Tensorflow: How to get a tensor by name?

Question

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

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

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')

But that is giving me an error:

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

But this works:

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

I can get around this with

return S3_conv1,regularizer, S1_conv1

but I don’t want to do that.

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?

Asked By: protas

||

Source

Answer 1

All tensors have string names which you can see as follows

[tensor.name for tensor in tf.get_default_graph().as_graph_def().node]

Once you know the name you can fetch the Tensor using <name>:0 (0 refers to endpoint which is somewhat redundant)

For instance if you do this

tf.constant(1)+tf.constant(2)

You have the following Tensor names

[u'Const', u'Const_1', u'add']

So you can fetch output of addition as

sess.run('add:0')

Note, this is part not part of public API. Automatically generated string tensor names are an implementation detail and may change.

Answered By: Yaroslav Bulatov

Answer 2

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)

Answered By: apfalz

Answer 3

All you gotta do in this case is:

ft=tf.get_variable('scale1/Scale1_first_relu:0')

Answered By: Kislay Kunal

Answer 4

Or simpler still, infer it from the corresponding .pbtxt file that comes with the model .pb file. Since it depends on the model, every case is different.

Answered By: Kris Stern

Tensorflow: How to get a tensor by name?

Question:

Answers: