tensorflow基于CNN实战mnist手写识别(小白必看)

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data #mnist数据用到的包

mnist = input_data.read_data_sets('mnist_data',one_hot=True)

input_x = tf.compat.v1.placeholder(tf.float32,[None,28*28],name='input_x')#图片输入
output_y = tf.compat.v1.placeholder(tf.int32,[None,10],name='output_y')#结果的输出
image = tf.reshape(input_x,[-1,28,28,1])#对input_x进行改变形状，

test_x = mnist.test.images[:3000]
test_y = mnist.test.labels[:3000]

#第一层卷积
conv1 = tf.layers.conv2d(inputs=image,#输入
  filters=32,#32个过滤器
  kernel_size=[5,5],#过滤器在二维的大小是5*5
  strides=1,#步长是1
  padding='same',#same表示输出的大小不变，因此需要补零
  activation=tf.nn.relu#激活函数
 )#形状[28,28,32]

pool1 = tf.layers.max_pooling2d(
  inputs=conv1,#第一层卷积后的值
  pool_size=[2,2],#过滤器二维大小2*2
  strides=2 #步长2
)#形状[14,14,32]

conv2 = tf.layers.conv2d(inputs=pool1,
  filters=64,
  kernel_size=[5,5],
  strides=1,
  padding='same',
  activation=tf.nn.relu
)#形状[14,14,64]

pool2 = tf.layers.max_pooling2d(
  inputs=conv2,
  pool_size=[2,2],
  strides=2
)#形状[7,7,64]

flat = tf.reshape(pool2,[-1,7*7*64])

dense = tf.layers.dense(inputs=flat,units=1024,activation=tf.nn.relu)

dropout = tf.layers.dropout(inputs=dense,rate=0.5)

logits = tf.layers.dense(inputs=dropout,units=10,name="logit_1")

#计算误差，使用交叉熵（交叉熵用来衡量真实值和预测值的相似性）
loss = tf.losses.softmax_cross_entropy(onehot_labels=output_y,logits=logits)
#学习率0.001 最小化loss值,adam优化器
train_op = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)

accurary = tf.metrics.accuracy(
   labels=tf.argmax(output_y,axis=1),
   predictions=tf.argmax(logits,axis=1),)[1]

sess = tf.compat.v1.Session()#创建一个会话
#初始化全局变量和局部变量
init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init)

for i in range(1000):
 #获取以batch_size为大小的一个元组，包含一组图片和标签
 batch = mnist.train.next_batch(50)
 train_loss,train_op_,logits_output = sess.run([loss,train_op,logits],{input_x:batch[0],output_y:batch[1]})
 if i % 100 == 0:
  test_accuracy = sess.run(accurary,{input_x:test_x,output_y:test_y})
  print(("step=%d,Train loss=%.4f,[Test accuracy=%.2f]") \
    % (i, train_loss, test_accuracy))