炼数成金Tensorflow学习笔记之3.2_MNIST分类简单版本

代码及分析

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# 载入数据集
mnist = input_data.read_data_sets('.\MNIST_data', one_hot=True)

# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size

# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

# 创建一个简单的神经网络
w = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x,w) + b)

# 二次代价函数
loss = tf.reduce_mean(tf.square(y - prediction))
# 使用梯度下降法
train_op = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

init_op = tf.global_variables_initializer()

# 求准确率
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(init_op)
    for epoch in range(21):
        for batch in range(n_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            sess.run(train_op, feed_dict={x:batch_x, y:batch_y})
        acc = sess.run(accuracy, feed_dict= {x:mnist.test.images, y:mnist.test.labels})
        print("iter" + str(epoch) + ", testing acc: " + str(acc))
'''
运行结果：
Extracting .\MNIST_data\train-images-idx3-ubyte.gz
Extracting .\MNIST_data\train-labels-idx1-ubyte.gz
Extracting .\MNIST_data\t10k-images-idx3-ubyte.gz
Extracting .\MNIST_data\t10k-labels-idx1-ubyte.gz
iter0, testing acc: 0.8307
iter1, testing acc: 0.8707
iter2, testing acc: 0.8805
iter3, testing acc: 0.8884
iter4, testing acc: 0.8938
iter5, testing acc: 0.8981
iter6, testing acc: 0.8996
iter7, testing acc: 0.902
iter8, testing acc: 0.9036
iter9, testing acc: 0.9055
iter10, testing acc: 0.9064
iter11, testing acc: 0.9073
iter12, testing acc: 0.9088
iter13, testing acc: 0.9091
iter14, testing acc: 0.9095
iter15, testing acc: 0.9104
iter16, testing acc: 0.9112
iter17, testing acc: 0.9119
iter18, testing acc: 0.9132
iter19, testing acc: 0.9135
iter20, testing acc: 0.9138
'''

1. tf.nn.softmax(logits, axis=None, name=None, dim=None)
   作用：计算softmax激活（softmax = tf.exp(logits) / tf.reduce_sum(tf.exp(logits), axis)）
   logits:一个非空张量
   axis:将被执行的softmax维度，默认值是-1，表示最后一个维度。
2. tf.argmax(input,axis)
   作用：根据axis取值的不同返回每行或者每列最大值的索引
3. tf.equal(x, y, name=None)
   作用：逐个元素进行判断，如果相等就是True，不相等，就是False（由于是逐个元素判断，所以x，y 的维度要一致。）
4. tf.cast(x, dtype, name=None)
   作用：执行 tensorflow 中张量数据类型转换
   x: 待转换的数据（张量）
   dtype： 目标数据类型
   name： 可选参数，定义操作的名称