#!/usr/bin/python#這是一個很經典的cnn 入門教程了import tensorflow as tf import sys from tensorflow.examples.tutorials.mnist import input_data#定以權重變量，初始狀態是一個隨機數 #https://blog.csdn.net/u013713117/article/details/65446361/ #tf.truncated_normal 截斷正太分布，下面函數中隨機數取自（0-0.1×標準差，0+0.1×標準差） #用截斷正太分布的原因應該是避免有些奇異值導致某些神經元不工作def weight_variable(shape):initial = tf.truncated_normal(shape, stddev=0.1)return tf.Variable(initial)#bias 采用0.1的常數 def bias_variable(shape):initial = tf.constant(0.1, shape=shape)return tf.Variable(initial)#二維卷積，x是輸入，W是卷積核的參數， 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')mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)sess = tf.InteractiveSession()x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10])W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10]))W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32])#數據的輸入是28*28的矩陣x_image = tf.reshape(x, [-1, 28, 28, 1])#在這個函數下,W_conv1 = weight_variable([5, 5, 1, 32]) #表示卷積核的大小是5*5，因為圖像是灰度圖只有一個通道，32表示有32個卷積核 #對于stride=1*1的卷積，并且padding=SAME,那么卷積后的圖像和卷積前的圖像，有相同的shape,conv1的shape是28*28*32 h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) #由于池化層的stride 是2*2，padding=SAME,那么每池化一次，shape降低一半，pool1的shape是14*14*32 h_pool1 = max_pool_2x2(h_conv1)W_conv2 = weight_variable([5, 5, 32, 64]) b_conv2 = bias_variable([64])#輸入層pool1層，對pool1層進行一次卷積，pool1層 的shape是14*14*32，conv2的shape也是14*14*64 h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2)# Now image size is reduced to 7*7#pool2的shape是7*7*64 W_fc1 = weight_variable([7 * 7 * 64, 1024]) b_fc1 = bias_variable([1024])h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])print(h_pool2_flat.shape) print(W_fc1.shape) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)print(h_fc1.shape)keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) print(h_fc1_drop.shape) W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)print(y_conv.shape)cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv)) train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) sess.run(tf.initialize_all_variables())for i in range(20000):batch = mnist.train.next_batch(50)if i%100 == 0:train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})print ("step %d, training accuracy %.3f"%(i, train_accuracy))train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})print ("Training finished")print ("test accuracy %.3f" % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

總結

以上是生活随笔為你收集整理的tensorflow 进阶(四)---CNN的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。