This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 2.5k
agnostic-regression for bbox #390
Merged
Merged
Changes from all commits
Commits
Show all changes
21 commits
Select commit
Hold shift + click to select a range
f93b369
make pixel indexes 0-based for bounding box in pascal voc dataset
zimenglan-sysu-512 45e4ba8
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 86caae2
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 a46bfb9
replacing all instances of torch.distributed.deprecated with torch.di…
zimenglan-sysu-512 7bbf46f
replacing all instances of torch.distributed.deprecated with torch.di…
zimenglan-sysu-512 7c8cf41
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 07a0f9c
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 6f09a6f
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 c4e3245
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 baba31f
add GroupNorm
zimenglan-sysu-512 4877e36
add GroupNorm -- sort out yaml files
zimenglan-sysu-512 d4ae039
use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' an…
zimenglan-sysu-512 333864d
modification on 'group_norm' and 'conv_with_kaiming_uniform' function
zimenglan-sysu-512 58da4d5
modification on yaml files in configs/gn_baselines/ and reduce the am…
zimenglan-sysu-512 1798e63
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 ecc68c4
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 02a86f3
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 9808a21
use 'kaiming_uniform' to initialize resnet, disable gn after fc layer…
zimenglan-sysu-512 d1ce06e
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 4de3488
agnostic-regression for bbox
zimenglan-sysu-512 52be8d7
Merge remote-tracking branch 'upstream/master'
zimenglan-sysu-512 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is how Detectron implements it: by using 0 for background and 1 for the other classes.
But I'm starting to wonder if this is actually necessary here: given that we index out all negative examples via
sampled_pos_inds_subset
, we don't backprop through the background elements anyway.Given that, I think we could have only
num_bbox_reg_classes = 1
, and the rest of the code should work as well.@rbgirshick what do you think? Am I missing something here?