1.前向传播 mnist_inference.py
# -- coding: utf-8 --
import tensorflow as tf
#输入与输出层
INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#第一个卷积层的尺寸和深度
CONV1_DEEP = 32
CONV1_SIZE = 5
#第二个卷积层的尺寸和深度
CONV2_DEEP = 64
CONV2_SIZE = 5
#全连接层的节点数
FC_SIZE = 512
#前向传播函数
def inference(input_tensor, train, regularizer):
#第一层——卷积层
with tf.variable_scope('layer1-conv1'):
conv1_weights = tf.get_variable("weight", [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP], initializer=tf.truncated_normal_initializer(stddev=0.1))
conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))
conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides=[1,1,1,1], padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))
#第二层——池化层
with tf.name_scope('layer2-pool1'):
pool1 = tf.nn.max_pool(relu1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
#第三层——卷积层
with tf.variable_scope('layer3-conv2'):
conv2_weights = tf.get_variable('weight', [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP], initializer=tf.truncated_normal_initializer(stddev=0.1))
conv2_biases = tf.get_variable("bias", [CONV2_DEEP], initializer=tf.constant_initializer(0.0))
conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1,1,1,1], padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
#第四层——池化层
with tf.name_scope('layer4-pool2'):
pool2 = tf.nn.max_pool(relu2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
#第五层——全连接
pool_shape = pool2.get_shape().as_list()
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
reshaped = tf.reshape(pool2, [pool_shape[0], nodes])
with tf.variable_scope('layer5-fc1'):
fc1_weights = tf.get_variable("weight", [nodes, FC_SIZE], initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', regularizer(fc1_weights))
fc1_biase = tf.get_variable('biase', [FC_SIZE], initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biase)
# if train == 1: fc1 = tf.nn.dropout(fc1, 0.5)
with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable("weight", [FC_SIZE, NUM_LABELS], initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', regularizer(fc1_weights))
fc2_biase = tf.get_variable('biase', [NUM_LABELS], initializer=tf.constant_initializer(0.1))
logit = tf.matmul(fc1, fc2_weights) + fc2_biase
return logit
2.训练代码 mnist_train.py
# -- coding: utf-8 --
import os
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
#数据batch大小
BATCH_SIZE = 100
#训练参数
LEARNING_RATE_BASE = 0.02
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE= 0.0001
TRAINING_STEPS = 80000
MOVING_AVERAGE_DECAY = 0.99
#模型保存路径及文件名
MODEL_SAVE_PATH = "/model2/"
MODEL_NAME = "model.ckpt"
def train(mnist):
#输入层和数据label
# x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
x = tf.placeholder(tf.float32, [BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS], name='x-input')
y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
#前向传播结果y
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = mnist_inference.inference(x, 1 ,regularizer)
global_step = tf.Variable(0, trainable=False)
#滑动平均模型
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
#计算交叉熵,并加入正则-->损失函数loss
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
# loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
loss = cross_entropy_mean
#学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
#train_step 梯度下降(学习率,损失函数,全局步数)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
#运算图控制,用train_op作集合
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
#持久化
saver = tf.train.Saver()
with tf.Session() as sess:
tf.initialize_all_variables().run()
for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
reshaped_xs = np.reshape(xs, (BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS))
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x:reshaped_xs, y_:ys})
#每1000轮保存一次
if i%1000 == 0:
print("After %d training step(s), loss on training batch is %g " %(step, loss_value))
saver.save(sess, "./model/model.ckpt")
def main(argv=None):
mnist = input_data.read_data_sets("mnist_data/", one_hot=True)
train(mnist)
if __name__== '__main__':
tf.app.run()