基于tensortflow的多层感知机模型

'''
A Multilayer Perceptron implementation example using TensorFlow library.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''

from __future__ import print_function

# Import MNIST data   数据导入
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

import tensorflow as tf

# Parameters
learning_rate = 0.001   #学习率
training_epochs = 15    # 训练次数
batch_size = 100        
display_step = 1

# Network Parameters
n_hidden_1 = 256 # 1st layer number of features  第一层的神经元个数
n_hidden_2 = 256 # 2nd layer number of features  第二层的神经元个数
n_input = 784 # MNIST data input (img shape: 28*28)  数据输入的大小
n_classes = 10 # MNIST total classes (0-9 digits)    分类结果

# tf Graph input  设置占位符
x = tf.placeholder("float", [None, n_input])     
y = tf.placeholder("float", [None, n_classes])


# Create model  定义模型
def multilayer_perceptron(x, weights, biases):
    # Hidden layer with RELU activation
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    layer_1 = tf.nn.relu(layer_1)
    # Hidden layer with RELU activation
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    layer_2 = tf.nn.relu(layer_2)
    tf.summary.histogram('layer_2',layer_2)  #  
    # Output layer with linear activation
    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
    tf.summary.histogram('out_layer', out_layer)
    return out_layer

# Store layers weight & bias 定义权重、偏置
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# Construct model
pred = multilayer_perceptron(x, weights, biases)

# Define loss and optimizer  定义损失、优化器
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
tf.summary.scalar("cost", cost)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()
summaries = tf.summary.merge_all()
# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    summary_writer = tf.summary.FileWriter('/logs', sess.graph)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch
        summary_str = sess.run(summaries, feed_dict={x: batch_x, y: batch_y})
        summary_writer.add_summary(summary_str, i)
    # Display logs per epoch step  # 每隔一步打印一次
        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", \
                "{:.9f}".format(avg_cost))
    print("Optimization Finished!")

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))