keras入门(四) ResNet网络实现猫狗大战

墨蓝 2021-12-17 07:23 427阅读 0赞

先来一张resnet网络结构图，本文采用的是resnet50![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTI2MDE2NDc_size_16_color_FFFFFF_t_70][]

核心思想就是引入skip connect，阻止深层网络的退化。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTI2MDE2NDc_size_16_color_FFFFFF_t_70 1][]

import keras
    from keras import Model, layers
    from keras.layers import Conv2D, BatchNormalization, Add, MaxPooling2D, AveragePooling2D, Input, Activation, Flatten, \
        Dense, GlobalAveragePooling2D, Dropout
    from keras.callbacks import EarlyStopping
    from keras.optimizers import SGD
    import os
    import argparse
    import random
    import numpy as np
    from scipy.misc import imread, imresize, imsave
    
    parser = argparse.ArgumentParser()
    parser.add_argument('--train_dir', default='F:/kaggle/train/')
    parser.add_argument('--test_dir', default='F:/kaggle/test/')
    parser.add_argument('--log_dir', default='./')
    parser.add_argument('--batch_size', default=32)
    parser.add_argument('--gpu', type=int, default=0)
    args = parser.parse_args()
    
    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpu)
    type_list = ['cat', 'dog']
    
    
    def identity_block(input, stage, filters):
        conv_name = 'cn' + str(stage) + '_branch'
        bais_name = 'bn' + str(stage)  + '_branch'
    
        input_short_cut = input
        filter1, filter2, filter3 = filters
        input = Conv2D(filter1, (1, 1), strides=(1, 1), padding='same', name=conv_name + '_one')(input)
        input = BatchNormalization(name=bais_name + "_one_BN")(input)
        input = Activation("relu")(input)
        input = Conv2D(filter2, (3, 3), strides=(1, 1), padding='same', name=conv_name + '_two')(input)
        input = BatchNormalization(name=bais_name + "_two_BN")(input)
        input = Activation("relu")(input)
        input = Conv2D(filter3, (1, 1), strides=(1, 1), padding='same', name=conv_name + '_three')(input)
        input = BatchNormalization(name=bais_name + "_three_BN")(input)
        input = Add()([input, input_short_cut])
        input = Activation("relu")(input)
        return input
    
    def convolutional_block(input, stage, strides, filters):
        conv_name = 'cn' + str(stage) + '_branch'
        bais_name = 'bn' + str(stage) + '_branch'
    
        input_short_cut = input
        filter1, filter2, filter3 = filters
        input = Conv2D(filter1, (1, 1), strides=strides, padding='same', name=conv_name + '_one')(input)
        input = BatchNormalization(name=bais_name + "_one_BN")(input)
        input = Activation('relu')(input)
        input = Conv2D(filter2, (3, 3), strides=(1, 1), padding='same', name=conv_name + '_two')(input)
        input = BatchNormalization(name=bais_name + "_two_BN")(input)
        input = Activation('relu')(input)
        input = Conv2D(filter3, (1, 1), strides=(1, 1), padding='same', name=conv_name + '_three')(input)
        input = BatchNormalization(name=bais_name + "_three_BN")(input)
        input_short_cut = Conv2D(filter3, (1, 1), strides=strides, padding='same', name=conv_name + '_four')(input_short_cut)
        input_short_cut = BatchNormalization(name=bais_name + "_four_BN")(input_short_cut)
        input = Add()([input, input_short_cut])
        input = Activation('relu')(input)
        return input
    
    
    
    def ResNet50(input_shape=(224, 224, 3)):
        input = Input(shape=input_shape)
        outinput = Conv2D(64, (7, 7), strides=(2, 2), padding='same', name='conv1')(input)
        outinput = BatchNormalization(name="conv1_BN")(outinput)
        outinput = Activation("relu")(outinput)
        outinput = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1_1')(outinput)
    
        outinput = convolutional_block(outinput, 1, 1, [64, 64, 256])
        outinput = identity_block(outinput, 2, [64, 64, 256])
        outinput = identity_block(outinput, 3, [64, 64, 256])
        outinput = convolutional_block(outinput, 4, 2, [128, 128, 512])
        outinput = identity_block(outinput, 5, [128, 128, 512])
        outinput = identity_block(outinput, 6, [128, 128, 512])
        outinput = identity_block(outinput, 7, [128, 128, 512])
        outinput = convolutional_block(outinput, 8, 2, [256, 256, 1024])
        outinput = identity_block(outinput, 9, [256, 256, 1024])
        outinput = identity_block(outinput, 10, [256, 256, 1024])
        outinput = identity_block(outinput, 11, [256, 256, 1024])
        outinput = identity_block(outinput, 12, [256, 256, 1024])
        outinput = identity_block(outinput, 13, [256, 256, 1024])
        outinput = convolutional_block(outinput, 14, 2, [512, 512, 2048])
        outinput = identity_block(outinput, 15, [512, 512, 2048])
        outinput = identity_block(outinput, 16, [512, 512, 2048])
        outinput = GlobalAveragePooling2D(name='avg_pool')(outinput)
        outinput = (Dropout(0.5))(outinput)
        #outinput = AveragePooling2D(pool_size=(2, 2), padding="same")(outinput)
        #outinput = Flatten()(outinput)
        outinput = Dense(2, activation='softmax')(outinput)
        model = Model(inputs=input, outputs=outinput, name="ResNet50")
        return model
    
    
    def create_generate(train_file_list, batch_size, input_size):
        while (True):
            random.shuffle(train_file_list)
            image_data = np.zeros((batch_size, input_size[0], input_size[1], 3), dtype='float32')
            label_data = np.zeros((batch_size, 1), dtype='int32')
            for index, file_name in enumerate(train_file_list):
                image = imresize(imread(args.train_dir + file_name), input_size)
                label = file_name.split('.')[0]
                image_data[index % batch_size] = np.reshape(image / 255, (input_size[0], input_size[1], 3))
                label_data[index % batch_size] = type_list.index(label)
                if (0 == (index + 1) % batch_size):
                    # label_data = to_categorical(labei_data, 2)
                    label_data = keras.utils.to_categorical(label_data, 2)
                    yield image_data, label_data
                    image_data = np.zeros((batch_size, input_size[0], input_size[1], 3), dtype='float32')
                    label_data = np.zeros((batch_size, 1), dtype='int32')
    
    
    def train(model):
        early_stop = EarlyStopping(monitor='val_loss', patience=5, mode='min')
        tensor_board = keras.callbacks.TensorBoard(log_dir='./logs', histogram_freq=0, batch_size=16, write_graph=True, write_grads=False, write_images=False, embeddings_freq=0, embeddings_layer_names=None, embeddings_metadata=None, embeddings_data=None, update_freq='epoch')
        sgd = SGD(lr=0.001, decay=1e-8, momentum=0.9, nesterov=True)
        model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
        #model.compile(optimizer=sgd, loss='binary_crossentropy', metrics=['accuracy'])
        train_generate, validation_genarate = prepare_data()
        model.fit_generator(generator=train_generate, steps_per_epoch=1250
                            , epochs=30, verbose=1,
                            validation_data=validation_genarate, validation_steps=30, max_queue_size=1,
                            shuffle=True,
                            callbacks=[early_stop, tensor_board])
        model.save_weights(args.log_dir + 'model.h5')
    
    
    def predict(model):
        file_list = os.listdir(args.test_dir)
        cat_real_count = 0
        dog_real_count = 0
        cat_predict_count = 0
        dog_predict_count = 0
        for index, file_name in enumerate(file_list):
            print(index)
            label = file_name.split('.')[0]
            if 'cat' == label:
                cat_real_count = cat_real_count + 1
            else:
                dog_real_count = dog_real_count + 1
            image = imresize(imread(args.test_dir + file_name), (224, 224, 3))
            label = model.predict(np.reshape(image / 255, (1, 224, 224, 3)))
            label = np.argmax(label, 1)
            if 0 == label:
                imsave('./result/cat/' + file_name, imread(args.test_dir + file_name))
                cat_predict_count = cat_predict_count + 1
            else:
                imsave('./result/dog/' + file_name, imread(args.test_dir + file_name))
                dog_predict_count = dog_predict_count + 1
        # print(cat_predict_count / cat_real_count)
    
    
    if __name__ == '__main__':
        try:
            model = ResNet50()
            train(model)
        except Exception  as err:
            print(err)

与VGG相比，在训练过程中能够快速收敛，而且准确率更高，能够达到97%，但是训练过程中遇到了过拟合的问题，验证集上的准确率在70%~80%，怎么调参都无法解决，训练了好几天，没有太多的头绪，等以后有想法了再解决一下

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTI2MDE2NDc_size_16_color_FFFFFF_t_70]: /images/20211217/9c1e1a5e8c314bf3ac7ebb5c86104b41.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3UwMTI2MDE2NDc_size_16_color_FFFFFF_t_70 1]: /images/20211217/e82ec0aaf48a49868c499832e1f1dca9.png