Added modules for embedding head #378
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
added 2 commits
November 4, 2024 06:40
mosheraboh
reviewed
Nov 11, 2024
| @@ -150,3 +151,149 @@ def __init__( | |||
| def forward(self, x: Tensor) -> Tensor: | |||
| x = self.classifier(x) | |||
| return x | |||
|
|
|||
|
|
|||
| class EncoderEmbeddingOutputHead(nn.Module): | |||
There was a problem hiding this comment.
Lets rename to something more general.
Maybe SequenceEmbeddingHead?
There was a problem hiding this comment.
EncoderEmbeddingOutputHead is mainly a placeholder code for when I start using the actual head for tasks. It works, but I still need to plan how to use it, given all our use cases. I suggest we leave this for now, and I'll incorporate your comments into next PRs of this.
Right now, I'm only using ModularPooling1D.
| num_classes=num_classes, | ||
| ).classifier | ||
|
|
||
| if pooling is not None: |
There was a problem hiding this comment.
Does it make sense that pooling will be None. Isn't it the whole point?
| embedding_size: int, | ||
| layers: List[int], | ||
| dropout: float, | ||
| num_classes: int, |
There was a problem hiding this comment.
Why do we need num_classes here? Maybe ClassifierMLP allows to skip this layer?
mosheraboh
previously approved these changes
Nov 11, 2024
mosheraboh
approved these changes
Nov 11, 2024
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Outdated suggestions cannot be applied.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.
No description provided.