Tensorflow训练MNIST模型持久化

mnist_inference.py

# -*- coding: utf-8 -*-
import tensorflow as tf

'''
mnist_inference.py 定义前向传播过程和神经网络参数
'''

# 神经网络结构参数
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

# 通过tf.get_variable函数获取变量
def get_weight_var(shape, regularizer):
  weights = tf.get_variable(
      "weights", shape,
      initializer=tf.truncated_normal_initializer(stddev=0.1))
  
  # 将正则化损失加入名为losses的集合
  if regularizer != None:
    tf.add_to_collection('losses', regularizer(weights))
    
  return weights

# 定义前向传播过程
def inference(input_tensor, regularizer):
  # 第一层神经网络
  with tf.variable_scope('layer1'):
    weights = get_weight_var([INPUT_NODE, LAYER1_NODE], regularizer)
    biases = tf.get_variable(
        "biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
    layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
    
  # 第二层神经网络
  with tf.variable_scope('layer2'):
    weights = get_weight_var([LAYER1_NODE, OUTPUT_NODE], regularizer)
    biases = tf.get_variable(
        "biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
    layer2 = tf.matmul(layer1, weights) + biases
    
  return layer2

mnist_train.py

# -*- coding: utf-8 -*-
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference

'''
mnist_train.py 定义神经网络的训练过程
'''

# 配置神经网络参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVG_DECAY = 0.99

# 模型保存的路径和文件名
MODEL_SAVE_PATH = '/content/saved_model/'
MODEL_NAME = 'model.ckpt'

def train(mnist):
  # 定义输入输出
  x = tf.placeholder(
      tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
  y_ = tf.placeholder(
      tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')

  # 前向传播
  regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
  y = mnist_inference.inference(x, regularizer)
  
  global_step = tf.Variable(0, trainable=False)
  
  # 滑动平均操作
  var_averages = tf.train.ExponentialMovingAverage(
      MOVING_AVG_DECAY, global_step)
  var_averages_op = var_averages.apply(tf.trainable_variables())
  
  # 定义损失函数
  cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
      logits=y, labels=tf.argmax(y_, 1))
  cross_entropy_mean = tf.reduce_mean(cross_entropy)
  loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
  
  # 定义学习率
  learning_rate = tf.train.exponential_decay(
      LEARNING_RATE_BASE,
      global_step,
      mnist.train.num_examples / BATCH_SIZE,
      LEARNING_RATE_DECAY)
  
  # 定义优化算法
  train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(
      loss, global_step=global_step)
  
  # 反向传播同时更新神经网络参数及其滑动平均值
  with tf.control_dependencies([train_step, var_averages_op]):
    train_op = tf.no_op(name='train')
    
  # 初始化tf持久化类
  saver = tf.train.Saver()
  with tf.Session() as sess:
    tf.global_variables_initializer().run()
    
    for i in range(TRAINING_STEPS):
      xs, ys = mnist.train.next_batch(BATCH_SIZE)
      _, loss_value, step = sess.run(
          [train_op, loss, global_step], feed_dict={x:xs, y_:ys})
      
      # 每1000轮保存一次模型
      if i % 1000 == 0:
        print("After %d training step(s), loss on training batch "
             "is %g." % (step, loss_value))
        saver.save(sess,
                   os.path.join(MODEL_SAVE_PATH, MODEL_NAME),
                   global_step=global_step)
        
        
def main(argv=None):
  mnist = input_data.read_data_sets("/tmp/data", one_hot=True)
  train(mnist)
  
if __name__ == '__main__':
  tf.app.run()

mnist_eval.py

# -*- coding: utf-8 -*-
import tensorflow as tf
import time

from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train

'''
mnist_eval.py 定义模型的测试过程
'''

# 每10s加再一次最新的模型，测试准确率
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
  with tf.Graph().as_default() as g:
    x = tf.placeholder(
      tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
    y_ = tf.placeholder(
      tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
    validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}

    # 前向传播，正则化项为None
    y = mnist_inference.inference(x, None)

    # 计算正确率
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(
      tf.cast(correct_prediction, tf.float32))

    # 通过变量重命名来加载模型
    var_averages = tf.train.ExponentialMovingAverage(
      mnist_train.MOVING_AVG_DECAY)
    var_to_restore = var_averages.variables_to_restore()
    saver = tf.train.Saver(var_to_restore)
        
    # 每隔一段时间检验一次正确率
    while True:
      with tf.Session() as sess:
        ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
        
        if ckpt and ckpt.model_checkpoint_path:
          # 加载模型
          saver.restore(sess, ckpt.model_checkpoint_path)
          
          # 通过文件名获取模型保存时的训练轮数
          global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
          accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
          print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))

        else:
          print("No checkpoint file found!")
          return

        time.sleep(EVAL_INTERVAL_SECS)

def main(argv=None):
  mnist = input_data.read_data_sets("/tmp/data", one_hot=True)
  evaluate(mnist)

if __name__ == '__main__':
  tf.app.run()

以上。

Tensorflow训练MNIST模型持久化

猜你喜欢