MNIST手写数字识别之Tensorflow实现---全连接实现

import tensorflow as tf
# 用tensorflow 导入数据
from tensorflow.examples.tutorials.mnist import input_data
import os

os.environ['CUDA_VISIBLE_DEVICES'] = '0'

# 设置按需使用GPU
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.InteractiveSession(config=config)

# MNIST_data代表当前程序文件所在的目录中，用于存放MNIST数据的文件夹，如果没有则新建，然后下载．
# 如果当前文件所在目录中，不存在 MNIST_data 这个目录的话，程序会自动下载 MNIST 数据到这个位置，# 如果已经存在了的话，就直接读取数据文件。
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)


# print('训练集信息：', mnist.train.images.shape, mnist.train.labels.shape)
# print('测试集信息：', mnist.test.images.shape, mnist.test.labels.shape)
# print('验证集信息：', mnist.validation.images.shape, mnist.validation.labels.shape)

# 获取第5张图片，标签为[0. 0. 0. 0. 0. 0. 0. 0. 1. 0.]
# image = mnist.train.images[5]
# 将图像数据还原成28*28的分辨率
# image = image.reshape(28, 28)
# 打印对应的标签
# print(mnist.train.labels[5])
# 
# plt.figure()
# plt.imshow(image)
# plt.show()

# 权值初始化
def weight_variable(shape):
    # 用正态分布来初始化权值
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)


# 偏置初始化
def bias_variable(shape):
    # 本例中用relu激活函数，所以用一个很小的正偏置较好
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)


# input_layer
x_input = tf.placeholder(tf.float32, [None, 784], name="x_input")
y_input = tf.placeholder(tf.float32, [None, 10], name="y_input")

# FC1
W_fc1 = weight_variable([784, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(x_input, W_fc1) + b_fc1, name="h_fc1")

# FC2
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_pre = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2, name="y_pre")

# 1.损失函数loss：loss_cross_entropy
# loss_cross_entropy = -tf.reduce_sum(y_input * tf.log(y_pre))

# 损失模型隐藏到loss-model模块
with tf.name_scope("loss-model"):
    # 1.损失函数loss：loss_cross_entropy
    loss_cross_entropy = -tf.reduce_sum(y_input * tf.log(y_pre))
    # 给损失模型的输出添加scalar，用来观察loss的收敛曲线
    tf.summary.scalar("loss", loss_cross_entropy)

# 2.优化函数：AdamOptimizer, 优化速度要比 GradientOptimizer 快很多
# train_step = tf.train.AdamOptimizer(0.001).minimize(loss_cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.001).minimize(loss_cross_entropy)
# 等价于以下语句：
# optimizer = tf.train.AdamOptimizer(0.001)
# train_step = optimizer.minimize(loss_cross_entropy)

# 3.预测结果评估
# 预测值中最大值（１）即分类结果，是否等于原始标签中的（１）的位置。
# argmax()取最大值所在的下标
# y_pre和y_input一行对应一个标签，行数对应batch的size大小
# correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.arg_max(y_input, 1))
# accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.name_scope("accuracy-model"):
    # y_pre和y_input一行对应一个标签，行数对应batch的size大小
    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.arg_max(y_input, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    # 给损失模型的输出添加scalar，用来观察accracy的收敛曲线
    tf.summary.scalar("test_acc", accuracy)

# 开始运行
sess.run(tf.global_variables_initializer())

# 调用 merge_all() 收集所有的操作数据
merged = tf.summary.merge_all()

# 模型运行产生的所有数据保存到 ./tensorflow 文件夹供 TensorBoard 使用
writer = tf.summary.FileWriter('./tensorboard', sess.graph, filename_suffix="_mnist")

# 迭代 100 个 epoch， 训练准确率已经达到了0.98
for i in range(55000):
    x_batch, y_batch = mnist.train.next_batch(batch_size=100)

    # train_step.run(feed_dict={x_input: x_batch, y_input: y_batch})
    # 等价于下面语句：
    # sess.run(train_step,feed_dict={x_input: x_batch, y_input: y_batch})

    # summary = sess.run(merged, feed_dict={x_input: x_batch, y_input: y_batch})
    # train_step.run(feed_dict={x_input: x_batch, y_input: y_batch})
    # 等价于上述两条语句
    summary, _, train_loss = sess.run([merged, train_step, loss_cross_entropy],
                                      feed_dict={x_input: x_batch, y_input: y_batch})
    # print("step %d, loss %s" % (i, train_loss))

    if (i + 1) % 100 == 0:
        # print("step %d,\ttrain_loss %s" % (i+1, train_loss))
        train_accuracy = accuracy.eval(feed_dict={x_input: mnist.train.images, y_input: mnist.train.labels})
        print("step %d,\ttrain_loss %s,\ttrain acc %g" % (i + 1, train_loss, train_accuracy))

    if (i + 1) % 500 == 0:
        test_accuracy = accuracy.eval(feed_dict={x_input: mnist.test.images, y_input: mnist.test.labels})
        print("= " * 10, "step %d,\ttest acc %g" % (i + 1, test_accuracy))

    writer.add_summary(summary, i)

val_accuracy = accuracy.eval(feed_dict={x_input: mnist.validation.images, y_input: mnist.validation.labels})
print("* " * 10, "step %d, validation acc %g" % (i + 1, val_accuracy))
手动下载mnist数据集地址：http://yann.lecun.com/exdb/mnist/
本程序是使用两个全连接层实现手写数字识别分类，模型框架如图所示：
MNIST手写数字识别之Tensorflow实现---全连接实现

猜你喜欢
