用Tensorflow实现AlexNet识别猫狗数据集（猫狗大战）【附代码】

一、下载猫狗数据集

百度云链接如下
链接：https://pan.baidu.com/s/1KWYrGVVS6He7lO7skyhgQQ
提取码：p2dd

二、AlexNet实现

1、划分训练集和测试集

因为猫狗大战的测试集没有label所以说我们就从训练集中抽取20%作为测试集，代码如下图所示
divide.py

import os, random, shutil
def moveFile(fileDir):
        pathDir = os.listdir(fileDir)    #取图片的原始路径
        filenumber=len(pathDir)
        rate=0.2    #自定义抽取图片的比例，比方说100张抽10张，那就是0.1
        picknumber=int(filenumber*rate) #按照rate比例从文件夹中取一定数量图片
        sample = random.sample(pathDir, picknumber)  #随机选取picknumber数量的样本图片
        print (sample)
        for name in sample:
                shutil.move(fileDir+name, tarDir+name)
        return

if __name__ == '__main__':
	fileDir = "D:\\神经网络\\Alexnet\猫狗数据集\\train\\"    #源图片文件夹路径
	tarDir = 'D:\\神经网络\\Alexnet\\猫狗数据集\\test\\'    #移动到新的文件夹路径
	moveFile(fileDir)

按照代码将训练集抽出20%作为测试集，在我们的目录中要有源文件夹train，里面存放的是训练数据集，还要有一个空文件夹test，用来存放从训练集转移过来的测试集，这里用的是交叉验证法。

2、将训练集和测试集图片放缩为224x224

我刚开始训练的时候没有把训练集和测试集的图片规范化化为224x224，导致我测试的时候精度只有70%-80%，后来我寻找原因，把训练时候的图片截取出来，发现大部分训练集的图片在训练时候被reshape为224x224导致图片只被截取了一部分，比如说有的图片只有一条猫腿，所以这样训练肯定是不行的，将图片预处理之后，精度得到了显著的提高

reshape.py
import cv2
import os
def rebuild(file_dir, save_dir):
    """ 将图片尺寸resize为224*224 """
    print('Start to resize images...')
    for file in os.listdir(file_dir):
        file_path = os.path.join(file_dir, file)
        try:
            image = cv2.imread(file_path)
            image_resized = cv2.resize(image, (224, 224))
            save_path = save_dir + file
            cv2.imwrite(save_path, image_resized)
        except:
            print(file_path)
            os.remove(file_path)
    print('Finished!')

rebuild('./train','./finaltrain/')
##./train代表初始训练集的地址，./finaltrain代表预处理之后图片存放的地址

将训练集预处理之后，同样方法预处理测试集

3、AlexNet实现

input_data.py

import tensorflow as tf
import os 
import numpy as np
def get_files(file_dir):
	cats = []
	label_cats = []
	dogs = []
	label_dogs = []
	for file in os.listdir(file_dir):
		name = file.split(sep='.')
		if 'cat' in name[0]:
			cats.append(file_dir + file)
			label_cats.append(0)
		else:
			if 'dog' in name[0]:
				dogs.append(file_dir + file)
				label_dogs.append(1)
		image_list = np.hstack((cats,dogs))
		label_list = np.hstack((label_cats,label_dogs))
        #print('There are %d cats\nThere are %d dogs' %(len(cats), len(dogs)))
			# 多个种类分别的时候需要把多个种类放在一起，打乱顺序,这里不需要
     
	# 把标签和图片都放倒一个 temp 中 然后打乱顺序，然后取出来
	temp = np.array([image_list,label_list])
	temp = temp.transpose()
	# 打乱顺序
	np.random.shuffle(temp)

	# 取出第一个元素作为 image 第二个元素作为 label
	image_list = list(temp[:,0])
	label_list = list(temp[:,1])
	label_list = [int(i) for i in label_list]  
	return image_list,label_list

# image_W ,image_H 指定图片大小，batch_size 每批读取的个数 ，capacity队列中 最多容纳元素的个数
def get_batch(image,label,image_W,image_H,batch_size,capacity):
	# 转换数据为 ts 能识别的格式
	image = tf.cast(image,tf.string)
	label = tf.cast(label, tf.int32)

