Tensorflow
文章平均质量分 90
ef-eve
这个作者很懒,什么都没留下…
展开
-
Tensorflow 变量
name_scope与variable_scope import tensorflow as tf with tf.name_scope("a_name_scope"): 无reuse initializer = tf.constant_initializer(value=1) var1 = tf.get_variable(name='var原创 2017-07-14 21:58:58 · 272 阅读 · 0 评论 -
Tensorflow Save
保存为四个文件: my-model.ckpt.meta my-model.ckpt.data-* my-model.ckpt.index checkpoint 图结构.meta与变量值.ckpt分离 from __future__ import print_function import tensorflow as tf import numpy as np原创 2017-07-14 21:52:34 · 471 阅读 · 0 评论 -
tf.scatter_update tf.scatter_sub
tf.scatter_update/sub原创 2017-08-10 20:21:06 · 1789 阅读 · 1 评论 -
tf.train.exponential_decay的用法
tf.train.exponential_decay(learning_rate, global_, decay_steps, decay_rate, staircase=True/False)import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt; learning_rate = 0.1转载 2017-08-10 21:31:32 · 561 阅读 · 0 评论