卷积网络
为了避免过拟合现象的发生,我们在实际应用时,往往不会将原始图片直接喂入全连接网络,会先对原始图片进行特征提取,把提取到的特征喂给全连接网络
卷积便是一种有效提取图片特征的方法
输出图片边长= (输入图片边长-卷积核长+1)/步长
有时候会在输入图片周围进行全0填充,这样可以保证输出图片的尺寸和输入图片一致
池化分为最大池化和均值池化
dropout可以有效减少过拟合
Lenet5卷积神经网络模型
LeNet-5:是Yann LeCun在1998年设计的用于手写数字识别的卷积神经网络,当年美国大多数银行就是用它来识别支票上面的手写数字的,它是早期卷积神经网络中最有代表性的实验系统之一。LenNet-5共有7层(2个卷积层、2个下抽样层(池化层)、3个全连接层),每层都包含不同数量的训练参数
mnist_lenet5_backward.py
# coding:utf-8 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_lenet5_forward import os import numpy as np BATCH_SIZE = 100 LEARNING_RATE_BASE = 0.005 LEARNING_RATE_DECAY = 0.99 REGULARIZER = 0.0001 STEPS = 50000 MOVING_AVERAGE_DECAY = 0.99 MODEL_SAVE_PATH = "./model/" MODEL_NAME = "mnist_model" def backward(mnist): x = tf.placeholder(tf.float32, [ BATCH_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.NUM_CHANNELS]) y_ = tf.placeholder(tf.float32, [None, mnist_lenet5_forward.OUTPUT_NODE]) y = mnist_lenet5_forward.forward(x, True, REGULARIZER) global_step = tf.Variable(0, trainable=False) ce = tf.nn.sparse_softmax_cross_entropy_with_logits( logits=y, labels=tf.argmax(y_, 1)) cem = tf.reduce_mean(ce) loss = cem + 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) ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step) ema_op = ema.apply(tf.trainable_variables()) with tf.control_dependencies([train_step, ema_op]): train_op = tf.no_op(name='train') saver = tf.train.Saver() with tf.Session() as sess: init_op = tf.global_variables_initializer() sess.run(init_op) ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: saver.restore(sess, ckpt.model_checkpoint_path) for i in range(STEPS): xs, ys = mnist.train.next_batch(BATCH_SIZE) reshaped_xs = np.reshape(xs, ( BATCH_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.NUM_CHANNELS)) _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={ x: reshaped_xs, y_: ys}) if i % 100 == 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(): mnist = input_data.read_data_sets("./data/", one_hot=True) backward(mnist) if __name__ == '__main__': main()
mnist_lenet5_forward.py# coding:utf-8 import tensorflow as tf IMAGE_SIZE = 28 NUM_CHANNELS = 1 #灰度图,所以通道数是1 #卷积核个数和卷积核大小 CONV1_SIZE = 5 CONV1_KERNEL_NUM = 32 CONV2_SIZE = 5 CONV2_KERNEL_NUM = 64 FC_SIZE = 512 OUTPUT_NODE = 10 def get_weight(shape, regularizer): w = tf.Variable(tf.truncated_normal(shape, stddev=0.1)) if regularizer != None: tf.add_to_collection( 'losses', tf.contrib.layers.l2_regularizer(regularizer)(w)) return w def get_bias(shape): b = tf.Variable(tf.zeros(shape)) return b def conv2d(x, w): return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME') def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') def forward(x, train, regularizer): #给出前向传播的网络结构 conv1_w = get_weight( [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_KERNEL_NUM], regularizer) conv1_b = get_bias([CONV1_KERNEL_NUM]) conv1 = conv2d(x, conv1_w) relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_b)) pool1 = max_pool_2x2(relu1) conv2_w = get_weight( [CONV2_SIZE, CONV2_SIZE, CONV1_KERNEL_NUM, CONV2_KERNEL_NUM], regularizer) conv2_b = get_bias([CONV2_KERNEL_NUM]) conv2 = conv2d(pool1, conv2_w) relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_b)) pool2 = max_pool_2x2(relu2) 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]) fc1_w = get_weight([nodes, FC_SIZE], regularizer) fc1_b = get_bias([FC_SIZE]) fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_w) + fc1_b) if train: fc1 = tf.nn.dropout(fc1, 0.5) fc2_w = get_weight([FC_SIZE, OUTPUT_NODE], regularizer) fc2_b = get_bias([OUTPUT_NODE]) y = tf.matmul(fc1, fc2_w) + fc2_b return y
mnist_lenet5_test.py# coding:utf-8 import time import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_lenet5_forward import mnist_lenet5_backward import numpy as np TEST_INTERVAL_SECS = 5 def test(mnist): with tf.Graph().as_default() as g: x = tf.placeholder(tf.float32, [ mnist.test.num_examples, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.NUM_CHANNELS]) y_ = tf.placeholder( tf.float32, [None, mnist_lenet5_forward.OUTPUT_NODE]) y = mnist_lenet5_forward.forward(x, False, None) ema = tf.train.ExponentialMovingAverage( mnist_lenet5_backward.MOVING_AVERAGE_DECAY) ema_restore = ema.variables_to_restore() saver = tf.train.Saver(ema_restore) correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) while True: with tf.Session() as sess: ckpt = tf.train.get_checkpoint_state( mnist_lenet5_backward.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] reshaped_x = np.reshape(mnist.test.images, ( mnist.test.num_examples, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.IMAGE_SIZE, mnist_lenet5_forward.NUM_CHANNELS)) accuracy_score = sess.run( accuracy, feed_dict={x: reshaped_x, y_: mnist.test.labels}) print("After %s training step(s), test accuracy = %g" % (global_step, accuracy_score)) else: print('No checkpoint file found') return time.sleep(TEST_INTERVAL_SECS) def main(): mnist = input_data.read_data_sets("./data/", one_hot=True) test(mnist) if __name__ == '__main__': main()
复现已有的卷积神经网络
代码
https://github.com/cj0012/AI-Practice-Tensorflow-Notes/tree/master/vgg
人工智能实践:Tensorflow笔记(五):卷积网络基础与实践
最新推荐文章于 2020-02-01 19:26:25 发布