This repository has been archived by the owner on Mar 19, 2021. It is now read-only.
Add a scalar weight classifier #18
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
twuebi
reviewed
Jan 7, 2020
twuebi
reviewed
Jan 7, 2020
| // | ||
| // stack the layers to get a single tensor of shape: | ||
| // [batch_size, sequence_len, n_layers, layer_size] | ||
| let layers = Tensor::stack(&layers, 2); |
There was a problem hiding this comment.
How does stack compare to a for loop?
There was a problem hiding this comment.
Good question! In the big picture, these differences will not be visible, since the encoder dominates things time-wise. But we could benchmark this in isolation. I will create an issue to write a criterion bench for this. We could then replace it by a for-loop if it is faster.
twuebi
reviewed
Jan 7, 2020
danieldk
force-pushed
the
scalar-weight
branch
from
528c609 to
4b89e42
Compare
twuebi
approved these changes
Jan 7, 2020
danieldk
force-pushed
the
scalar-weight
branch
from
4b89e42 to
2a0acd1
Compare
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Outdated suggestions cannot be applied.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.
No description provided.