Add vocabulary object. Model loading infers RNN size. #38
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
Only works for 1-layer RNNs for now, but should load any file.
Make sure no words are just duplicated during generation
Sasafrass
approved these changes
Jul 18, 2021
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
Co-authored-by: Sasafrass <36883067+Sasafrass@users.noreply.github.com>
This was referenced Jul 18, 2021
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Outdated suggestions cannot be applied.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.
#26 Vocabulary object implemented. Vocabulary is assumed to be loaded from a text file. Multiple models can share the same vocabulary. It should therefore be sorted, so no weird mismatches happen.
It is checked during loading of a model whether vocabulary is the same size.
#31 Model loading now inferns the RNN size from the current architecture. For future architectures, such as multiple layers, we should make sure this still happens.