restructure embeddings to avoid issues with torch jit #634
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Outdated suggestions cannot be applied.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.
I restructured the embeddings to avoid problems with torch jit.
Nuclear and electronic embeddings are separated, because electronic embeddings currently require
(embedding, inputs)
as arguments in the forward pass and nuclear embeddings only requireatomic_numbers
in the forward pass.With this, we can further use
torch.nn.Embedding
as a default value and electronic embeddings can be added asnn.ModuleList
.This is still a draft and not tested!