Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Jump to bottom

Sync upstream #1

Merged
merged 29 commits into from
Apr 6, 2022
Merged

Sync upstream #1

merged 29 commits into from
Apr 6, 2022

Conversation

ashwinvaidya17
Copy link
Owner

Description

  • Provide a summary of the modification as well as the issue that has been resolved. List any dependencies that this modification necessitates.

  • Fixes # (issue)

Changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist

  • My code follows the pre-commit style and check guidelines of this project.
  • I have performed a self-review of my code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing tests pass locally with my changes

alexriedel1 and others added 29 commits February 24, 2022 10:46
@alexriedel1
c_idx cast to LongTensor in random sparse projection (#113)
fe665d2 
* c_idx cast to LongTensor in random sparse projection

* cast on creation

* black formatting
@samet-akcay
Update README.md
3d71cd1
@samet-akcay
Update README.md
fbc59da
@ashwinvaidya17
Update Nightly (#126)
64b2704 
* 🩹 fix checkpoint issue

* Backup multi-GPU test

* Backup thresholds

* Update thresholds + backup script for benchmarking

* Backup ganomaly thresholds

* Backup cflow and stfpm thresholds

* Fix all thresholds

* Update num categories to 3

* Fix pill threshold

* Fix tile  threshold

* Fix patchcore pill threshold

* Fix stfpm metal_nut threshold

* Add all close to tests

* Update cable threshold

* Update toothbrush

* Update transistor

* Update transistor

* Fix stfpm cable threshold

* Fix stfpm carpet threshold

* Add tolerance to file

* Change tox threshold + resturcture tests

* Restore benchmarking params

* Restore benchmarking params

* Update bottle threshold

* Update toothbrush threshold

* Update capsule  threshold

* Reduce thresholds + remove nncf tests

* Add badges to readme

Co-authored-by: Ashwin Vaidya <[email protected]>
@samet-akcay
Updated logos (#131)
20cbffa
@LeonidBeynenson @samet-akcay
Add third-party-programs.txt file and update license (#132)
aa49b7d 
* Add third-party-programs.txt file and update license

* Fix precommit warnings

* Update third-party-programs.txt

* Update README.md

Co-authored-by: Samet Akcay <[email protected]>
@ashwinvaidya17 @samet-akcay
🔨 Increase inference + openvino support (#122)
0d23715 
* 🔨 Increase inference + openvino support

* Rename fit_normality_model to model

* Address DFKDE comments

* Addressed DFM pytlint comments

Co-authored-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Samet Akcay <[email protected]>
@djdameln
Fix/da/image size bug (#135)
ee8807b 
* fix image size bug and add test case

* fix padim inference

* docstrings

* use dummy dataset for image size tests

* detach before moving to cpu
@djdameln
Fix/da/image size bug (#140)
8457809 
* fix image size bug and add test case

* fix padim inference

* docstrings

* use dummy dataset for image size tests

* detach before moving to cpu

* fix bug for non-square input images
@alexriedel1
optimize compute_anomaly_score by using torch native funcrtions (#141)
cebc3a4
@djdameln
Fix IndexError in adaptive threshold computation (#146)
5f3ee27 
* address scalar thresholds issue

* add tests for adaptive threshold metric
@samet-akcay
Feature/data/btad (#120)
539ee6b 
* renamed download-progress-bar as download

* added new download functions to init

* Added Btech data module

* Added btech tests

* Move split functions into a util module

* Modified mvtec

* added btech to get-datamodule

* fix typo in btech docstring

* update docstring

* cleanedup dataset download utils

* Address mypy

* modify config files and update readme.md

* Fix dataset path
@AlexanderDokuchaev
Update for nncf_task (#145)
834d45a 
* Update for nncf_task

* linter

* update nncf commit

* Rename CompressionCallback to OpenVINOCallback

* struct

* rename compression to openvino in config

* rm
@djdameln
fix non-adaptive thresholding bug (#152)
b66e5e3
@alexriedel1
Calculate feature map shape patchcore (#148)
b57e025 
* calculate feature map shape patchcore

* passed to wrong function

* unpack values from torch tensor directly

* get feature map shape before reshaping

* updating docstrings in patchcore

* fix line length

* w, h (too short) -> width, height

* typing torch.Size of feature_map_shape

* removing trailing whitespaces
@samet-akcay
Add transform config to yaml fil (#156)
2dfa0a7
@samet-akcay
Add Custom Dataset Training Support (#154)
b03fb32 
* renamed download-progress-bar as download

