Tensorflow:如何按名称获取张量?

问题描述

我无法按名称恢复张量，我什至不知道是否可行.

I'm having trouble recovering a tensor by name, I don't even know if it's possible.

我有一个创建图表的函数:

I have a function that creates my graph:

def create_structure(tf, x, input_size,dropout):
 with tf.variable_scope("scale_1") as scope:
  W_S1_conv1 = deep_dive.weight_variable_scaling([7,7,3,64], name='W_S1_conv1')
  b_S1_conv1 = deep_dive.bias_variable([64])
  S1_conv1 = tf.nn.relu(deep_dive.conv2d(x_image, W_S1_conv1,strides=[1, 2, 2, 1], padding='SAME') + b_S1_conv1, name="Scale1_first_relu")
.
.
.
return S3_conv1,regularizer

我想在这个函数之外访问变量 S1_conv1.我试过了:

I want to access the variable S1_conv1 outside this function. I tried:

with tf.variable_scope('scale_1') as scope_conv:
 tf.get_variable_scope().reuse_variables()
 ft=tf.get_variable('Scale1_first_relu')

但这给了我一个错误:

ValueError: Under-sharing: Variable scale_1/Scale1_first_relu 不存在，不允许.您的意思是在 VarScope 中设置重用=无吗?

ValueError: Under-sharing: Variable scale_1/Scale1_first_relu does not exist, disallowed. Did you mean to set reuse=None in VarScope?

但这有效:

with tf.variable_scope('scale_1') as scope_conv:
 tf.get_variable_scope().reuse_variables()
 ft=tf.get_variable('W_S1_conv1')

我可以解决这个问题

return S3_conv1,regularizer, S1_conv1

但我不想那样做.

我认为我的问题是 S1_conv1 并不是一个真正的变量，它只是一个张量.有没有办法做我想做的事?

I think my problem is that S1_conv1 is not really a variable, it's just a tensor. Is there a way to do what I want?

推荐答案

有一个函数 tf.Graph.get_tensor_by_name().例如:

There is a function tf.Graph.get_tensor_by_name(). For instance:

import tensorflow as tf

c = tf.constant([[1.0, 2.0], [3.0, 4.0]])
d = tf.constant([[1.0, 1.0], [0.0, 1.0]])
e = tf.matmul(c, d, name='example')

with tf.Session() as sess:
    test =  sess.run(e)
    print e.name #example:0
    test = tf.get_default_graph().get_tensor_by_name("example:0")
    print test #Tensor("example:0", shape=(2, 2), dtype=float32)

这篇关于Tensorflow:如何按名称获取张量?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！