[Fix] Fix the bug of large seg map IoU calculation #534
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
Codecov Report
@@ Coverage Diff @@
## master #534 +/- ##
=======================================
Coverage 86.79% 86.80%
=======================================
Files 101 101
Lines 5249 5252 +3
Branches 848 848
=======================================
+ Hits 4556 4559 +3
Misses 533 533
Partials 160 160
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
sennnnn
changed the title
aravind-h-v
pushed a commit
to aravind-h-v/mmsegmentation
that referenced
this pull request
Mar 27, 2023
* pytorch only schedulers * fix style * remove match_shape * pytorch only ddpm * remove SchedulerMixin * remove numpy from karras_ve * fix types * remove numpy from lms_discrete * remove numpy from pndm * fix typo * remove mixin and numpy from sde_vp and ve * remove remaining tensor_format * fix style * sigmas has to be torch tensor * removed set_format in readme * remove set format from docs * remove set_format from pipelines * update tests * fix typo * continue to use mixin * fix imports * removed unsed imports * match shape instead of assuming image shapes * remove import typo * update call to add_noise * use math instead of numpy * fix t_index * removed commented out numpy tests * timesteps needs to be discrete * cast timesteps to int in flax scheduler too * fix device mismatch issue * small fix * Update src/diffusers/schedulers/scheduling_pndm.py Co-authored-by: Patrick von Platen <[email protected]>
|
sennnnn seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
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.
This PR is realated to #523.
Problem statement
torch.histcmay meet a trouble when inputting large size seg map.torch.histcmay only be able to count 2^24. When pixels of single class exceed 2^24,torch.histccan't count exceeded part.Fix
We change
torch.histctotorch.bincountwhen counting pixels of each class.Others
torch.bincountcan only support 1-d non-negative integral inputs. Besides, the inference speed oftorch.bincountis slower thantorch.histc