tensorflow学习（4) MNIST数据集 +2层神经网络

前言：前一次学习用了逻辑回归的方法，准确率大概0.91。这次采用2层神经网络，迭代20次，但是准确率不太高。input_data在上一篇有。

#!/usr/bin/env python
# -*- coding:utf-8 -*-
#@Time  : 2018/12/10 23:36
#@Author: little bear
#@File  : tf_neuralnetwork.py

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

mnist = input_data.read_data_sets('data/', one_hot=True)

n_hidden_1 = 256 #两层神经网络，256  128 个神经元，一个全连接输出层
n_hidden_2 = 128
n_input = 784
n_classes = 10

# INPUTS AND OUTPUTS
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

# NETWORK PARAMETERS
stddev = 0.1  #高斯初始化方差0.1
# 字典的方式
weights = {
    'w1': tf.Variable(tf.random_normal([n_input, n_hidden_1], stddev=stddev)),
    'w2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], stddev=stddev)),
    'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes], stddev=stddev))
}
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]))
}
print("NETWORK READY")

# 接上激活函数
def multilayer_perceptron(_X, _weights, _biases):
    layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X, _weights['w1']), _biases['b1']))
    layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, _weights['w2']), _biases['b2']))
    return (tf.matmul(layer_2, _weights['out']) + _biases['out'])

# PREDICTION 计算预测值
pred = multilayer_perceptron(x, weights, biases)

# LOSS AND OPTIMIZER  计算损失值
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))   #采用交叉熵的方法计算损失值，再取平均（降维到1维）
optm = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(cost) #采用梯度下降法
corr = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))    # 得出预测正确率
accr = tf.reduce_mean(tf.cast(corr, "float"))

# INITIALIZER
init = tf.global_variables_initializer()
print ("FUNCTIONS READY")

#  正式运行
training_epochs = 20
batch_size      = 100
display_step    = 4
# LAUNCH THE GRAPH
sess = tf.Session()
sess.run(init)
# OPTIMIZE
for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = int(mnist.train.num_examples/batch_size)
    # ITERATION
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        feeds = {x: batch_xs, y: batch_ys}
        sess.run(optm, feed_dict=feeds)
        avg_cost += sess.run(cost, feed_dict=feeds)
    avg_cost = avg_cost / total_batch
    # DISPLAY
    if (epoch+1) % display_step == 0: # 每四次迭代打印一次
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        feeds = {x: batch_xs, y: batch_ys}
        train_acc = sess.run(accr, feed_dict=feeds)
        print ("TRAIN ACCURACY: %.3f" % (train_acc))
        feeds = {x: mnist.test.images, y: mnist.test.labels}
        test_acc = sess.run(accr, feed_dict=feeds)
        print ("TEST ACCURACY: %.3f" % (test_acc))
print ("OPTIMIZATION FINISHED")