深度学习框架tensorflow实战（Cifar图像分类任务）

~Cifar分类前需理解：

Numpy中stack()，hstack()，vstack()函数详解：https://blog.csdn.net/csdn15698845876/article/details/73380803

python 的np.mean()解析：https://blog.csdn.net/fu6543210/article/details/80223711

关于numpy中random-seed函数：https://blog.csdn.net/IAMoldpan/article/details/78429165

数据源：The CIFAR-10 dataset

http://www.cs.toronto.edu/~kriz/cifar.html
CIFAR-10数据集包含10个类中的60000张32x32彩色图像，每个类包含6000张图像。训练图像50000张，测试图像10000张。

返回字典类型的读取

import pickle

def unpickle(file):
    fo = open(file, 'rb')
    dict = pickle.load(fo, encoding='latin1')
    fo.close()
    return dict

在字典结构中，每一张图片是以被展开的形式存储，即一张32乘以32乘以3的图片被展开成3072长度的list，每一个数据的格式为unit8，前1024为红色通道，中间1024为绿色通道，后1024为蓝色通道。

对图像进行预处理

对数据进行标准化操作，按照一定比例进行缩放，使其落入一个特定的区域，便于操作处理。提高了处理速度。

'''
对RGB图像进行处理，输入5000乘3072返回5000乘574（24乘24），后面会用灰度图像输出
'''
import numpy as np

def clean(data):
    imgs = data.reshape(data.shape[0], 3, 32, 32)
    grayscale_imgs = imgs.mean(1)
    cropped_imgs = grayscale_imgs[:, 4:28, 4:28]
    img_data = cropped_imgs.reshape(data.shape[0], -1)
    img_size = np.shape(img_data)[1]
    means = np.mean(img_data, axis=1)
    meansT = means.reshape(len(means), 1)
    stds = np.std(img_data, axis=1)
    stdsT = stds.reshape(len(stds), 1)
    adj_stds = np.maximum(stdsT, 1.0 / np.sqrt(img_size))
    normalized = (img_data - meansT) / adj_stds
    return normalized

读取数据

def read_data(directory):
    names = unpickle('{}/batches.meta'.format(directory))['label_names']
    print('names', names)

    data, labels = [], []
    for i in range(1, 6):
        filename = '{}/data_batch_{}'.format(directory, i)
        batch_data = unpickle(filename)
        if len(data) > 0:                          #拼接五个文件的数据
            data = np.vstack((data, batch_data['data']))
            labels = np.hstack((labels, batch_data['labels']))
        else:
            data = batch_data['data']
            labels = batch_data['labels']

    print(np.shape(data), np.shape(labels))

    data = clean(data)
    data = data.astype(np.float32)
    return names, data, labels

显示数据

import matplotlib.pyplot as plt
import random
random.seed(1)   #指定random.seed后，每次运行产生的图片都会是那几个图像，不会每次都发生改变

names, data, labels = read_data('./cifar-10-batches-py')

def show_some_examples(names, data, labels):
    plt.figure()
    rows, cols = 4, 4
    random_idxs = random.sample(range(len(data)), rows * cols)
    for i in range(rows * cols):
        plt.subplot(rows, cols, i + 1)
        j = random_idxs[i]
        plt.title(names[labels[j]])
        img = np.reshape(data[j, :], (24, 24))
        plt.imshow(img, cmap='Greys_r')
        plt.axis('off')
    plt.tight_layout()
    plt.savefig('cifar_examples.png')
    plt.show()

show_some_examples(names, data, labels)

random.sample(sequence,k)函数

从指定序列中随机获取指定长度的片段。

plt.subplot(r,c,num)函数

当需要包含多个子图时使用，分成r行和c列，从左到右从上到下对每个子区进行编号，num指定创建的对象在哪个区域。

输出结果：

names ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
(50000, 3072) (50000,)

显示卷积后的图片以及参数的函数

import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf

names, data, labels = read_data('./cifar-10-batches-py')


def show_conv_results(data, filename=None):
    plt.figure(1)
    rows, cols = 4, 8
    for i in range(np.shape(data)[3]):
        img = data[0, :, :, i]
        plt.subplot(rows, cols, i + 1)
        plt.imshow(img, cmap='Greys_r', interpolation='none')
        plt.axis('off')
    if filename:
        plt.savefig(filename)
    else:
        plt.show()


def show_weights(W, filename=None):
    plt.figure()
    rows, cols = 4, 8
    for i in range(np.shape(W)[3]):
        img = W[:, :, 0, i]
        plt.subplot(rows, cols, i + 1)
        plt.imshow(img, cmap='Greys_r', interpolation='none')
        plt.axis('off')
    if filename:
        plt.savefig(filename)
    else:
        plt.show()

读取某张图片把它显示出来

print(np.shape(data))
raw_data = data[4, :]
raw_img = np.reshape(raw_data, (24, 24))
plt.figure()
plt.imshow(raw_img, cmap='Greys_r')
plt.show()

卷积参数初始化,进行卷积和池化

x = tf.reshape(raw_data, shape=[-1, 24, 24, 1])
W = tf.Variable(tf.random_normal([5, 5, 1, 32]))
b = tf.Variable(tf.random_normal([32]))
'''
以下为卷积操作
'''
conv = tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
conv_with_b = tf.nn.bias_add(conv, b)
conv_out = tf.nn.relu(conv_with_b)
'''
以下为池化操作
'''
k = 2
maxpool = tf.nn.max_pool(conv_out, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')

分类过程中输出四种情况

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    W_val = sess.run(W)
    print('weights:')
    show_weights(W_val)

    conv_val = sess.run(conv)
    print('convolution results:')
    print(np.shape(conv_val))
    show_conv_results(conv_val)

    conv_out_val = sess.run(conv_out)
    print('convolution with bias and relu:')
    print(np.shape(conv_out_val))
    show_conv_results(conv_out_val)

    maxpool_val = sess.run(maxpool)
    print('maxpool after all the convolutions:')
    print(np.shape(maxpool_val))
    show_conv_results(maxpool_val)

产生的32种随机卷积核：

经过32种卷积核卷积产生的图片
(1, 24, 24, 32)

通过激活函数后的图片
(1, 24, 24, 32)

通过池化产生的图像
(1, 12, 12, 32)