	# 将image 和 label 放倒队列里 
	input_queue = tf.train.slice_input_producer([image,label])
	label = input_queue[1]
	# 读取图片的全部信息
	image_contents = tf.read_file(input_queue[0])
	# 把图片解码，channels ＝3 为彩色图片, r，g ，b  黑白图片为 1 ，也可以理解为图片的厚度
	image = tf.image.decode_jpeg(image_contents,channels =3)
	# 将图片以图片中心进行裁剪或者扩充为 指定的image_W，image_H
	image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
	# 对数据进行标准化,标准化，就是减去它的均值，除以他的方差
	image = tf.image.per_image_standardization(image)

	# 生成批次  num_threads 有多少个线程根据电脑配置设置  capacity 队列中 最多容纳图片的个数  tf.train.shuffle_batch 打乱顺序，
	image_batch, label_batch = tf.train.batch([image, label],batch_size = batch_size, num_threads = 64, capacity = capacity)
	
    # 重新定义下 label_batch 的形状
	label_batch = tf.reshape(label_batch , [batch_size])
	# 转化图片
	image_batch = tf.cast(image_batch,tf.float32)
	return  image_batch, label_batch
  
def one_hot(labels):
    '''one-hot 编码'''
    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

'''

这个文件的作用是获取训练用的一个batch。

AlexNet.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import time
#import creat_and_read_TFReacod as reader
import os
import input_data
os.environ['CUDA_VISIBLE_DEVICES'] = '0'  #这步代表的是采用第一块GPU
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.InteractiveSession(config=config)
train_dir = 'D:\\神经网络\\Alexnet\\猫狗数据集\\train\\'#训练集的地址
#这两步是获取batch
x_train,y_train=input_data.get_files(train_dir)  
image_batch,label_batch=input_data.get_batch(x_train,y_train,227,227,50,2048)

#Batch_Normalization正则化，这一步规范化处理相当重要，
#经过我的实验发现，如果不经过规范化处理，都很难达到收敛，这一开始困扰了我很长时间
def batch_norm(inputs,is_train,is_conv_out=True,decay=0.999):
    scale=tf.Variable(tf.ones([inputs.get_shape()[-1]]))
    beta = tf.Variable(tf.zeros([inputs.get_shape()[-1]]))
    pop_mean = tf.Variable(tf.zeros([inputs.get_shape()[-1]]), trainable=False)
    pop_var = tf.Variable(tf.ones([inputs.get_shape()[-1]]), trainable=False)

    if is_train:
        if is_conv_out:
            batch_mean, batch_var = tf.nn.moments(inputs, [0, 1, 2])
        else:
            batch_mean, batch_var = tf.nn.moments(inputs, [0])

        train_mean = tf.assign(pop_mean, pop_mean * decay + batch_mean * (1 - decay))
        train_var = tf.assign(pop_var, pop_var * decay + batch_var * (1 - decay))

        with tf.control_dependencies([train_mean, train_var]):
            return tf.nn.batch_normalization(inputs,
                                             batch_mean, batch_var, beta, scale, 0.001)
    else:
        return tf.nn.batch_normalization(inputs,
                                         pop_mean, pop_var, beta, scale, 0.001)

 # 模型参数
learning_rate = 1e-4   #学习率
training_iters = 3000  #训练次数
batch_size = 50        #batch的大小
display_step = 5       #每隔5步打印结果
n_classes = 2          #最终划分为两类
n_fc1 = 4096           #第一层全连接层输出的参数
n_fc2 = 2048           #第二层全连接层输出的参数

    # 构建模型
x = tf.placeholder(tf.float32, [None, 227, 227, 3])  #占位符
y = tf.placeholder(tf.float32, [None, n_classes])
#按照论文中的参数设置Alexnet每层网络的参数
#每层网络权重
W_conv = {
        'conv1': tf.Variable(tf.truncated_normal([11, 11, 3, 96], stddev=0.0001)),
        'conv2': tf.Variable(tf.truncated_normal([5, 5, 96, 256], stddev=0.01)),
        'conv3': tf.Variable(tf.truncated_normal([3, 3, 256, 384], stddev=0.01)),
        'conv4': tf.Variable(tf.truncated_normal([3, 3, 384, 384], stddev=0.01)),
        'conv5': tf.Variable(tf.truncated_normal([3, 3, 384, 256], stddev=0.01)),
        'fc1': tf.Variable(tf.truncated_normal([6 * 6 * 256, n_fc1], stddev=0.1)),
        'fc2': tf.Variable(tf.truncated_normal([n_fc1, n_fc2], stddev=0.1)),
        'fc3': tf.Variable(tf.truncated_normal([n_fc2, n_classes], stddev=0.1))
    }
#每层网络的偏置
b_conv = {
        'conv1': tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[96])),
        'conv2': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[256])),
        'conv3': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[384])),
        'conv4': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[384])),
        'conv5': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[256])),
        'fc1': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_fc1])),
        'fc2': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_fc2])),
        'fc3': tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[n_classes]))
    }

x_image = tf.reshape(x, [-1, 227, 227, 3])   #将xreshape为张量

    # 卷积层 1
conv1 = tf.nn.conv2d(x_image, W_conv['conv1'], strides=[1, 4, 4, 1], padding='VALID')
conv1 = tf.nn.bias_add(conv1, b_conv['conv1'])
conv1 = batch_norm(conv1, True)
conv1 = tf.nn.relu(conv1)
    # 池化层 1
pool1 = tf.nn.avg_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
norm1 = tf.nn.lrn(pool1, 5, bias=1.0, alpha=0.001 / 9.0, beta=0.75)

    # 卷积层 2
conv2 = tf.nn.conv2d(pool1, W_conv['conv2'], strides=[1, 1, 1, 1], padding='SAME')
conv2 = tf.nn.bias_add(conv2, b_conv['conv2'])
conv2 = batch_norm(conv2, True)
conv2 = tf.nn.relu(conv2)
    # 池化层 2
pool2 = tf.nn.avg_pool(conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')

    # 卷积层3
conv3 = tf.nn.conv2d(pool2, W_conv['conv3'], strides=[1, 1, 1, 1], padding='SAME')
conv3 = tf.nn.bias_add(conv3, b_conv['conv3'])
conv3 = batch_norm(conv3, True)
conv3 = tf.nn.relu(conv3)

    # 卷积层4
conv4 = tf.nn.conv2d(conv3, W_conv['conv4'], strides=[1, 1, 1, 1], padding='SAME')
conv4 = tf.nn.bias_add(conv4, b_conv['conv4'])
conv4 = batch_norm(conv4, True)
conv4 = tf.nn.relu(conv4)

    # 卷积层5
conv5 = tf.nn.conv2d(conv4, W_conv['conv5'], strides=[1, 1, 1, 1], padding='SAME')
conv5 = tf.nn.bias_add(conv5, b_conv['conv5'])
conv5 = batch_norm(conv5, True)
conv5 = tf.nn.relu(conv5)

    # 池化层5
pool5 = tf.nn.avg_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
reshape = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc1 = tf.add(tf.matmul(reshape, W_conv['fc1']), b_conv['fc1'])
fc1 = batch_norm(fc1, True, False)
fc1 = tf.nn.relu(fc1)

    # 全连接层 2
fc2 = tf.add(tf.matmul(fc1, W_conv['fc2']), b_conv['fc2'])
fc2 = batch_norm(fc2, True, False)
fc2 = tf.nn.relu(fc2)
out = tf.add(tf.matmul(fc2, W_conv['fc3']), b_conv['fc3'])

    # 定义损失
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=out))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)
# 评估模型
correct_pred = tf.equal(tf.argmax(out,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

init = tf.global_variables_initializer()

#独热编码，可以提高准确度
def onehot(labels):
    '''one-hot 编码'''
    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
    
save_model = "./model/AlexNetModel.ckpt"   #模型保存的地址以及名字

def train(opech):
    with tf.Session() as sess:
        sess.run(init)
        train_writer = tf.summary.FileWriter(".//log", sess.graph)  # 输出日志的地方
        saver = tf.train.Saver()
        c = []
        start_time = time.time()
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(coord=coord)
        step = 0
        for i in range(opech):
            step = i
            image, label = sess.run([image_batch, label_batch])
            labels = onehot(label)
            acc=[]
            sess.run(optimizer, feed_dict={x: image, y: labels})
            loss_record = sess.run(loss, feed_dict={x: image, y: labels})
            acc=sess.run(accuracy,feed_dict={x:image,y:labels})
            print("now the loss is %f " % loss_record)
            print("now the accuracy is %f "%acc)
            c.append(loss_record)
            end_time = time.time()
            print('time: ', (end_time - start_time))
            start_time = end_time
            print("---------------%d onpech is finished-------------------" % i)
        print("Optimization Finished!")
        #        checkpoint_path = os.path.join(".//model", 'model.ckpt')  # 输出模型的地方
        saver.save(sess, save_model)
        print("Model Save Finished!")

