TensorFlow学习笔记（3）——CNN在CIFAR10上的实现

其他 2018-11-24 11:19:51 阅读次数: 0

CIFAR10是一个对图片进行10种分类的项目
这里写图片描述
官网提供了数据集的下载，此外官网还有对于数据集的介绍。数据集中数据被分为了两部分。第一部分是特征部分，使用一个[10000,3072]的uint8的矩阵进行存储，每一行向量都是32*32大小的3通道图片，构成的格式类似于[32,32,3]；第二部分为标签部分，使用一个10000数据的list进行存储，每个list对应的是0-9中的一个数字，对应物品的分类。此外在python数据集中还有一个标签为‘label_names’，例如label_names[0] ==’airplane’等。
对于数据的读取，官网也提供了相应的代码

def unpickle(file):
    import pickle
    with open(file, 'rb') as fo;
         dict = pickle.load(fo, encoding='bytes')
    return dict

代码示例

1、数据读取

前面说到，label是一个包含0-9的list列表，根据之前我们用到的one-hot方法，采用稀疏性列表法，即10个列表数字中只有对应的那个值是1，其他的值都是0，因此需要将list格式化成对应的one-hot矩阵。

def unpickle(filename):
    with open(filename, 'rb') as f:
        d = pickle.load(f, encoding='latin1')
        return d

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

# 训练数据集
data1 = unpickle('cifar10-dataset/data_batch_1')
data2 = unpickle('cifar10-dataset/data_batch_2')
data3 = unpickle('cifar10-dataset/data_batch_3')
data4 = unpickle('cifar10-dataset/data_batch_4')
data5 = unpickle('cifar10-dataset/data_batch_5')
X_train = np.concatenate((data1['data'], data2['data'], data3['data'], data4['data'], data5['data']), axis=0)
y_train = np.concatenate((data1['labels'], data2['labels'], data3['labels'], data4['labels'], data5['labels']), axis=0)
y_train = onehot(y_train)
# 测试数据集
test = unpickle('cifar10-dataset/test_batch')
X_test = test['data'][:5000, :]
y_test = onehot(test['labels'])[:5000, :]

print("Training dataset shape:", X_train.shape)
print('Training labels shape:', y_train.shape)
print('Testing dataset shape:', X_test.shape)
print('Testing labels shape:', y_test.shape)

这里使用unpick函数依次读取5个batch中的数据，生成5个dict格式文件，而其中的数据以[data, labels]格式存放，之后连接对应的5个特征数据和标签数据生成最终的训练集，采用前5000个数据作为测试集进行使用。

2、模型参数

learning_rate= 1e-3
training_iters = 200
batch_size = 50
display_step = 5
n_features = 3072 #32*32*3
n_classes = 10
n_fc1 = 384
n_fc2 = 192

3、模型构建

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

W_conv = {
    'conv1' : tf.Variable(tf.truncated_normal([5, 5, 3, 32], stddev=0.0001)),
    'conv2' : tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.01)),
    'fc1' : tf.Variable(tf.truncated_normal([8*8*64, 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=[32])),
    'conv2' : tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[64])),
    '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, 32, 32, 3])
# 卷积层1
conv1 = tf.nn.conv2d(x_image, W_conv['conv1'], strides=[1, 1, 1, 1], padding='SAME')
conv1 = tf.nn.bias_add(conv1, b_conv['conv1'])
conv1 = tf.nn.relu(conv1)
# 池化层1
poo11 = tf.nn.avg_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
# LRN层，Local Response Normalization
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
# 卷积层 2
conv2 = tf.nn.conv2d(norm1, E_conv['conv2'], ttrides=[1, 1, 1, 1], padding='SAME')
conv2 = tf.nn.bias_add(conv2, b_conv['conv2'])
conv2 = tf.nn.relu(conv2)
# LRN层
norm2  = tf.nn.lrn(conv2, 4, bias-1.0, alpha=0.001/9.0, beta=0.75)
# 池化层2
pool2 = tf.nn.avg_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
reshape = tf.reshape(pool2, [-1, 8*8*64])
# 全连接层1
fc1 = tf.add(tf.matmul(reshape, W_conv['fc1']), b_conv1['fc1'])
fc1 = tf.nn.relu(fc1)
# 全连接层2
fc2 = tf.add(tf.matmul(tf.matmul(fc1, W_conv['fc2']), b_conv['fc2']))
fc2 = tf.nn.relu(fc2)
# 全连接层3，即分类层
fc3 =  tf.nn.softmax(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(logits=fc3, labels=y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss)
# 评估模型
correct_pred = tf.equal(tf.argmax(fc3, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

4、运行部分

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    c = []
    total_batch = int(X_train.shape[0] / batch_size)
    start_time = time.time()
    for i in range(200):
        for batch in range(total_batch):
            batch_x = X_train[batch*batch_size : (batch+1)*batch_size, :]
            batch_y = y_train[batch*batch_size : (batch+1)*batch_size, :]
            sess.run(optimizer, feed_dict={x: batch_x, y : batch_y})
        acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
        print(acc)
        c.append(acc)
        end_time = time.time()
        print('time:', (end_time - start_time))
        start_time = end_time
        print("--------------%d onpech is finished------------", i)
    print("Optimization Finished!")

