Tensorflow cannot initialize tf.Variable for dynamic batch size

Question

I tried creating a tf.Variable with a dynamic shape. The following outlines the problem.

Doing this works.

init_bias = tf.random_uniform(shape=[self.config.hidden_layer_size, tf.shape(self.question_inputs)[0]])

However, when i try to do this:

init_bias = tf.Variable(init_bias)

It throws the error ValueError: initial_value must have a shape specified: Tensor("random_uniform:0", shape=(?, ?), dtype=float32)

Just come context (question input is a placeholder which dynamic batch ):

self.question_inputs = tf.placeholder(tf.int32, shape=[None, self.config.qmax])

It seems like putting a dynamic value into random uniform gives shape=(?,?) which gives an error with tf.Variable.

Thanks and appreciate any help!

user1523170 · Accepted Answer · 2016-10-14 14:55:22Z

11

This should work:

init_bias = tf.Variable(init_bias,validate_shape=False)

If validate_shape is False, tensorflow allows the variable to be initialized with a value of unknown shape.

However, what you're doing seems a little strange to me. In tensorflow, Variables are generally used to store weights of a neural net, whose shape remains fixed irrespective of the batch size. Variable batch size is handled by passing a variable length tensor into the graph (and multiplying/adding it with a fixed shape bias Variable).

answered Oct 14, 2016 at 14:55

user1523170

3934 silver badges9 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

minhle_r7 Over a year ago

I found an use case in preloading data: tensorflow.org/programmers_guide/reading_data#preloaded_data. You might want to feed different datasets of different sizes.

dexhunter Over a year ago

I still get an error

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder' with dtype int32  [[Node: Placeholder = Placeholder[dtype=DT_INT32, shape=[], device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Collectives™ on Stack Overflow

Tensorflow cannot initialize tf.Variable for dynamic batch size

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related