TensorFlow - Defining the shape of a variable dynamically, depending on the shape of another variable

Question

Say I have a certain the Tensor x whose dimensions are not defined upon graph initialization.

I can get its shape using:

x_shape = tf.shape(input=x)

Now if I want to create a variable based on the values defined in x_shape using:

y = tf.get_variable(variable_name="y", shape=[x_shape[0], 10])

I get an error, since the values passed to the argument shape must be int and not Tensor. How can I create such a dynamically shaped variable without using placeholders?

Answer 1

I'm running out of time so this is quick and dirty, but maybe it helps you to get to your solution... It's based on this (dynamic size for tf.zeros) but extends the idea to tf.Variables. Since your variable needs to be initialized anyway - I choose 0s...

import tensorflow as tf
I1_ph = tf.placeholder(name = "I1",shape=(None,None,None),dtype=tf_dtype)

zerofill = tf.fill(tf.shape(I1_ph), 0.0)
myVar = tf.Variable(0.0)
updateMyVar = tf.assign(myVar,zerofill,validate_shape=False)

res, = sess.run([updateMyVar], { I1_ph:np.zeros((1,2,2)) } )
print ("dynamic variable shape",res.shape)

res, = sess.run([updateMyVar], { I1_ph:np.zeros((3,5,2)) } )
print ("dynamic  variable shape",res.shape)

Answer 2

You can use x.get_shape():

y = tf.get_variable('y', shape=[x.get_shape()[0], 10])