03_基于CNN的猫狗大战实现

猫狗大战背景介绍

猫狗大战数据集来源于Kaggle上的一个竞赛：Dogs vs. Cats，猫狗大战的数据集下载地址，其中数据集有12500只猫和12500只狗

1. http://www.kaggle.com/c/dogs-vs-cats
   
   使用Finetuning对VGGNet进行调整，从而针对猫狗大战的训练集进行训练，创建工程文件，所有素材如下
   

代码示例

step1 对模型的修改

首先是对模型的修改（VGG16_model.py文件），在这里原先的输出结果是对1000个不同的类别进行判定，而在此是对2个图像，也就是猫和狗的判断，因此首先第一步就是修改输出层的全连接数据

def fc_layers(self):
	self.fc6 = self.fc("fc1", self.pool5, 4096, trainable=False) #语句变动
    self.fc7 = self.fc("fc2", self.fc6, 4096, trainable=False) #语句变动
    self.fc8 = self.fc("fc3", self.fc7, 2)

这里是最后一层的输出通道被设置成2，而对于其他部分，定义创建卷积层和全连接层的方法则无需做出太大改动。

        def conv(self,name, input_data, out_channel):
        in_channel = input_data.get_shape()[-1]
        with tf.variable_scope(name):
            kernel = tf.get_variable("weights", [3, 3, in_channel, out_channel], dtype=tf.float32, trainable=False) #语句变动
            biases = tf.get_variable("biases", [out_channel], dtype=tf.float32, trainable=False) #语句变动
            conv_res = tf.nn.conv2d(input_data, kernel, [1, 1, 1, 1], padding="SAME")
            res = tf.nn.bias_add(conv_res, biases)
            out = tf.nn.relu(res, name=name)
        self.parameters += [kernel, biases]
        return out

    def fc(self, name, input_data, out_channel, trainable=True):
        shape = input_data.get_shape().as_list()
        if len(shape) == 4:
            size = shape[-1] * shape[-2] * shape[-3]
        else:size = shape[1]
        input_data_flat = tf.reshape(input_data,[-1,size])
        with tf.variable_scope(name):
            weights = tf.get_variable(name="weights",shape=[size,out_channel],dtype=tf.float32,trainable=trainable) #语句变动
            biases = tf.get_variable(name="biases",shape=[out_channel],dtype=tf.float32, trainable=trainable) #语句变动
            res = tf.matmul(input_data_flat,weights)
            out = tf.nn.relu(tf.nn.bias_add(res,biases))
        self.parameters += [weights, biases]
        return out

step2 数据的输入

对于修改后的模型，需要对其进行重新训练，而首要条件就是数据输入，在这里笔者使用数据的输入流方式。代码如下

def get_file(file_dir):
    images = []
    temp = []
    for root, sub_folders, files in os.walk(file_dir):
        for name in files:
            images.append(os.path.join(root, name))
        for name in sub_folders:
            temp.append(os.path.join(root, name))
    labels = []
    for one_folder in temp:
        n_img = len(os.listdir(one_folder))
        letter = one_folder.split('/')[-1]
        if letter == 'cat':
            labels = np.append(labels, n_img * [0])
        else:
            labels = np.append(labels, n_img * [1])
    # shuffle
    temp = np.array([images, labels])
    temp = temp.transpose()
    np.random.shuffle(temp)
    image_list = list(temp[:, 0])
    label_list = list(temp[:, 1])
    label_list = [int(float(i)) for i in label_list]

    return image_list, label_list

这里定义的get_file函数对输入文件的文件夹进行分类，通过以不同的文件夹作为分类标准将图片分为2类，使用2个列表文件分别用来存储图片地址和对应的标记地址，同时我们需要按照程序的要求，将train文件夹中的图片，分成cat和dog 文件夹，如图所示：

def get_batch(image_list, label_list, img_width, img_height, batch_size, capacity):

    image = tf.cast(image_list, tf.string)
    label = tf.cast(label_list, tf.int32)

    input_queue = tf.train.slice_input_producer([image,label])

    label = input_queue[1]
    image_contents = tf.read_file(input_queue[0])
    image = tf.image.decode_jpeg(image_contents,channels=3)

    image = tf.image.resize_image_with_crop_or_pad(image,img_width,img_height)
    image = tf.image.per_image_standardization(image) # 将图片标准化
    image_batch,label_batch = tf.train.batch([image,label],batch_size=batch_size,num_threads=64,capacity=capacity)
    label_batch = tf.reshape(label_batch,[batch_size])

    return image_batch,label_batch

get_batch函数是通过对列表地址的读取而循环载入具有参数batch_size大小而定的图片，并读取相应的图片标签作为数据标签一同进行训练，完整定义如下：

import tensorflow as tf
import numpy as np
import os
img_width = 224
img_height = 224


def get_file(file_dir):
    images = []
    temp = []
    for root, sub_folders, files in os.walk(file_dir):
        for name in files:
            images.append(os.path.join(root, name))
        for name in sub_folders:
            temp.append(os.path.join(root, name))
    labels = []
    for one_folder in temp:
        n_img = len(os.listdir(one_folder))
        letter = one_folder.split('/')[-1]
        if letter == 'cat':
            labels = np.append(labels, n_img * [0])
        else:
            labels = np.append(labels, n_img * [1])
    # shuffle
    temp = np.array([images, labels])
    temp = temp.transpose()
    np.random.shuffle(temp)
    image_list = list(temp[:, 0])
    label_list = list(temp[:, 1])
    label_list = [int(float(i)) for i in label_list]

    return image_list, label_list


def get_batch(image_list, label_list, img_width, img_height, batch_size, capacity):

    image = tf.cast(image_list, tf.string)
    label = tf.cast(label_list, tf.int32)

    input_queue = tf.train.slice_input_producer([image,label])

    label = input_queue[1]
    image_contents = tf.read_file(input_queue[0])
    image = tf.image.decode_jpeg(image_contents,channels=3)

    image = tf.image.resize_image_with_crop_or_pad(image,img_width,img_height)
    image = tf.image.per_image_standardization(image) # 将图片标准化
    image_batch,label_batch = tf.train.batch([image,label],batch_size=batch_size,num_threads=64,capacity=capacity)
    label_batch = tf.reshape(label_batch,[batch_size])

    return image_batch,label_batch


def onehot(labels):
    n_sample = len(labels)
    n_class = max(labels) + 1
    onehot_labels = np.zeros((n_sample, n_class))
    onehot_labels[np.arange(n_sample), labels] = 1
    return onehot_labels

step3 模型的重新训练与存储

Finetuning最重要的一个步骤就是模型的重新训练与存储。首先对于模型的值的输出，在类中已经做了定义，因此只需要将定义的模型类初始化后输出赋予一个特定的变量即可

vgg = model.vgg16(x_imgs)
    fc3_cat_and_dog = vgg.probs
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=fc3_cat_and_dog, labels=y_imgs))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)

这里同时定义了损失函数已经最小化方法，完整代码如下：

import numpy as np
import tensorflow as tf
import VGG16_model as model
import create_and_read_TFRecord2 as reader2

if __name__ == '__main__':

    X_train, y_train = reader2.get_file("./train/")
    image_batch, label_batch = reader2.get_batch(X_train, y_train, 224, 224, 25, 256)

    x_imgs = tf.placeholder(tf.float32, [None, 224, 224, 3])
    y_imgs = tf.placeholder(tf.int32, [None, 2])

    vgg = model.vgg16(x_imgs)
    fc3_cat_and_dog = vgg.probs
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=fc3_cat_and_dog, labels=y_imgs))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)

    sess = tf.Session()
    sess.run(tf.global_variables_initializer())
    vgg.load_weights('./vgg16_weights.npz', sess)
    saver = vgg.saver()

    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord, sess=sess)

    import time
    start_time = time.time()

    for i in range(200):

            image, label = sess.run([image_batch, label_batch])
            labels = reader2.onehot(label)

            sess.run(optimizer, feed_dict={x_imgs: image, y_imgs: labels})
            loss_record = sess.run(loss, feed_dict={x_imgs: image, y_imgs: labels})
            print("now the loss is %f " % loss_record)
            end_time = time.time()
            print('time: ', (end_time - start_time))
            start_time = end_time
            print("----------epoch %d is finished---------------" % i)

    saver.save(sess, "./model/")
    print("Optimization Finished!")

在训练函数中使用了Tensorflow的队列方式进行数据输入，而对于权重的重新载入也使用的是前面文章类似的方式，最终数据进行200次迭代，存储模型在model文件夹中。

step4 模型的复用

import tensorflow as tf
from scipy.misc import imread, imresize
import VGG16_model as model

imgs = tf.placeholder(tf.float32, [None, 224, 224, 3])
sess = tf.Session()
vgg = model.vgg16(imgs)
fc3_cat_and_dog = vgg.probs
saver = vgg.saver()
saver.restore(sess, './model/')

import os
for root, sub_folders, files in os.walk('./test/'):
    i = 0
    cat = 0
    dog = 0
    for name in files:
        i += 1
        filepath = os.path.join(root, name)

        try:
            img1 = imread(filepath, mode='RGB')
            img1 = imresize(img1, (224, 224))
        except:
            print("remove", filepath)

        prob = sess.run(fc3_cat_and_dog, feed_dict={vgg.imgs: [img1]})
        import numpy as np
        max_index = np.argmax(prob)
        if max_index == 0:
            cat += 1
        else:
            dog += 1
        if i % 50 == 0:
            acc = (cat * 1.)/(dog + cat)
            print(acc)
            print("-----------img number is %d------------" % i)