python实现RNN/LSTM

最新推荐文章于 2025-06-09 23:40:42 发布

原创最新推荐文章于 2025-06-09 23:40:42 发布 · 839 阅读

1 ·

CC 4.0 BY-SA版权

该博客探讨了如何使用Python中的长短期记忆（LSTM）网络进行手写数字识别，通过实例展示了RNN/LSTM在图像识别任务中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

用LSTM实现手写图片的数字识别

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

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

lr = 0.001
training_iters = 100000
batch_size = 128

n_inputs = 28  # 输入的是每一行有28个像素
n_steps = 28  # 一共有28行，图片28x28
n_hidden_units = 128
n_classes = 10  # 10分类

x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

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, ]))
}


def rnn(x_input, weights_input, biases_input):
    x = tf.reshape(x_input, [-1, n_inputs])
    x_in = tf.matmul(x, weights_input['in'] + biases_input['in'])
    x_in = tf.reshape(x_in, [-1, n_steps, n_hidden_units])

    lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
    _init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)

    outputs, states = tf.nn.dynamic_rnn(lstm_cell, x_in, initial_state=_init_state, time_major=False)

    results = tf.matmul(states[1], weights_input['out']) + biases_input['out']
    return results


pred = rnn(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=pred))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    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