tensorflow rnn 最简单实现代码


tensorflow rnn 最简单实现代码


#!/usr/bin/env python
# -*- coding: utf-8 -*-


import tensorflow as tf
from tensorflow.contrib import rnn

import numpy as np

x=tf.placeholder(dtype=tf.float64,shape=[10,10,10],name="x")

train_x = np.ones(shape=[10, 10, 10], dtype=float)


cell=tf.nn.rnn_cell.BasicLSTMCell(10)


unstack_x = tf.unstack(x, 10, 1)

lstm_cell = rnn.BasicLSTMCell(10, forget_bias=1.0)

outputs, states = rnn.static_rnn(lstm_cell, unstack_x, dtype=tf.float64)

with tf.Session() as sess:
	sess.run(tf.global_variables_initializer())
	outputs_array=(sess.run(outputs,feed_dict={x:train_x}))

更多教程:http://www.tensorflownews.com/


免责声明!

本站转载的文章为个人学习借鉴使用,本站对版权不负任何法律责任。如果侵犯了您的隐私权益,请联系本站邮箱yoyou2525@163.com删除。



 
粤ICP备18138465号  © 2018-2025 CODEPRJ.COM