可和這篇文章對(duì)比：https://blog.csdn.net/fanzonghao/article/details/81603367

# coding: utf-8 # ## MNIST數(shù)據(jù)集from __future__ import division, print_function, absolute_importimport tensorflow as tf# Import MNIST data，MNIST數(shù)據(jù)集導(dǎo)入 from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)# In[2]:# Hyper-parameters，超參數(shù) learning_rate = 0.001 num_steps = 500 batch_size = 128 display_step = 10# Network Parameters，網(wǎng)絡(luò)參數(shù) num_input = 784 # MNIST數(shù)據(jù)輸入 (img shape: 28*28) num_classes = 10 # MNIST所有類別 (0-9 digits) dropout = 0.75 # Dropout, probability to keep units，保留神經(jīng)元相應(yīng)的概率# tf Graph input，TensorFlow圖結(jié)構(gòu)輸入 X = tf.placeholder(tf.float32, [None, num_input]) Y = tf.placeholder(tf.float32, [None, num_classes]) keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)，保留i# In[3]:# Create some wrappers for simplicity，創(chuàng)建基礎(chǔ)卷積函數(shù)，簡化寫法 def conv2d(x, W, b, strides=1):# Conv2D wrapper, with bias and relu activation，卷積層，包含bias與非線性relu激勵(lì)x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')x = tf.nn.bias_add(x, b)return tf.nn.relu(x)def maxpool2d(x, k=2):# MaxPool2D wrapper，最大池化層return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],padding='SAME')# Create model，創(chuàng)建模型 def conv_net(x, weights, biases, dropout):# MNIST數(shù)據(jù)為維度為1，長度為784 (28*28 像素)的# Reshape to match picture format [Height x Width x Channel]# Tensor input become 4-D: [Batch Size, Height, Width, Channel]x = tf.reshape(x, shape=[-1, 28, 28, 1])# Convolution Layer，卷積層conv1 = conv2d(x, weights['wc1'], biases['bc1'])# Max Pooling (down-sampling)，最大池化層／下采樣conv1 = maxpool2d(conv1, k=2)# Convolution Layer，卷積層conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])# Max Pooling (down-sampling)，最大池化層／下采樣conv2 = maxpool2d(conv2, k=2)# Fully connected layer，全連接網(wǎng)絡(luò)# Reshape conv2 output to fit fully connected layer input，調(diào)整conv2層輸出的結(jié)果以符合全連接層的需求fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])fc1 = tf.nn.relu(fc1)# Apply Dropout，應(yīng)用dropoutfc1 = tf.nn.dropout(fc1, dropout)# Output, class prediction，最后輸出預(yù)測out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])return out# In[4]:# Store layers weight & bias 存儲(chǔ)每一層的權(quán)值和全差 weights = {# 5x5 conv, 1 input, 32 outputs'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),# 5x5 conv, 32 inputs, 64 outputs'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),# fully connected, 7*7*64 inputs, 1024 outputs'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),# 1024 inputs, 10 outputs (class prediction)'out': tf.Variable(tf.random_normal([1024, num_classes])) }biases = {'bc1': tf.Variable(tf.random_normal([32])),'bc2': tf.Variable(tf.random_normal([64])),'bd1': tf.Variable(tf.random_normal([1024])),'out': tf.Variable(tf.random_normal([num_classes])) }# Construct model，構(gòu)建模型 logits = conv_net(X, weights, biases, keep_prob) prediction = tf.nn.softmax(logits)# Define loss and optimizer，定義誤差函數(shù)與優(yōu)化器 loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y)) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) train_op = optimizer.minimize(loss_op)# Evaluate model，評(píng)估模型 correct_pred = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))# Initialize the variables (i.e. assign their default value)，初始化圖結(jié)構(gòu)所有變量 init = tf.global_variables_initializer()# In[5]:# Start training，開始訓(xùn)練 with tf.Session() as sess:# Run the initializer，初始化sess.run(init)for step in range(1, num_steps+1):batch_x, batch_y = mnist.train.next_batch(batch_size)# Run optimization op (backprop)，優(yōu)化sess.run(train_op, feed_dict={X: batch_x, Y: batch_y, keep_prob: dropout})if step % display_step == 0 or step == 1:# Calculate batch loss and accuracyloss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x,Y: batch_y,keep_prob: 1.0})print("Step " + str(step) + ", Minibatch Loss= " +?????????????????? "{:.4f}".format(loss) + ", Training Accuracy= " +?????????????????? "{:.3f}".format(acc))print("Optimization Finished!")# Calculate accuracy for 256 MNIST test images，以每256個(gè)測試圖像為例，print("Testing Accuracy:",???????? sess.run(accuracy, feed_dict={X: mnist.test.images[:256],Y: mnist.test.labels[:256],keep_prob: 1.0}))

總結(jié)

以上是生活随笔為你收集整理的两层卷积网络实现手写数字的识别（基于tensorflow）的全部內(nèi)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(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。