[Fix] Fix loss parse in val_step #906
Merged
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
|
|
|
Hi @acdart |
Codecov Report
@@ Coverage Diff @@
## master #906 +/- ##
==========================================
+ Coverage 89.09% 89.33% +0.23%
==========================================
Files 112 112
Lines 6081 6083 +2
Branches 977 977
==========================================
+ Hits 5418 5434 +16
+ Misses 468 452 -16
- Partials 195 197 +2
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Junjun2016
reviewed
Sep 25, 2021
bowenroom
pushed a commit
to bowenroom/mmsegmentation
that referenced
this pull request
Feb 25, 2022
* [Fix] Fix loss parse in val_step * Add val_step unittest * Add train_step unittest
aravind-h-v
pushed a commit
to aravind-h-v/mmsegmentation
that referenced
this pull request
Mar 27, 2023
* ONNX supervised inpainting * sync with the torch pipeline * fix concat * update ref values * back to 8 steps * type fix * make fix-copies
wjkim81
pushed a commit
to wjkim81/mmsegmentation
that referenced
this pull request
Dec 3, 2023
* paf detector * add paf detector & head & loss * rename to PartAffinityField * rebase master * add paper ref * fix tab indent * update show * update heads * update heads * update paf head * update docstring * integrate get_multi_stage_outputs function for ae and paf * delete PAFParser * refactor ae * rm project2image in aggregate_scale * update head/init * update paf post-processing * fix docstring * fix docstring * fix config * add res50 config * add res50 config * fix bugs in paf generator * update paf flip * update paf group * update deconvhead * paf + head * fix config * update post-processing * fix bugs in flip paf * update unittest * add 'align_corners' in cfg * update refine * handle empty list * fix order * update pose filter * add openpose network * add openpose_v1 and openpose_v2 model * fix openpose v1 * rename stem to features for pre-trained vgg model loading * add openpose v1 v2 configs * add with_bg * allow different num_blocks and block_channels for different stages * remove redundant settings * update lightweight openpose * add lightopenpose config * update pretrained * update config * add neck & modify skeleton * rename addneck cfg * BottomUpGenerateHeatmapTarget pipeline with add_neck * BottomUpGenerateHeatmapTarget pipeline with add_neck * update addneck cfg * copy to keep self.coco unchanged * update pipeline with addneck * train paf wholebody * add bn * add bn * get add_neck on dataset * fix unittest * fix test with addneck * fix with bg * fix lightweight openpose with_bg=False * fix config * fix conv bias * fix with_bg config * fix paf * update config * gamma 0.333 * sgd config * fix MaskedMSELoss & add supervise_empty * fix add_neck * cfg of paf wholebody withbg + pretrain + supervise_empty * update lr * fix cfg * fix cfg * update configs * update configs * add configs * update configs * update configs * fix unittest * paf wholebody with hrnet/openposev2 backone * update cfg * add hourglass_ae model * add hourglass_ae model * add hourglass_ae model * update unittest * update hourglass * add select_output_index * supervise_empty=False * update batch size * resume from 50 epoch * hourglass wholebody coco pretrain * release resource limit * resume from 100ep * reduce workers_per_gpu * test multi-scale coco * delete paf * fix forward test * fix pytest * update batch size * update cfg Co-authored-by: jinsheng <jinsheng@sensetime.com> Co-authored-by: jin-s13 <jinsheng13@foxmail.com> Co-authored-by: 金晟 <SENSETIME\jinsheng@stit10.domain.sensetime.com>
sibozhang
pushed a commit
to sibozhang/mmsegmentation
that referenced
this pull request
Mar 22, 2024
* add json output for video demo * add json output for long_video_demo * add json output video demo
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.
Motivation
Add loss parse in val_step, so that logger can get loss value of validation dataset
Modification
add loss parse and format output dict in val_step function