TensorFlow(五)——MNIST分类值RNN

最新推荐文章于 2020-02-12 13:38:16 发布

MVincent

最新推荐文章于 2020-02-12 13:38:16 发布

阅读量251

点赞数

分类专栏： tensorflow 文章标签： tensorflow

本文链接：https://blog.csdn.net/MRxjh/article/details/82669510

版权

tensorflow 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

import input_data
import tensorflow as tf
import numpy as np

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

#设置训练超参数
lr = 0.001
training_iters = 100000
batch_size = 128

#设置神经网络参数
n_inputs = 28 #输入层的n
n_steps = 28
n_hidden_units = 128
n_classes = 10

#输入数据占位符
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

#定义权重
weights = {
    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
    'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
    'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}

#定义RNN模型
def RNN(X, weights, biases):
    
    #转化输入的X==>(128 batch * 28 steps, 28 inputs)
    X = tf.reshape(X, [-1, n_inputs])
    
    #进入隐藏层
    X_in = tf.matmul(X, weights['in']) + biases['in']
    X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])
    
    #采用LSTM
    lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units, forget_bias=1.0, 
                                            state_is_tuple=True)
    init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)
    
    outputs, final_state = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=init_state, time_major=False)
    
    results = tf.matmul(final_state[1], weights['out']) + biases['out']
    return results

#定义损失函数和优化器
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

#定义模型预测结果和评价方法
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    step = 0
    while step * batch_size < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
        sess.run([train_op], feed_dict={
            x: batch_xs,
            y: batch_ys,
        })
        if step % 20 == 0:
            print (sess.run(accuracy, feed_dict={
                x: batch_xs,
                y: batch_ys,
            }))
        step += 1

结果：