深度学习-使用tensorflow实现猫狗识别

最近一直在撸猫，为了猫主子的事情忧三愁四，皱纹多了不少，头发也掉了好几根，神态也多了几分忧郁，唯一不变的还是那份闲鱼的懒散和浪荡的心。

要说到深度学习图像分类的经典案例之一，那就是猫狗大战了。猫和狗在外观上的差别还是挺明显的，无论是体型、四肢、脸庞和毛发等等， 都是能通过肉眼很容易区分的。

那么如何让机器来识别猫和狗呢？这就需要使用卷积神经网络来实现了。

网上已经有不少人写过这案例了，我也来尝试下练练手。

完整代码：https://github.com/ADlead/Dogs-Cats.git

一. 数据集的准备

猫狗照片的数据集直接从kaggle官网(https://www.kaggle.com/c/dogs-vs-cats)下载即可，下载后解压，可以看到有训练集和测试集

train文件夹内容如下：

test1文件夹内容如下：

编写代码将图片存储成batch文件

import cv2 as cv
import os
import numpy as np
import random
import pickle
import time

start_time = time.time()

data_dir = './data'
batch_save_path = './batch_files'

# 创建batch文件存储的文件夹
os.makedirs(batch_save_path, exist_ok=True)

# 图片统一大小：100 * 100
# 训练集 20000：100个batch文件，每个文件200张图片
# 验证集 5000：一个测试文件，测试时 50张 x 100 批次

# 进入图片数据的目录，读取图片信息
all_data_files = os.listdir(os.path.join(data_dir, 'train/'))

# print(all_data_files)

# 打算数据的顺序
random.shuffle(all_data_files)

all_train_files = all_data_files[:20000]
all_test_files = all_data_files[20000:]

train_data = []
train_label = []
train_filenames = []

test_data = []
test_label = []
test_filenames = []

# 训练集
for each in all_train_files:
    img = cv.imread(os.path.join(data_dir,'train/',each),1)
    resized_img = cv.resize(img, (100,100))

    img_data = np.array(resized_img)
    train_data.append(img_data)
    if 'cat' in each:
        train_label.append(0)
    elif 'dog' in each:
        train_label.append(1)
    else:
        raise Exception('%s is wrong train file'%(each))
    train_filenames.append(each)

# 测试集
for each in all_test_files:
    img = cv.imread(os.path.join(data_dir,'train/',each), 1)
    resized_img = cv.resize(img, (100,100))

    img_data = np.array(resized_img)
    test_data.append(img_data)
    if 'cat' in each:
        test_label.append(0)
    elif 'dog' in each:
        test_label.append(1)
    else:
        raise Exception('%s is wrong test file'%(each))
    test_filenames.append(each)

print(len(train_data), len(test_data))

# 制作100个batch文件
start = 0
end = 200
for num in range(1, 101):
    batch_data = train_data[start: end]
    batch_label = train_label[start: end]
    batch_filenames = train_filenames[start: end]
    batch_name = 'training batch {} of 15'.format(num)

    all_data = {
    'data':batch_data,
    'label':batch_label,
    'filenames':batch_filenames,
    'name':batch_name
    }

    with open(os.path.join(batch_save_path, 'train_batch_{}'.format(num)), 'wb') as f:
        pickle.dump(all_data, f)

    start += 200
    end += 200

# 制作测试文件
all_test_data = {
    'data':test_data,
    'label':test_label,
    'filenames':test_filenames,
    'name':'test batch 1 of 1'
    }

with open(os.path.join(batch_save_path, 'test_batch'), 'wb') as f:
    pickle.dump(all_test_data, f)

end_time = time.time()
print('制作结束, 用时{}秒'.format(end_time - start_time))

