图像融合代码

原文地址：mnist,AE

在mnist数据集上使用CNN网络：

#!/usr/bin/python
import tensorflow as tf
import sys
from tensorflow.examples.tutorials.mnist import input_data


def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)


def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)


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])


x_image = tf.reshape(x, [-1, 28, 28, 1])


h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)


W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([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
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])


h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)


keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)


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)




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}))

AE算法：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

# 导入MNIST数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False)

learning_rate = 0.01
training_epochs = 10
batch_size = 256
display_step = 1
examples_to_show = 10
n_input = 784

# tf Graph input (only pictures)
X = tf.placeholder("float", [None, n_input])

# 用字典的方式存储各隐藏层的参数
n_hidden_1 = 256 # 第一编码层神经元个数
n_hidden_2 = 128 # 第二编码层神经元个数
# 权重和偏置的变化在编码层和解码层顺序是相逆的
# 权重参数矩阵维度是每层的 输入*输出，偏置参数维度取决于输出层的单元数
weights = {
    'encoder_h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'encoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'decoder_h1': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_1])),
    'decoder_h2': tf.Variable(tf.random_normal([n_hidden_1, n_input])),
}
biases = {
    'encoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'encoder_b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'decoder_b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'decoder_b2': tf.Variable(tf.random_normal([n_input])),
}

# 每一层结构都是 xW + b
# 构建编码器
def encoder(x):
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['encoder_h1']),
                                   biases['encoder_b1']))
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['encoder_h2']),
                                   biases['encoder_b2']))
    return layer_2


# 构建解码器
def decoder(x):
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(x, weights['decoder_h1']),
                                   biases['decoder_b1']))
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['decoder_h2']),
                                   biases['decoder_b2']))
    return layer_2

# 构建模型
encoder_op = encoder(X)
decoder_op = decoder(encoder_op)

# 预测
y_pred = decoder_op
y_true = X

# 定义代价函数和优化器
cost = tf.reduce_mean(tf.pow(y_true - y_pred, 2)) #最小二乘法
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)

with tf.Session() as sess:
    # tf.initialize_all_variables() no long valid from
    # 2017-03-02 if using tensorflow >= 0.12
    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        init = tf.initialize_all_variables()
    else:
        init = tf.global_variables_initializer()
    sess.run(init)
    # 首先计算总批数，保证每次循环训练集中的每个样本都参与训练，不同于批量训练
    total_batch = int(mnist.train.num_examples/batch_size) #总批数
    for epoch in range(training_epochs):
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)  # max(x) = 1, min(x) = 0
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={X: batch_xs})
        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c))
    print("Optimization Finished!")

    encode_decode = sess.run(
        y_pred, feed_dict={X: mnist.test.images[:examples_to_show]})
    f, a = plt.subplots(2, 10, figsize=(10, 2))
    for i in range(examples_to_show):
        a[0][i].imshow(np.reshape(mnist.test.images[i], (28, 28)))
        a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))
    plt.show()