        coord.request_stop()
        coord.join(threads)
        plt.plot(c)
        plt.xlabel('Iter')
        plt.ylabel('loss')
        plt.title('lr=%f, ti=%d, bs=%d' % (learning_rate, training_iters, batch_size))
        plt.tight_layout()
        plt.savefig('cat_and_dog_AlexNet.jpg', dpi=200)

train(training_iters)

训练时只需要更改训练集的地址即可

4、训练过程

训练结束后模型会保存在model文件夹中，我们就可以用训练好的模型进行测试啦。

5、模型测试

import cv2
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import time
import os
import input_data
from PIL import Image
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.InteractiveSession(config=config)

testfile = 'D:\\神经网络\\Alexnet\\猫狗数据集\\test\\'#测试集地址
def batch_norm(inputs,is_train,is_conv_out=True,decay=0.999):
    scale=tf.Variable(tf.ones([inputs.get_shape()[-1]]))
    beta = tf.Variable(tf.zeros([inputs.get_shape()[-1]]))
    pop_mean = tf.Variable(tf.zeros([inputs.get_shape()[-1]]), trainable=False)
    pop_var = tf.Variable(tf.ones([inputs.get_shape()[-1]]), trainable=False)

    if is_train:
        if is_conv_out:
            batch_mean, batch_var = tf.nn.moments(inputs, [0, 1, 2])
        else:
            batch_mean, batch_var = tf.nn.moments(inputs, [0])

        train_mean = tf.assign(pop_mean, pop_mean * decay + batch_mean * (1 - decay))
        train_var = tf.assign(pop_var, pop_var * decay + batch_var * (1 - decay))

        with tf.control_dependencies([train_mean, train_var]):
            return tf.nn.batch_normalization(inputs,
                                             batch_mean, batch_var, beta, scale, 0.001)
    else:
        return tf.nn.batch_normalization(inputs,
                                         pop_mean, pop_var, beta, scale, 0.001)


 # 模型参数
learning_rate = 1e-4
training_iters = 200
batch_size = 50
display_step = 5
n_classes = 2
n_fc1 = 4096
n_fc2 = 2048

    # 构建模型
x = tf.placeholder(tf.float32, [None, 227, 227, 3])
y = tf.placeholder(tf.float32, [None, n_classes])

W_conv = {
        'conv1': tf.Variable(tf.truncated_normal([11, 11, 3, 96], stddev=0.0001)),
        'conv2': tf.Variable(tf.truncated_normal([5, 5, 96, 256], stddev=0.01)),
        'conv3': tf.Variable(tf.truncated_normal([3, 3, 256, 384], stddev=0.01)),
        'conv4': tf.Variable(tf.truncated_normal([3, 3, 384, 384], stddev=0.01)),
        'conv5': tf.Variable(tf.truncated_normal([3, 3, 384, 256], stddev=0.01)),
        'fc1': tf.Variable(tf.truncated_normal([6 * 6 * 256, n_fc1], stddev=0.1)),
        'fc2': tf.Variable(tf.truncated_normal([n_fc1, n_fc2], stddev=0.1)),
        'fc3': tf.Variable(tf.truncated_normal([n_fc2, n_classes], stddev=0.1))
    }
b_conv = {
        'conv1': tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[96])),
        'conv2': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[256])),
        'conv3': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[384])),
        'conv4': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[384])),
        'conv5': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[256])),
        'fc1': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_fc1])),
        'fc2': tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_fc2])),
        'fc3': tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[n_classes]))
    }

x_image = tf.reshape(x, [-1, 227, 227, 3])