运行程序后，文件就处理好了

二. 神经网络的编写

cnn卷积神经网络的编写如下，编写卷积层、池化层和全连接层的代码

conv1_1 = tf.layers.conv2d(x, 16, (3, 3), padding='same', activation=tf.nn.relu, name='conv1_1')
conv1_2 = tf.layers.conv2d(conv1_1, 16, (3, 3), padding='same', activation=tf.nn.relu, name='conv1_2')
pool1 = tf.layers.max_pooling2d(conv1_2, (2, 2), (2, 2), name='pool1')
conv2_1 = tf.layers.conv2d(pool1, 32, (3, 3), padding='same', activation=tf.nn.relu, name='conv2_1')
conv2_2 = tf.layers.conv2d(conv2_1, 32, (3, 3), padding='same', activation=tf.nn.relu, name='conv2_2')
pool2 = tf.layers.max_pooling2d(conv2_2, (2, 2), (2, 2), name='pool2')
conv3_1 = tf.layers.conv2d(pool2, 64, (3, 3), padding='same', activation=tf.nn.relu, name='conv3_1')
conv3_2 = tf.layers.conv2d(conv3_1, 64, (3, 3), padding='same', activation=tf.nn.relu, name='conv3_2')
pool3 = tf.layers.max_pooling2d(conv3_2, (2, 2), (2, 2), name='pool3')
conv4_1 = tf.layers.conv2d(pool3, 128, (3, 3), padding='same', activation=tf.nn.relu, name='conv4_1')
conv4_2 = tf.layers.conv2d(conv4_1, 128, (3, 3), padding='same', activation=tf.nn.relu, name='conv4_2')
pool4 = tf.layers.max_pooling2d(conv4_2, (2, 2), (2, 2), name='pool4')

flatten = tf.layers.flatten(pool4)
fc1 = tf.layers.dense(flatten, 512, tf.nn.relu)
fc1_dropout = tf.nn.dropout(fc1, keep_prob=keep_prob)
fc2 = tf.layers.dense(fc1, 256, tf.nn.relu)
fc2_dropout = tf.nn.dropout(fc2, keep_prob=keep_prob)
fc3 = tf.layers.dense(fc2, 2, None)

三. tensorflow计算图的搭建

然后，再搭建tensorflow的计算图，定义占位符，计算损失函数、预测值和准确率等等

self.x = tf.placeholder(tf.float32, [None, IMAGE_SIZE, IMAGE_SIZE, 3], 'input_data')
self.y = tf.placeholder(tf.int64, [None], 'output_data')
self.keep_prob = tf.placeholder(tf.float32)

# 图片输入网络中
fc = self.conv_net(self.x, self.keep_prob)
self.loss = tf.losses.sparse_softmax_cross_entropy(labels=self.y, logits=fc)
self.y_ = tf.nn.softmax(fc) # 计算每一类的概率
self.predict = tf.argmax(fc, 1)
self.acc = tf.reduce_mean(tf.cast(tf.equal(self.predict, self.y), tf.float32))
self.train_op = tf.train.AdamOptimizer(LEARNING_RATE).minimize(self.loss)
self.saver = tf.train.Saver(max_to_keep=1)

最后的saver是要将训练好的模型保存到本地。

四. 模型的训练和测试

然后编写训练部分的代码，训练步骤为1万步

acc_list = []
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    for i in range(TRAIN_STEP):
        train_data, train_label, _ = self.batch_train_data.next_batch(TRAIN_SIZE)

        eval_ops = [self.loss, self.acc, self.train_op]
        eval_ops_results = sess.run(eval_ops, feed_dict={
            self.x:train_data,
            self.y:train_label,
            self.keep_prob:0.7
        })
        loss_val, train_acc = eval_ops_results[0:2]

        acc_list.append(train_acc)
        if (i+1) % 100 == 0:
            acc_mean = np.mean(acc_list)
            print('step:{0},loss:{1:.5},acc:{2:.5},acc_mean:{3:.5}'.format(
                i+1,loss_val,train_acc,acc_mean
            ))
        if (i+1) % 1000 == 0:
            test_acc_list = []
            for j in range(TEST_STEP):
                test_data, test_label, _ = self.batch_test_data.next_batch(TRAIN_SIZE)
                acc_val = sess.run([self.acc],feed_dict={
                    self.x:test_data,
                    self.y:test_label,
                    self.keep_prob:1.0
            })
            test_acc_list.append(acc_val)
            print('[Test ] step:{0}, mean_acc:{1:.5}'.format(
                i+1, np.mean(test_acc_list)
            ))
    # 保存训练后的模型
    os.makedirs(SAVE_PATH, exist_ok=True)
    self.saver.save(sess, SAVE_PATH + 'my_model.ckpt')

训练结果如下

训练1万步后模型测试的平均准确率有0.82。

五. 识别和分类

最后，使用自己训练好的模型，把官网的测试图片(共12500张)识别后进行分类，并将分类后的图片分别写入到两个文件夹中，结果如下

分类为狗的图片如下：

分类为猫的图片如下：

可以看出，分类之后还有少数分类不对的结果。看来模型还有待提升，还可以调整网络参数、调整学习率和学习步数、使用图像增强等技术对模型识别准确率进行提高。

搞了一番，手和脚也有些累了。是时候撸撸猫继续闲鱼了。。

更多内容，可以到公众号 [ 浪学 ] 一起学习~