TensorArray Initialization from another tensor

Question

What is the right way to initialize a tensorarray from another tensor in tensorflow.

Suppose I have a tensor

T1 

TensorArr = tf.TensorArray(tf.int32, 1, dynamic_size=True)

What is way to say that this tensorarray depends on T1? Looking at the documentation I cant figure out how to initialize this.

Correct me if my understanding is wrong, T1 is a nested tensor and I want to loop over a dimension using tf.while_loop and hence I want to initialize the TensorArray with it.

Ola R · Accepted Answer · 2018-03-14 10:05:45Z

1

In documentation for raw_rnn, they use

inputs_ta = tf.TensorArray(dtype=tf.float32, size=max_time)
inputs_ta = inputs_ta.unstack(inputs)

inputs is a tensor with shape: (max_time,batch_size,num_hidden). Hope this helps.

answered Mar 14, 2018 at 10:05

Ola R

584 bronze badges

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

Collectives™ on Stack Overflow

TensorArray Initialization from another tensor

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related