Fixes bug with optional features encoder #220
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 logic in `train.py` was to use a separate features encoder module if:
- features are present in the datamodule
- the model requires features to be separate from source (e.g., pointer-generators)
- and a separate features encoder module is requested.
This is incorrect; the logic should read:
- features are present in the datamodule, and
- a separate features encoder module is requested, or
- the model requires features to be separate from source
In the case where the model requires it but a specific features encoder module is not specified, we use the same module as the source encoder; e.g., a pointer-generator LSTM will have an LSTM source encoder and an LSTM features encoder.
The README was also out of date: the flags are `--source_encoder_arch` and `--features_encoder_arch` (was missing the `_arch` part).
|
This is now thoroughly tested so I'm submitting. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 logic in
train.pywas to use a separate features encoder module if:This is incorrect; the logic should read:
- a separate features encoder module is requested, or
- the model requires features to be separate from source.
In the case where the model requires it but a specific features encoder module is not specified, we use the same module as the source encoder; e.g., a pointer-generator LSTM will have an LSTM source encoder and an LSTM features encoder.
The README was also out of date: the flags are
--source_encoder_archand--features_encoder_arch(was missing the_archpart).