This repository has been archived by the owner on Jul 1, 2023. It is now read-only.
Improve RNN cell abstraction. #86
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The existing `RNNCell` protocol and `RNNInput` type are not flexible in that each time step has the take both the previous output and the hidden state. This PR lifts that restriction. * Rename `RNNInput` to `RNNCellInput` so that it's more accurate. * Add a new `RNNCellOutput` generic structure type that stores an output and a state. * Add associated type `State` in `RNNCell`. * Make the `Output` type of `RNNCell` be `RNNOutput<TimeStepOutput, State>`. Thanks @superbobry for the suggestions.
|
@superbobry @tanmayb123 @eaplatanios Please review when you get a chance. |
|
Thanks Richard! This looks good to me. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The existing
RNNCellprotocol andRNNInputtype are not flexible in that each time step has the take both the previous output and the hidden state. This PR lifts that restriction.RNNInputtoRNNCellInputso that it's more accurate.RNNCellOutputgeneric structure type that stores an output and a state.StateinRNNCell.Outputtype ofRNNCellbeRNNOutput<TimeStepOutput, State>.Thanks @superbobry for the suggestions.