import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 # 输入节点 OUTPUT_NODE = 10 # 输出节点 LAYER1_NODE = 500 # 隐藏层数 BATCH_SIZE = 100 # 每次batch打包的样本个数 # 模型相关的参数 LEARNING_RATE_BASE = 0.8 LEARNING_RATE_DECAY = 0.99 REGULARAZTION_RATE = 0.0001 TRAINING_STEPS = 5000 MOVING_AVERAGE_DECAY = 0.99 def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2): # 不使用滑动平均类 if avg_class == None: layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1) return tf.matmul(layer1, weights2) + biases2 else: # 使用滑动平均类 layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1)) return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2) def train(mnist): x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input') y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input') # 生成隐藏层的参数。 weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1)) biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE])) # 生成输出层的参数。 weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1)) biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE])) # 计算不含滑动平均类的前向传播结果 y = inference(x, None, weights1, biases1, weights2, biases2) # 定义训练轮数及相关的滑动平均类 global_step = tf.Variable(0, trainable=False) variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step) variables_averages_op = variable_averages.apply(tf.trainable_variables()) average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2) # 计算交叉熵及其平均值 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) # 损失函数的计算 regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE) regularaztion = regularizer(weights1) + regularizer(weights2) loss = cross_entropy_mean + regularaztion # 设置指数衰减的学习率。 learning_rate = tf.train.exponential_decay( LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY, staircase=True) # 优化损失函数 train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step) # 反向传播更新参数和更新每一个参数的滑动平均值 with tf.control_dependencies([train_step, variables_averages_op]): train_op = tf.no_op(name='train') # 计算正确率 correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # 初始化会话，并开始训练过程。 with tf.Session() as sess: tf.global_variables_initializer().run() validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels} test_feed = {x: mnist.test.images, y_: mnist.test.labels} # 循环的训练神经网络。 for i in range(TRAINING_STEPS): if i % 1000 == 0: validate_acc = sess.run(accuracy, feed_dict=validate_feed) print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc)) xs,ys=mnist.train.next_batch(BATCH_SIZE) sess.run(train_op,feed_dict={x:xs,y_:ys}) test_acc=sess.run(accuracy,feed_dict=test_feed) print(("After %d training step(s), test accuracy using average model is %g" %(TRAINING_STEPS, test_acc))) def main(argv=None): mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True) train(mnist) if __name__=='__main__': main()
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): # 定义输入输出placeholder。 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) # 定义损失函数、学习率、滑动平均操作以及训练过程。 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) train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step) with tf.control_dependencies([train_step, variables_averages_op]): train_op = tf.no_op(name='train') # 初始化TensorFlow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}) 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("../../../datasets/MNIST_data", one_hot=True) train(mnist) if __name__ == '__main__': main()
import time import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_inference import mnist_train # 加载的时间间隔。 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} 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: ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: saver.restore(sess, ckpt.model_checkpoint_path) 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("../../../datasets/MNIST_data", one_hot=True) evaluate(mnist) if __name__ == '__main__': main()
