# -*- coding: utf-8 -*- #实现的神经网络共有三层,输入层有 784 个神经元,隐藏层与输出层分别有 500 和 10 个神经元。这所以这样设计是因为 MNIST 的像素为 28×28=784,所以每一个输入神经元对应于一个灰度像素点。批量大小为 100并使用学习率衰减的情况下迭代 10000 步能得到 98.34% 的测试集准确度, import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data #加载MNIST数据集 mnist = input_data.read_data_sets("./data/MNIST/", one_hot=True) INPUT_NODE = 784 OUTPUT_NODE = 10 LAYER1_NODE = 500 BATCH_SIZE = 100 # 模型相关的参数 LEARNING_RATE_BASE = 0.8 LEARNING_RATE_DECAY = 0.99 REGULARAZTION_RATE = 0.0001 TRAINING_STEPS = 10000 MOVING_AVERAGE_DECAY = 0.99 def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2): # 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: 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) # 定义交叉熵损失函数加上正则项为模型损失函数 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) # 随机梯度下降优化器优化损失函数,使用梯度下降优化器来优化权重。然而,TensorFlow 中还有很多优化器,最常用的是 GradientDescentOptimizer、AdamOptimizer 和 AdaGradOptimizer。 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') # 计算准确度 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} # 循环地训练神经网络。 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))) avg_class = None train(mnist)
TF之DNN:TF利用 784 个神经元的三层全连接的神经网络DNN对MNIST手写数字识别实现98%准确率——Jason niu
猜你喜欢
转载自blog.csdn.net/qq_41185868/article/details/80279242
今日推荐
周排行