[Fix] Fix the bug that when all pixels in an image is ignored, the ac… #1336
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
…curacy calculation raises ZeroDivisionError
MeowZheng
reviewed
Mar 1, 2022
Codecov Report
@@ Coverage Diff @@
## master #1336 +/- ##
==========================================
+ Coverage 90.26% 90.32% +0.06%
==========================================
Files 131 132 +1
Lines 7611 7702 +91
Branches 1264 1290 +26
==========================================
+ Hits 6870 6957 +87
Misses 531 531
- Partials 210 214 +4
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
MeowZheng
approved these changes
Mar 8, 2022
MeowZheng
approved these changes
Mar 8, 2022
MengzhangLI
approved these changes
Mar 8, 2022
Junjun2016
reviewed
Mar 9, 2022
mmseg/models/losses/accuracy.py
Outdated
| @@ -46,10 +46,13 @@ def accuracy(pred, target, topk=1, thresh=None, ignore_index=None): | |||
| correct = correct & (pred_value > thresh).t() | |||
| correct = correct[:, target != ignore_index] | |||
| res = [] | |||
| eps = 1e-6 | |||
There was a problem hiding this comment.
Should we use eps in torch.finfo?
https://pytorch.org/docs/stable/type_info.html?highlight=finfo#torch.torch.finfo
There was a problem hiding this comment.
Please also refer to https://discuss.pytorch.org/t/torch-epsilon/30497.
Junjun2016
approved these changes
Mar 9, 2022
Merged
mob5566
pushed a commit
to mob5566/mmsegmentation
that referenced
this pull request
Apr 13, 2022
open-mmlab#1336) * [Fix] Fix the bug that when all pixels in an image is ignored, the accuracy calculation raises ZeroDivisionError * use eps * all close * add ignore test * add eps
ZhimingNJ
pushed a commit
to AetrexTechnology/mmsegmentation
that referenced
this pull request
Jun 29, 2022
open-mmlab#1336) * [Fix] Fix the bug that when all pixels in an image is ignored, the accuracy calculation raises ZeroDivisionError * use eps * all close * add ignore test * add eps
aravind-h-v
pushed a commit
to aravind-h-v/mmsegmentation
that referenced
this pull request
Mar 27, 2023
* Add heun * Finish first version of heun * remove bogus * finish * finish * improve * up * up * fix more * change progress bar * Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py * finish * up * up * up
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.
…curacy calculation raises ZeroDivisionError
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Fix the bug that when all pixels in an image is ignored, the accuracy computation raises ZeroDivisionError
Modification
Fix the bug that when all pixels in an image is ignored, the accuracy computation raises ZeroDivisionError