By Glau


2016-10-20 13:33:10 8 Comments

I have my input state with shape = (84,84,4)

state = Input(shape=(84,84,4), dtype="float")

It's stacked sequence of continuous frames.

I want to pass this state to the keras model as input, firstly - to TimeDistributed layers and then - to LSTM

as I understand, time step is the first dimension and I need to reshape my state appropriately to

shape=(4, 84, 84)

and holds the frames in their own size and topology

1 comments

@jean 2016-10-20 13:39:28

state_t=tf.transpose(state,[2,1,0])

Is this what you are looking for ?
(or [2,0,1] that depends on what you wanna do...)

Related Questions

Sponsored Content

3 Answered Questions

[SOLVED] Understanding Keras LSTMs

1 Answered Questions

1 Answered Questions

Query about the input output shape of LSTM in Keras

  • 2019-02-14 21:45:09
  • Suman
  • 67 View
  • 0 Score
  • 1 Answer
  • Tags:   keras lstm

1 Answered Questions

[SOLVED] keras tensor reshaping (lstm input shape error)

1 Answered Questions

1 Answered Questions

1 Answered Questions

[SOLVED] How to feed into LSTM with 4 dimensional input?

1 Answered Questions

[SOLVED] Keras- LSTM- Input Size Error

1 Answered Questions

[SOLVED] Keras: reshape to connect lstm and conv

Sponsored Content