replace einsum() with other ops #118
Merged
Conversation
This file contains hidden or 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
|
nice pr~ |
ben15021999
pushed a commit
to ben15021999/YOLO-World
that referenced
this pull request
Jun 26, 2025
replace einsum() with other ops
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Outdated suggestions cannot be applied.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.
Since most edge devices don't support the op einsum(), I use some other normal ops to replace it. It outputs same results after my verification.
And I don't replacce einsum() in I-PoolingAttention cause it was banned in YOLO-WORLD v2.
Users can determine whether to use einsum() in config, by setting the variable
use_einsum:neck=dict(type='YOLOWorldPAFPN',guide_channels=text_channels,embed_channels=neck_embed_channels,num_heads=neck_num_heads,block_cfg=dict(type='MaxSigmoidCSPLayerWithTwoConv', use_einsum=False)),bbox_head=dict(type='YOLOWorldHead',head_module=dict(type='YOLOWorldHeadModule',use_bn_head=True,embed_dims=text_channels,num_classes=num_training_classes,use_einsum=False)),And It does NOT influence the raw outcome of YOLO-WORLD cause its default value is True.