keras实战-猫狗数据-VGG16

男娘i 2021-11-17 18:28 329阅读 0赞

# 原理图 #

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pob25nbG9uZ3NoZW4_size_16_color_FFFFFF_t_70]

## 预处理 ##

图片的预处理就是每一个像素减去了均值，算是比较简单的处理

## 卷积核 ##

整体使用的卷积核都比较小（3x3），3x3是可以表示「左右」、「上下」、「中心」这些模式的最小单元了。  
还有比较特殊的1x1的卷积核（Inception-v1也有这个东西），可看做是空间的线性映射。

前面几层是卷积层的堆叠，后面几层是全连接层，最后是softmax层。所有隐层的激活单元都是ReLU，论文中会介绍好几个网络结构，只有其中一个应用了局部响应归一化层（Local Response Normalisation）。

使用多个较小卷积核的卷积层代替一个卷积核较大的卷积层，一方面可以减少参数，另一方面作者认为相当于是进行了更多的非线性映射，可以增加网络的拟合/表达能力

# -*- coding: utf-8 -*-
    """
    Created on 2019/7/30 19:31
    @Author: Johnson
    @Email:593956670@qq.com
    @File: catvsdog-02.py
    """
    import os
    import numpy as np
    from keras.models import Sequential,Model
    from keras import layers
    from keras.preprocessing.image import ImageDataGenerator
    from keras import optimizers
    from keras.applications.vgg16 import VGG16
    from keras.utils.np_utils import to_categorical
    from scipy.misc import imread,imresize
    import matplotlib.pyplot as plt
    
    imgs = []
    labels = []
    img_shape = (150,150)
    #image generator
    files = os.listdir('data/test')
    #read 1000 files for the generator
    for img_file in files[:10000]:
        img = imread("data/test"+img_file).astype("float32")
        img = imresize(img,img_shape)
        imgs.append(img)
    
    
    imgs = np.array(imgs)
    
    train_gen = ImageDataGenerator(
        rescale=1./255.,
        featurewise_center=True,
        featurewise_std_normalization=True,
        rotation_range=20,
        width_shift_range=0.2,
        height_shift_range=0.2,
    horizontal_flip=True
    )
    val_gen = ImageDataGenerator(
         # rescale = 1./255,
         featurewise_center=True,
         featurewise_std_normalization=True)
    
    train_gen.fit(imgs)
    val_gen.fit(imgs)
    
    #4500 training images
    train_iter = train_gen.flow_from_directory("data/train",classes="binary",target_size=img_shape,batch_size=16)
    #501 validation images
    val_iter = val_gen.flow_from_directory("data/val",classes="binary",target_size=img_shape,batch_size=16)
    '''
    # image generator debug
    for x_batch, y_batch in img_iter:
        print(x_batch.shape)
        print(y_batch.shape)
        plt.imshow(x_batch[0])
        plt.show()
    '''
    #######
    #创建模型
    #######
    
    #finetune from the base model VGG16
    base_model = VGG16(include_top=False,weights='imagenet',input_shape=(150,150,3))
    base_model.summary()
    
    out = base_model.layers[-1].output
    out = layers.Flatten()(out)
    out = layers.Dense(1024,activation="relu")(out)
    #因为前面输出的dense feature 太多了，我们这里加入Dropout，layer来防止过拟合
    out = layers.Dropout(0.5)(out)
    out = layers.Dense(512, activation='relu')(out)
    out = layers.Dropout(0.3)(out)
    out = layers.Dense(1, activation='sigmoid')(out)
    tuneModel = Model(inputs=base_model.input, outputs = out)
    for layer in tuneModel.layers[:19]: # freeze the base model only use it as feature extractors
        layer.trainable = False
    tuneModel.compile(loss='binary_crossentropy', optimizer=optimizers.RMSprop(lr=1e-4),
            metrics=['acc'])
    
    history = tuneModel.fit_generator(
            generator=train_iter,
            steps_per_epoch=100,
            epochs=100,
            validation_data=val_iter,
            validation_steps=32
            )
    
    acc = history.history['acc']
    val_acc = history.history['val_acc']
    loss = history.history['loss']
    val_loss = history.history['val_loss']
    epochs = range(1,101)
    plt.plot(epochs, acc, 'bo', label='Training acc')
    plt.plot(epochs, val_acc, 'r', label='Validation acc')
    plt.legend()
    plt.figure()
    plt.plot(epochs, loss, 'bo', label='Training loss')
    plt.plot(epochs, val_loss, 'r', label='Validation loss')
    plt.legend()
    plt.show()

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pob25nbG9uZ3NoZW4_size_16_color_FFFFFF_t_70]: /images/20211116/a8c116a087ec45939327c5f255744b71.png