【Tensorflow】最佳時間樣例程序_MNIST數字識別問題

• 以下爲mnist_inference.py。

import tensorflow as tf
# 定義相關參數
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
#通過tf.get_variable獲取變量
def get_weight_variable(shape,regularizer):
	weights = tf.get_variable("weight",shape,
		initializer=truncated_normal_initilizer(stddev=0.1))
	#add_to_collection函數將新生成變量的L2正則化損失項加入集合
	if regularizer !=  None:
		tf.add_to_collection('losses',regularizer(weights))
	return weights
#定義神經網絡的前向傳播過程
def inference(input_tensor,regularizer):
	#聲明第一層神經網絡的變量並完成前向傳播過程
	with tf.variable_scope('layer1'):
		weights=get_weight_variable(
			[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)
	#聲明第二層
	 with tf.variable_scope('layer2'):
  		weights=get_weight_variable(
   			[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

• 以下爲mnist_train.py。

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

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH="MNIST_model/"
MODEL_NAME="mnist_model"

def train(mnist):
	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')
	
	regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
	y = mnist_inference.inference(x, regularizer)
	global_step = tf.Variable(0, trainable=False) # 存儲訓練輪數
	
	#定義損失函數、學習率、滑動平均操作以及訓練過程
	variable_averages = tf.train.ExponentialMovingAverage(
		MOVING_AVERAGE_DECAY, global_step)
	variables_averages_op = variable_averages.apply(
		tf.trainable_variables())
	
	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'))
	learning_rate = tf.train.exponential_decay(
		LEARNING_RATE_BASE,global_step,
		mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
		staircase=True)
	# 使用以下算法來優化損失函數（交叉熵損失和L2正則化損失）
	train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
	#同時完成通過反向傳播更新參數和更新每個參數的滑動平均值。
	#等價於：train_op=tf.group(train_step,variables_averages_op)
	#返回的是操作，不是值
	with tf.control_dependencies([train_step, variables_averages_op]):
        	train_op = tf.no_op(name='train')
         
         # 初始化TensorFlow持久化類
	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})
			if i % 1000 == 0:
				print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
				#保存當前模型。用到了global_step參數，這樣可以讓每個
				#被保存的模型文件名末尾加上訓練的輪數
				#如“model.ckpt_1000”表示訓練1000輪之後得到的模型
				saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
#主程序入口
def main(argv=None):
	mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
	train(mnist)
if __name__ == '__main__':
	main()

• 訓練程序mnist_eval.py

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train

#每10秒加載一次最新的模型，並在測試數據上測試最新模型的正確率。
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
	with tf.Graph().as_default() as g:
		#定義輸入輸出的格式
		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}
	
	y = mnist_inference.inference(x, None)

	correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
	accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

	variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
	variables_to_restore = variable_averages.variables_to_restore()
	saver = tf.train.Saver(variables_to_restore)

	while True:
		with tf.Session() as sess:
			#下面函數會通過checkpoint文件自動找到目錄中最新模型文件名
			ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
			if ckpt and ckpt.model_checkpoint_path:
				#加載模型
				saver.restore(sess, ckpt.model_checkpoint_path)
				#通過文件名得到模型保存時的迭代輪數
				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)
#主程序
def main(argv=None):
	mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
	evaluate(mnist)
if __name__ == '__main__':
	main()