[feat] add intervention methods for multi-target learning #49
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
tiankongdeguiji
requested changes
Nov 29, 2024
| import torch | ||
| from torch import nn | ||
|
|
||
| class RotateLayer(nn.Module): |
There was a problem hiding this comment.
add unit test for these module in intervention_test.py
|
|
||
|
|
||
|
|
||
| class DC2VR(MultiTaskRank): |
There was a problem hiding this comment.
add model test in dc2vr_test.py
tiankongdeguiji
requested changes
Nov 29, 2024
| class Intervention(nn.Module): | ||
| def __init__(self, | ||
| base_dim,source_dim, | ||
| low_rank_dim,orth=True): |
There was a problem hiding this comment.
the orth param has no effect?
| base_dim, | ||
| low_rank_dim): | ||
| super().__init__() | ||
| # n > m |
There was a problem hiding this comment.
base_dim must greater than low_rank_dim?
assert base_dim > low_rank_dim
| // intervention tower names | ||
| repeated string intervention_tower_names = 8; | ||
| // low_rank_dim | ||
| required uint32 low_rank_dim = 9; |
There was a problem hiding this comment.
Is it possible for us to assign a distinct low_rank_dim to each tower?
| self.base_rotate_layer = torch.nn.utils.parametrizations.orthogonal(base_rotate_layer) | ||
| source_rotate_layer = RotateLayer(source_dim, low_rank_dim) | ||
| self.source_rotate_layer = torch.nn.utils.parametrizations.orthogonal(source_rotate_layer) | ||
| self.dropout = torch.nn.Dropout(0.1) |
There was a problem hiding this comment.
dropout rate can be configurable?
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Outdated suggestions cannot be applied.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.