    # 卷积层 1
conv1 = tf.nn.conv2d(x_image, W_conv['conv1'], strides=[1, 4, 4, 1], padding='VALID')
conv1 = tf.nn.bias_add(conv1, b_conv['conv1'])
conv1 = batch_norm(conv1, True)
conv1 = tf.nn.relu(conv1)
    # 池化层 1
pool1 = tf.nn.avg_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
norm1 = tf.nn.lrn(pool1, 5, bias=1.0, alpha=0.001 / 9.0, beta=0.75)

    # 卷积层 2
conv2 = tf.nn.conv2d(pool1, W_conv['conv2'], strides=[1, 1, 1, 1], padding='SAME')
conv2 = tf.nn.bias_add(conv2, b_conv['conv2'])
conv2 = batch_norm(conv2, True)
conv2 = tf.nn.relu(conv2)
    # 池化层 2
pool2 = tf.nn.avg_pool(conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')

    # 卷积层3
conv3 = tf.nn.conv2d(pool2, W_conv['conv3'], strides=[1, 1, 1, 1], padding='SAME')
conv3 = tf.nn.bias_add(conv3, b_conv['conv3'])
conv3 = batch_norm(conv3, True)
conv3 = tf.nn.relu(conv3)

    # 卷积层4
conv4 = tf.nn.conv2d(conv3, W_conv['conv4'], strides=[1, 1, 1, 1], padding='SAME')
conv4 = tf.nn.bias_add(conv4, b_conv['conv4'])
conv4 = batch_norm(conv4, True)
conv4 = tf.nn.relu(conv4)

    # 卷积层5
conv5 = tf.nn.conv2d(conv4, W_conv['conv5'], strides=[1, 1, 1, 1], padding='SAME')
conv5 = tf.nn.bias_add(conv5, b_conv['conv5'])
conv5 = batch_norm(conv5, True)
conv5 = tf.nn.relu(conv5)

    # 池化层5
pool5 = tf.nn.avg_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
reshape = tf.reshape(pool5, [-1, 6 * 6 * 256])
fc1 = tf.add(tf.matmul(reshape, W_conv['fc1']), b_conv['fc1'])
fc1 = batch_norm(fc1, True, False)
fc1 = tf.nn.relu(fc1)

    # 全连接层 2
fc2 = tf.add(tf.matmul(fc1, W_conv['fc2']), b_conv['fc2'])
fc2 = batch_norm(fc2, True, False)
fc2 = tf.nn.relu(fc2)
out = tf.add(tf.matmul(fc2, W_conv['fc3']), b_conv['fc3'])

saver = tf.train.Saver()

with tf.device('/gpu:0'):
    def Evaluate(testfile):
        
        count = 0
        sums = 0
        start_time = time.time()
        with tf.Session() as sess:
           # sess.run(tf.initialize_all_variables())
            saver.restore(sess, './model/AlexNetModel.ckpt-2000')#提取模型参数
            for root, sub_folders, files in os.walk(testfile):
                for name in files:
                    sums += 1
                    imagefile = os.path.join(root, name)
                    print(imagefile)
                    image = Image.open(imagefile)
                    image = image.resize([224, 224])
                    image_array = np.array(image) 
                    image = tf.cast(image_array, tf.float32)
                    image = tf.image.per_image_standardization(image)
                    image = tf.reshape(image, [1, 224, 224, 3])
                    image = sess.run(image)
                    prediction = sess.run(out,feed_dict={x: image})
                    end_time = time.time()
                    print('time: ', (end_time - start_time))
                    start_time = end_time
                    max_index = np.argmax(prediction)
                    if max_index==0:
                        print("猫")
                    else:
                        print("狗")
                    if max_index == 0 and name.split('.')[0] == 'cat':
                        count += 1
                    if max_index == 1 and name.split('.')[0] == 'dog':
                        count += 1
                    print(" The accuracy is: ", count,sums)
                print(" The accuracy is: ", count / sums)
                print(" The accuracy is: ", count,sums)
                
                
 
Evaluate(testfile)

三、总结

我们首先要做的就是划分数据集，先运行devide.py文件，从训练集中抽取20%作为测试集，运行结束之后，运行reshape.py文件，将训练集和测试集都reshape为224x224，然后运行train.py文件，注意要修改测试集的地址。训练完成以后模型保存在model文件夹中，我们运行evaluate.py文件进行模型测试，注意要修改模型所在的地址。
各位同学如果有不懂的地方可以评论或者私信我，我都会一一解答，有错误的地方还请大佬指正