tensorflow实现简单神经网络对mnist数据集操作

我的这个简单神经网络包括两个中间隐层，激励函数用的是sigmoid

首先需要导入必要的包：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

然后获取mnist数据集：通过mnist下的一个input_data.read_data_sets

mnist = input_data.read_data_sets('data/', one_hot=True)
#此处注意one_hot需要指定，不然在后边在进行矩阵运算时会报错
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10

定义一些参数，包括两个隐层和输入的特征个数，以及分类个数（10）

n_hidden_1 =256
n_hidden_2 = 128
n_input = 784
n_classes = 10

#定义x,y
x = tf.placeholder(tf.float32,[None,n_input])
y = tf.placeholder(tf.float32,[None,n_classes])

stddev = 0.1
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]))
}

定义前向传播函数：（有关什么是前向传播和反向传播相关知识请看这里：）https://mp.youkuaiyun.com/postedit/80849187

def forward_propagation(_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'])

预测

pred = forward_propagation(x,weights,biases)

通过交叉熵来定义损失函数：，优化器（采用梯度下降）:交叉熵概念请看：https://mp.youkuaiyun.com/postedit/80858789

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits= pred,labels= y))
optimizer = tf.train.GradientDescentOptimizer(0.3)
train = optimizer.minimize(cost)
corr = tf.equal(tf.arg_max(pred,1),tf.arg_max(y,1))
accr = tf.reduce_mean(tf.cast(corr,'float'))

init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
    train_epochs = 6
    batch_size = 64
    train_step = 2
    avg_cost = 0
    for epoch in range(train_epochs):
        num_batch = int(mnist.train.num_examples/batch_size)+1
        batch_example,batch_label = mnist.train.next_batch(batch_size)
        
        print(batch_label.shape,batch_example.shape)
        for i in range(num_batch):
            feed_seed = {x:batch_example,y:batch_label}
            sess.run(train,feed_dict=feed_seed)

            avg_cost += sess.run(cost,feed_dict=feed_seed)
        avg_cost = avg_cost/num_batch
        if (epoch+1) % train_step ==0：
            feed_train = {x:batch_example,y:batch_label}
            feed_test = {x:test_img,y:test_label}


            print('train accr:%f'%sess.run(accr,feed_dict=feed_train))
            print('test accr:%f'%sess.run(accr,feed_dict=feed_test))
            print('avg_cost:%f'%avg_cost)