# 卷积神经网络，从cifar100的文件中获取数据
import tensorflow as tf
import numpy as np
import pickle
# 1.获取数据集
fo = open(r'test', 'rb')
dict = pickle.load(fo, encoding='bytes') #用pickle加载数据
fo.close()
#2.数据处理
imgArr = dict[b'data'].reshape(-1, 3, 32, 32).transpose(0, 2, 3, 1) / 255 #提取data=X,并reshape(?,32,32,3),缩放
total = imgArr.shape[0] #总样本数total
Y_one_hot = np.eye(100)[dict[b'fine_labels']] #fine_labels=y, np.eye(100):独热编码
# 训练集的比例
train_test = 0.9
# 自己实现next_batch函数，每次返回一批数据
def next_batch(size):
global g_b
xb = imgArr[g_b:g_b+size]
yb = Y_one_hot[g_b:g_b+size]
g_b = g_b + size
return xb,yb
# 参数
learning_rate = 0.001 # 学习率
training_epochs = 1 # 训练总周期
batch_size = 100 # 训练每批样本数
#定义占位符
X = tf.placeholder(tf.float32, [None, 32, 32, 3])
Y = tf.placeholder(tf.float32, [None, 100]) # 独热编码
# 第1层卷积，输入图片数据(?, 32, 32, 3)
W1 = tf.Variable(tf.random_normal([3, 3, 3, 32])) #卷积核3x3，输入通道3，输出通道32
L1 = tf.nn.conv2d(X, W1, strides=[1, 1, 1, 1], padding='SAME') #卷积输出 （?, 32, 32, 32)
L1 = tf.nn.relu(L1)
L1 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME') #池化输出 (?, 16, 16, 32)
# 第2层卷积，输入图片数据(?, 16, 16, 32)
W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01)) #卷积核3x3，输入通道32，输出通道64
L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME') #卷积输出 (?, 16, 16, 64)
L2 = tf.nn.relu(L2)
L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #池化输出 (?, 8, 8, 64)
#全连接展平
dim = L2.get_shape()[1].value * L2.get_shape()[2].value * L2.get_shape()[3].value
L2_flat = tf.reshape(L2,[-1, dim])
# 全连接
W3 = tf.get_variable("W3", shape=[dim, 100])
b = tf.Variable(tf.random_normal([100]))
logits = tf.matmul(L2_flat, W3) + b
#代价或损失函数, 优化器
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # 优化器
# 测试模型检查准确率
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 创建会话
sess = tf.Session()
sess.run(tf.global_variables_initializer()) #全局变量初始化
# 迭代训练
print('开始学习...')
for epoch in range(training_epochs):
total_batch = int(total * train_test / batch_size) # 计算总批次
g_b = 0
for i in range(total_batch):
batch_xs, batch_ys = next_batch(batch_size)
_ = sess.run([optimizer], feed_dict={X: batch_xs, Y: batch_ys})
print('学习完成')
# 测试模型检查准确率
print('Accuracy:', sess.run(accuracy, feed_dict={X: imgArr[int(total * train_test):], Y: Y_one_hot[int(total * train_test):]}))
