Join GitHub today
GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.Sign up
Crash when use VariationalAutoEncoder with Bidirectional LSTM but not with unidirectional LSTM #5472
The program will crash when using VariationalAutoEncoder with Bidirectional LSTM(or GravesLSTM),
The following is the code for test:
When using Bidirectional LSTM, the following exception will be thrown:
Thank you very much for help, and really sorry for late reply.
I isolated the code from my original project.
Also, I found more information during create this demo project.
Hope above project and observation can help for solve the problem.
Thanks for reporting, and thanks for the repo that helped me to reproduce the issue.
A few hours after that PR has been merged, you will be able to access the fix using snapshots, as described here: https://deeplearning4j.org/snapshots