TensorFlow之Cifar-10图像分类任务

cifar-10数据集位置如下图：

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

random.seed(1)


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


# 图像数据预处理下
def clean(data):
    data_0_shape = data.shape[0]
    print(data_0_shape)
    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']  # ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
    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:
            data = np.vstack((data, batch_data['data']))
            labels = np.hstack((labels, batch_data['labels']))
        else:
            data = batch_data['data']
            labels = batch_data['labels']

    # data的shape=(50000,3072) ,3072 = 32x32x3
    # labels的shape=(50000,)
    print("shape = ", np.shape(data), np.shape(labels))

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

#显示几张图片
def show_some_examples(names, data, labels):
    # data shape=  (50000, 576),576 = 24x24
    print("after data shape= ", data.shape)

    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()
cifar10_dir = 'F:/AI/Python/HXPyhon/PycharmProjects/CIFAR10_dataset/cifar-10-batches-py/'
names, data, labels = read_data(cifar10_dir)
show_some_examples(names, data, labels)

---

选择其中一张图片，查看结果

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

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]))

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)

k = 2
maxpool = tf.nn.max_pool(conv_out, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')

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)

weights:

convolution results:
(1, 24, 24, 32)

convolution with bias and relu:
(1, 24, 24, 32)

maxpool after all the convolutions:
(1, 12, 12, 32)

---

构建完整网络模型：

# 构建完整网络模型
x = tf.placeholder(tf.float32, [None, 24 * 24])
y = tf.placeholder(tf.float32, [None, len(names)])
W1 = tf.Variable(tf.random_normal([5, 5, 1, 64]))
b1 = tf.Variable(tf.random_normal([64]))
W2 = tf.Variable(tf.random_normal([5, 5, 64, 64]))
b2 = tf.Variable(tf.random_normal([64]))
W3 = tf.Variable(tf.random_normal([6 * 6 * 64, 1024]))
b3 = tf.Variable(tf.random_normal([1024]))
W_out = tf.Variable(tf.random_normal([1024, len(names)]))
b_out = tf.Variable(tf.random_normal([len(names)]))


def conv_layer(x, W, b):
    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)
    return conv_out


def maxpool_layer(conv, k=2):
    return tf.nn.max_pool(conv, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')


def model():
    x_reshaped = tf.reshape(x, shape=[-1, 24, 24, 1])

    conv_out1 = conv_layer(x_reshaped, W1, b1)
    maxpool_out1 = maxpool_layer(conv_out1)
    # 提出了LRN层，对局部神经元的活动创建竞争机制，使得其中响应比较大的值变得相对更大，并抑制其他反馈较小的神经元，增强了模型的泛化能力。
    # 推荐阅读http://blog.csdn.net/banana1006034246/article/details/75204013
    norm1 = tf.nn.lrn(maxpool_out1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
    conv_out2 = conv_layer(norm1, W2, b2)
    norm2 = tf.nn.lrn(conv_out2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
    maxpool_out2 = maxpool_layer(norm2)

    maxpool_reshaped = tf.reshape(maxpool_out2, [-1, W3.get_shape().as_list()[0]])
    local = tf.add(tf.matmul(maxpool_reshaped, W3), b3)
    local_out = tf.nn.relu(local)

    out = tf.add(tf.matmul(local_out, W_out), b_out)
    return out


learning_rate = 0.001
model_op = model()

cost = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits=model_op, labels=y)
)
train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

correct_pred = tf.equal(tf.argmax(model_op, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    onehot_labels = tf.one_hot(labels, len(names), axis=-1)
    onehot_vals = sess.run(onehot_labels)
    batch_size = 64
    print('batch size', batch_size)
    for j in range(0, 1000):
        avg_accuracy_val = 0.
        batch_count = 0.
        data_len = len(data)
        for i in range(0, len(data), batch_size):
            batch_data = data[i:i + batch_size, :]
            batch_onehot_vals = onehot_vals[i:i + batch_size, :]
            _, accuracy_val = sess.run([train_op, accuracy], feed_dict={x: batch_data, y: batch_onehot_vals})
            avg_accuracy_val += accuracy_val
            batch_count += 1.
            print("avg_accuracy_val=", avg_accuracy_val)
        avg_accuracy_val /= batch_count
        print('Epoch {}. Avg accuracy {}'.format(j, avg_accuracy_val))