AlexNet识别猫狗数据集
- 一、下载猫狗数据集
- 二、AlexNet实现
- 1、划分训练集和测试集
- 2、将训练集和测试集图片放缩为224x224
- 3、AlexNet实现
- 4、训练过程
- 5、模型测试
- 三、总结
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0.1picknumber=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)returnif __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 + filecv2.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 labelimage_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_Himage = 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_batchdef one_hot(labels):'''one-hot 编码'''n_sample=len(labels)n_class=max(labels)+1onehot_labels=np.zeros((n_sample,n_class))onehot_labels[np.arange(n_sample),labels]=1return 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) + 1onehot_labels = np.zeros((n_sample, n_class))onehot_labels[np.arange(n_sample), labels] = 1return onehot_labelssave_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 = 0for i in range(opech):step = iimage, 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_timeprint("---------------%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 = 0sums = 0start_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 += 1imagefile = 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_timemax_index = np.argmax(prediction)if max_index==0:print("猫")else:print("狗")if max_index == 0 and name.split('.')[0] == 'cat':count += 1if max_index == 1 and name.split('.')[0] == 'dog':count += 1print(" 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