    # TEST
    test_acc = sess.run(accuracy, feed_dict={x : X_test, y : y_test})
    print("Testing Accuracy:", test_acc)
    plt.plot(c)
    plt.xlabel('Iter')
    plt.ylabel('Cost')
    plt.title('lr=%f, ti=%d, bs=%d, acc=%f' % (learning_rate, training_iters,batch_size, test_acc))
    plt.tight_layout()
    plt.savefig('cnn-tf-cifar10-%s.png' % test_acc, dpi=200)

完整代码

# coding:utf-8
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import _pickle as pickle
import time

def unpickle(filename):
    with open(filename, 'rb') as f:
        d = pickle.load(f, encoding='latin1')
        return d

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

# 训练数据集
data1 = unpickle('cifar10-dataset/data_batch_1')
data2 = unpickle('cifar10-dataset/data_batch_2')
data3 = unpickle('cifar10-dataset/data_batch_3')
data4 = unpickle('cifar10-dataset/data_batch_4')
data5 = unpickle('cifar10-dataset/data_batch_5')
X_train = np.concatenate((data1['data'], data2['data'], data3['data'], data4['data'], data5['data']), axis=0)
y_train = np.concatenate((data1['labels'], data2['labels'], data3['labels'], data4['labels'], data5['labels']), axis=0)
y_train = onehot(y_train)
# 测试数据集
test = unpickle('cifar10-dataset/test_batch')
X_test = test['data'][:5000, :]
y_test = onehot(test['labels'])[:5000, :]

print("Training dataset shape:", X_train.shape)
print('Training labels shape:', y_train.shape)
print('Testing dataset shape:', X_test.shape)
print('Testing labels shape:', y_test.shape)

learning_rate= 1e-3
training_iters = 200
batch_size = 50
display_step = 5
n_features = 3072 #32*32*3
n_classes = 10
n_fc1 = 384
n_fc2 = 192

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

W_conv = {
    'conv1' : tf.Variable(tf.truncated_normal([5, 5, 3, 32], stddev=0.0001)),
    'conv2' : tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.01)),
    'fc1' : tf.Variable(tf.truncated_normal([8*8*64, 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=[32])),
    'conv2' : tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[64])),
    '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, 32, 32, 3])
# 卷积层1
conv1 = tf.nn.conv2d(x_image, W_conv['conv1'], strides=[1, 1, 1, 1], padding='SAME')
conv1 = tf.nn.bias_add(conv1, b_conv['conv1'])
conv1 = tf.nn.relu(conv1)
# 池化层1
poo11 = tf.nn.avg_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
# LRN层，Local Response Normalization
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
# 卷积层 2
conv2 = tf.nn.conv2d(norm1, E_conv['conv2'], ttrides=[1, 1, 1, 1], padding='SAME')
conv2 = tf.nn.bias_add(conv2, b_conv['conv2'])
conv2 = tf.nn.relu(conv2)
# LRN层
norm2  = tf.nn.lrn(conv2, 4, bias-1.0, alpha=0.001/9.0, beta=0.75)
# 池化层2
pool2 = tf.nn.avg_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME')
reshape = tf.reshape(pool2, [-1, 8*8*64])
# 全连接层1
fc1 = tf.add(tf.matmul(reshape, W_conv['fc1']), b_conv1['fc1'])
fc1 = tf.nn.relu(fc1)
# 全连接层2
fc2 = tf.add(tf.matmul(tf.matmul(fc1, W_conv['fc2']), b_conv['fc2']))
fc2 = tf.nn.relu(fc2)
# 全连接层3，即分类层
fc3 =  tf.nn.softmax(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(logits=fc3, labels=y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(loss)
# 评估模型
correct_pred = tf.equal(tf.argmax(fc3, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    c = []
    total_batch = int(X_train.shape[0] / batch_size)
    start_time = time.time()
    for i in range(200):
        for batch in range(total_batch):
            batch_x = X_train[batch*batch_size : (batch+1)*batch_size, :]
            batch_y = y_train[batch*batch_size : (batch+1)*batch_size, :]
            sess.run(optimizer, feed_dict={x: batch_x, y : batch_y})
        acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
        print(acc)
        c.append(acc)
        end_time = time.time()
        print('time:', (end_time - start_time))
        start_time = end_time
        print("--------------%d onpech is finished------------", i)
    print("Optimization Finished!")

    # TEST
    test_acc = sess.run(accuracy, feed_dict={x : X_test, y : y_test})
    print("Testing Accuracy:", test_acc)
    plt.plot(c)
    plt.xlabel('Iter')
    plt.ylabel('Cost')
    plt.title('lr=%f, ti=%d, bs=%d, acc=%f' % (learning_rate, training_iters,batch_size, test_acc))
    plt.tight_layout()
    plt.savefig('cnn-tf-cifar10-%s.png' % test_acc, dpi=200)

猜你喜欢

转载自blog.csdn.net/weixin_42595515/article/details/82496708
今日推荐
TIOBE 5 月榜单：Fortran “复活”进入 Top 10
GCC 14.1 发布
面壁智能发布 Eurux-8x22B 开源大模型 —— 堪称「理科状元」
开源日报 | 谷歌扶持鸿蒙上位；开源Rabbit R1；Docker加持的安卓手机；微软的焦虑和野心；海尔电器把开放平台关了
中国码农的“35岁魔咒”
蘭雅 CorelDRAW 插件 2024.5.1 国际劳动节版，免费下载
Arc Browser for Windows 1.0 正式 GA
90后程序员开发视频搬运软件、不到一年获利超 700 万，结局很刑！
周排行
Java自定义时间格式
同步整形电路
在开发中最最最常用的字符串的属性大集合
Linux 查看端口占用并杀掉
Java基础四：ArrayList
多线程之死锁就是这么简单
mysql 基础命令集
awk 命令详解
Centos6.3编译安装nginx+php步骤
OCR （Optical Character Recognition，光学字符识别）
每日归档
更多
2024-05-08(42)
2024-05-07(14)
2024-05-06(40)
2024-05-05(0)
2024-05-04(7)
2024-05-03(19)
2024-05-02(0)
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022