Skip to content
This repository was archived by the owner on Oct 31, 2025. It is now read-only.

Conversation

@sunvod
Copy link
Contributor

@sunvod sunvod commented Oct 24, 2021

Add capabilities for LSTM layer:

  1. getting a complete state RNN (c, h) from the stack as input instead to use a zero initialization . Use initial_state=True parameter for that. Default False.
  2. putting a complete state RNN (c, h) in the stack as output instead to discard it. Use return_state=True parameter for that . Default False.

Add capability for  LSTN layer:
1) getting a complete state RNN (c, h) from the stack as input instead to use a zero initialization . Use initial_state=True parameter for that. Default False.
2) putting a complete state RNN (c, h) in the stack as output instead to discard it. Use return_state=True parameter for that . Default False.
@google-cla google-cla bot added the cla: yes label Oct 24, 2021
@sunvod sunvod changed the title Update rnn.py Update LRTM layer Oct 24, 2021
@sunvod sunvod changed the title Update LRTM layer Update LSTM layer Oct 24, 2021
@sunvod sunvod changed the title Update LSTM layer Update LSTM layer for e.g. seq2seq models Oct 24, 2021
@sunvod sunvod changed the title Update LSTM layer for e.g. seq2seq models Update LSTM layer for e.g. seq2seq based models Oct 24, 2021
@sunvod sunvod changed the title Update LSTM layer for e.g. seq2seq based models Update LSTM layer Oct 24, 2021
@sunvod sunvod changed the title Update LSTM layer Update LSTM layer by adding more capabilities Oct 24, 2021
@afrozenator afrozenator added the ready to pull Added when the PR is ready to be merged. label Oct 25, 2021
@copybara-service copybara-service bot merged commit cf657f0 into google:master Oct 25, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

cla: yes ready to pull Added when the PR is ready to be merged.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants