Tflearn: Bug with GRU using 3d input

Created on 24 Feb 2017  路  3Comments  路  Source: tflearn/tflearn

I got this error when implementing GRU cell :

TypeError: Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32.

but when i use LSTM, it works like usual. Is there any idea what possibly happening with the code?

Most helpful comment

Can you try again with master version of TFLearn? It should be working.

pip install git+https://github.com/tflearn/tflearn.git

All 3 comments

Can you try again with master version of TFLearn? It should be working.

pip install git+https://github.com/tflearn/tflearn.git

@aymericdamien Thanks for the reply. I still got the same error message and only when i'm using the gru cell. What else that i should do?

i've found the solution for this problem, turns out i didn't upgrade the tensorflow to the latest version yet.

Was this page helpful?
0 / 5 - 0 ratings