.3470 - val_acc: 0.9393 Epoch 486/500 76s 153ms/step - loss: 0.1391 - acc: 0.9953 - val_loss: 0.3474 - val_acc: 0.9393 Epoch 487/500 77s 153ms/step - loss: 0.1395 - acc: 0.9955 - val_loss: 0.3479 - val_acc: 0.9395 Epoch 488/500 77s 153ms/step - loss: 0.1388 - acc: 0.9952 - val_loss: 0.3475 - val_acc: 0.9391 Epoch 489/500 77s 153ms/step - loss: 0.1393 - acc: 0.9954 - val_loss: 0.3477 - val_acc: 0.9390 Epoch 490/500 77s 153ms/step - loss: 0.1399 - acc: 0.9953 - val_loss: 0.3482 - val_acc: 0.9390 Epoch 491/500 76s 153ms/step - loss: 0.1397 - acc: 0.9950 - val_loss: 0.3487 - val_acc: 0.9389 Epoch 492/500 77s 153ms/step - loss: 0.1395 - acc: 0.9952 - val_loss: 0.3487 - val_acc: 0.9388 Epoch 493/500 77s 153ms/step - loss: 0.1391 - acc: 0.9956 - val_loss: 0.3491 - val_acc: 0.9390 Epoch 494/500 76s 153ms/step - loss: 0.1396 - acc: 0.9952 - val_loss: 0.3481 - val_acc: 0.9389 Epoch 495/500 76s 153ms/step - loss: 0.1395 - acc: 0.9952 - val_loss: 0.3479 - val_acc: 0.9387 Epoch 496/500 76s 153ms/step - loss: 0.1389 - acc: 0.9953 - val_loss: 0.3482 - val_acc: 0.9386 Epoch 497/500 76s 153ms/step - loss: 0.1385 - acc: 0.9960 - val_loss: 0.3487 - val_acc: 0.9388 Epoch 498/500 76s 153ms/step - loss: 0.1386 - acc: 0.9957 - val_loss: 0.3483 - val_acc: 0.9388 Epoch 499/500 76s 153ms/step - loss: 0.1391 - acc: 0.9955 - val_loss: 0.3482 - val_acc: 0.9390 Epoch 500/500 76s 153ms/step - loss: 0.1397 - acc: 0.9951 - val_loss: 0.3481 - val_acc: 0.9396 Train loss: 0.1304543605595827 Train accuracy: 0.9980800018310547 Test loss: 0.3480722904205322 Test accuracy: 0.9396000015735626
相較於調參記錄18,訓練準確率和測試準確率都降了一點。同時,訓練準確率比測試準確率大概高了6%,說明依然存在過擬合。
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
————————————————
版權宣告:本文為CSDN博主「dangqing1988」的原創文章,遵循CC 4.0 BY-SA版權協議,轉載請附上原文出處連結及本宣告。
原文連結: https://blog.csdn.net/dangqing1988/article/details/105988050
來自 “ ITPUB部落格 ” ,連結:http://blog.itpub.net/69972329/viewspace-2691047/,如需轉載,請註明出處,否則將追究法律責任。
相關文章
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄18)Cifar10~94.28%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄26)Cifar10~95.92%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄20)Cifar10~94.17%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄21)Cifar10~95.12%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄22)Cifar10~95.25%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄23)Cifar10~95.47%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄24)Cifar10~95.80%函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄10)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄11)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄12)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄13)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄14)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄15)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄16)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄17)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄1)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄2)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄3)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄4)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄5)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄6)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄7)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄8)函式
- 深度殘差網路+自適應引數化ReLU啟用函式(調參記錄9)函式
- 注意力機制下的啟用函式:自適應引數化ReLU函式
- 深度殘差網路(ResNet)
- 深度學習之殘差網路深度學習
- 殘差網路再升級之深度殘差收縮網路(附Keras程式碼)Keras
- 深度殘差收縮網路:(三)網路結構
- 深度學習故障診斷——深度殘差收縮網路深度學習
- 深度殘差收縮網路:(一)背景知識
- 深度殘差收縮網路:(二)整體思路
- 學習筆記16:殘差網路筆記
- 從ReLU到GELU,一文概覽神經網路的啟用函式神經網路函式
- 十分鐘弄懂深度殘差收縮網路
- 深度殘差收縮網路:(五)實驗驗證
- 深度殘差收縮網路:(六)程式碼實現
- 殘差網路(Residual Networks, ResNets)