Skip to content

[Benchmark] Add BiSeNetV1 COCO-Stuff 164k benchmark #1019

New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Merged
merged 5 commits into from
Nov 17, 2021

Conversation

MengzhangLI
Copy link
Contributor

Uploading BiSeNetV1 model (R18, R50, R101) on Coco-Stuff 164k dataset.

Paper: https://arxiv.org/pdf/1808.00897.pdf
R18: 28.1(paper), 28.55(ours)
R101: 31.3(paper), 37.38(ours)

image

@MengzhangLI MengzhangLI self-assigned this Nov 8, 2021
@codecov
Copy link

codecov bot commented Nov 8, 2021

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 89.55%. Comparing base (6b3e550) to head (98abfec).
Report is 300 commits behind head on master.

Additional details and impacted files
@@           Coverage Diff           @@
##           master    #1019   +/-   ##
=======================================
  Coverage   89.55%   89.55%           
=======================================
  Files         119      119           
  Lines        6626     6626           
  Branches     1034     1034           
=======================================
  Hits         5934     5934           
  Misses        488      488           
  Partials      204      204           
Flag Coverage Δ
unittests 89.55% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@RockeyCoss
Copy link
Contributor

Please merge the master branch into your branch, thank you.

@Junjun2016 Junjun2016 changed the title [Benchmark] Uploading BiSeNetV1 on Coco-Stuff 164k [Benchmark] Add BiSeNetV1 COCO-Stuff 164k benchmark Nov 17, 2021
@Junjun2016 Junjun2016 requested a review from xvjiarui November 17, 2021 06:56
@xvjiarui xvjiarui merged commit e38eae3 into open-mmlab:master Nov 17, 2021
@MengzhangLI MengzhangLI deleted the bisenetv1_cocostuff164k branch February 1, 2022 03:17
bowenroom pushed a commit to bowenroom/mmsegmentation that referenced this pull request Feb 25, 2022
* bisenetv1 on cocostuff164k

* change config_names & delete redundant keys

* pretrain should before lr.

* remove redundancy in bisenetv1_r50-d32
aravind-h-v pushed a commit to aravind-h-v/mmsegmentation that referenced this pull request Mar 27, 2023
* k-diffusion-euler

* make style make quality

* make fix-copies

* fix tests for euler a

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* remove unused arg and method

* update doc

* quality

* make flake happy

* use logger instead of warn

* raise error instead of deprication

* don't require scipy

* pass generator in step

* fix tests

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update tests/test_scheduler.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove unused generator

* pass generator as extra_step_kwargs

* update tests

* pass generator as kwarg

* pass generator as kwarg

* quality

* fix test for lms

* fix tests

Co-authored-by: patil-suraj <surajp815@gmail.com>
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants