LeNet-5结构写Mnist识别(Tensorflow)
来源:互联网 发布:多益网络校园招聘 编辑:程序博客网 时间:2024/06/08 05:21
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 = 28NUM_CHANNELS = 1NUM_LABELS = 10#第一个卷积层的尺寸和深度CONV1_DEEP = 32CONV1_SIZE = 5#第二个卷积层的尺寸和深度CONV2_DEEP = 64CONV2_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 osimport numpy as npimport 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()
阅读全文
1 0
- LeNet-5结构写Mnist识别(Tensorflow)
- tensorflow 卷积神经网络 LeNet-5模型 MNIST手写体数字识别
- 81、Tensorflow实现LeNet-5模型,多层卷积层,识别mnist数据集
- 理解mnist识别特征(lenet)
- 基于tensorflow和mnist的LeNet-5模型实现
- TensorFlow MNIST LeNet 模型持久化
- Tensorflow学习:MNIST 识别
- Tensorflow MNIST 手写识别
- Tensorflow手写体识别mnist
- MNIST手写体识别--tensorflow
- TensorFlow实现Lenet-5
- tensorflow实现softma识别MNIST
- tensorflow实现KNN识别MNIST
- Tensorflow | MNIST手写字识别
- tensorflow-mnist手写数字识别
- 【TensorFlow】神经网络MNIST手写识别
- MNIST识别数字(TensorFlow框架)
- TensorFlow的MNIST数据识别
- springboot项目启动报警java.sql.SQLException:
- React Native关键字详解
- 登录、鉴权业务实践
- 代码创建UICollectionView(带分组header)
- I/O复用的场景
- LeNet-5结构写Mnist识别(Tensorflow)
- 图论第一次课
- Python自动化第四周
- idea cannot find declaration to go to
- WebPack使用流程小记
- 数据分析的统计学基础--相关及回归分析
- mysql alter
- 这么简单的道理,猩猩都懂,我们却忘了
- 回文质数