モウtensorflowノート(二)CNN
7179 ワード
構造:
1、convolutional layer1 + max pooling; 2、convolutional layer2 + max pooling; 3、fully connected layer1 + dropout; 4、fully connected layer2 to prediction.
コード:
出力:Extracting Mnist_data/train-images-idx3-ubyte.gz Extracting Mnist_data/train-labels-idx1-ubyte.gz Extracting Mnist_data/t10k-images-idx3-ubyte.gz Extracting Mnist_data/t10k-labels-idx1-ubyte.gz 0.097 0.707 0.853 0.869 0.896 0.906 0.907 0.927 0.931 0.938 0.934 0.933 0.945 0.948 0.953 0.953 0.962 0.951 0.963 0.964
1、convolutional layer1 + max pooling; 2、convolutional layer2 + max pooling; 3、fully connected layer1 + dropout; 4、fully connected layer2 to prediction.
コード:
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Aug 18 11:33:43 2017
@author: xiaolian
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('Mnist_data', one_hot = True)
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict = {xs : v_xs, keep_prob : 1})
correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy, feed_dict = {xs : v_xs, ys : v_ys, keep_prob : 1})
return result
# define weight
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev = 0.1)
return tf.Variable(initial)
# define biases
def bias_variable(shape):
initial = tf.constant(0.1, shape = shape)
return tf.Variable(initial)
# cov2d [1, 1]
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = 'SAME')
# max_pool
def max_poo_2x2(x):
return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME')
# define placeholder for inputting data
xs = tf.placeholder(tf.float32, [None, 784])
ys = tf.placeholder(tf.float32, [None, 10])
# define placeholder for dropout
keep_prob = tf.placeholder(tf.float32)
# nn ,-1
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# patch 5x5 ,channel is 1 , output 32 featuremap
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
# structure is 28x28x32
h_cov1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
# structure is 14x14x32
h_pool1 = max_poo_2x2(h_cov1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
# structure is 14x14x64
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
# structure is 7x7x64
h_pool2 = max_poo_2x2(h_conv2)
# full connection
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# add dropout
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# last layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
# softmax
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# define loss
cross_entropy = tf.reduce_mean( - tf.reduce_sum(ys * tf.log(prediction), reduction_indices = [1]) )
train_step = tf.train.AdamOptimizer( 1e-4 ).minimize( cross_entropy )
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict = {xs : batch_xs, ys : batch_ys, keep_prob : 0.5})
if i % 50 == 0:
print(compute_accuracy(mnist.test.images[:1000], mnist.test.labels[:1000]))
出力:Extracting Mnist_data/train-images-idx3-ubyte.gz Extracting Mnist_data/train-labels-idx1-ubyte.gz Extracting Mnist_data/t10k-images-idx3-ubyte.gz Extracting Mnist_data/t10k-labels-idx1-ubyte.gz 0.097 0.707 0.853 0.869 0.896 0.906 0.907 0.927 0.931 0.938 0.934 0.933 0.945 0.948 0.953 0.953 0.962 0.951 0.963 0.964