* added new download functions to init

* Added Btech data module

* Added btech tests

* Move split functions into a util module

* Modified mvtec

* added btech to get-datamodule

* fix typo in btech docstring

* update docstring

* cleanedup dataset download utils

* Address mypy

* modify config files and update readme.md

* Fix dataset path

* WiP: Created make_dataset function

* Renamed folder dataset into custom

* Added custom dataset tests

* updated config.yaml file to show custom dataset is available

* Added custom dataset to get_datamodule

* Address PR comments

* fix dataset path

* Debugging the ci

* Fixed folder dataset tests

* Added code quality checks back to the ci

* Added code coverage back to pre-merge tests
@samet-akcay
Added extension as an option when saving the result images. (#162)
3b85ce4 
* Added extension as an option when saving the result images.

* Added an extension check

* reverted visualizer callback

* Convert bmp images to png after downloading btech dataset.

* pylint

* ignore arguments differ
@samet-akcay
Update anomalib version and requirements (#163)
6829739 
* renamed download-progress-bar as download

* added new download functions to init

* Added Btech data module

* Added btech tests

* Move split functions into a util module

* Modified mvtec

* added btech to get-datamodule

* fix typo in btech docstring

* update docstring

* cleanedup dataset download utils

* Address mypy

* modify config files and update readme.md

* Fix dataset path

* WiP: Created make_dataset function

* Renamed folder dataset into custom

* Added custom dataset tests

* updated config.yaml file to show custom dataset is available

* Added custom dataset to get_datamodule

* Address PR comments

* fix dataset path

* Debugging the ci

* Fixed folder dataset tests

* Added code quality checks back to the ci

* Added code coverage back to pre-merge tests

* Do not import openvino at the top level. Cause some import issues when openvino is not install

* Move nncf to openvino-requirements.txt

* Move opencv to base requirements.txt/

* Added extension as an option when saving the result images.

* Added an extension check

* python verion 3.7

* Added opencv contrib python

* reverted visualizer callback

* Convert bmp images to png after downloading btech dataset.

* pylint

* ignore arguments differ

* Version to 0.2.5

* Ignore arguments-differ

* loosen pandas version

* import openvino with absolute import
@samet-akcay
Add torchtext==0.9.1 to support Kaggle environments. (#165)
8c1a04f 
* renamed download-progress-bar as download

* added new download functions to init

* Added Btech data module

* Added btech tests

* Move split functions into a util module

* Modified mvtec

* added btech to get-datamodule

* fix typo in btech docstring

* update docstring

* cleanedup dataset download utils

* Address mypy

* modify config files and update readme.md

* Fix dataset path

* WiP: Created make_dataset function

* Renamed folder dataset into custom

* Added custom dataset tests

* updated config.yaml file to show custom dataset is available

* Added custom dataset to get_datamodule

* Address PR comments

* fix dataset path

* Debugging the ci

* Fixed folder dataset tests

* Added code quality checks back to the ci

* Added code coverage back to pre-merge tests

* Do not import openvino at the top level. Cause some import issues when openvino is not install

* Move nncf to openvino-requirements.txt

* Move opencv to base requirements.txt/

* Added extension as an option when saving the result images.

* Added an extension check

* python verion 3.7

* Added opencv contrib python

* reverted visualizer callback

* Convert bmp images to png after downloading btech dataset.

* pylint

* ignore arguments differ

* Version to 0.2.5

* Ignore arguments-differ

* loosen pandas version

* import openvino with absolute import

* Added torchtext to requirements for kaggle support
@samet-akcay
Fix KeyError:'label' in classification folder dataset (#175)
c6fc4dd 
* Fix classification label bug in folder dataset

* bump black to 22.3.0

* bump black to 22.3.0

* format with new black
@samet-akcay
Added MVTec license to the repo (#177)
82ce062 
* Added MVTec license

* Renamed MVTec as MVTec AD
@djdameln
load best model from checkpoint (#195)
6a23a30
@samet-akcay
Replace SaveToCSVCallback with PL CSVLogger (#198)
c8ef5dd 
* remove `save_to_csv` flag from config __init__

* Removed `save_to_csv` from config files

* Added csv option to logger in the config files

* Add csv tests to logger tests

* remove save to csv callback

* 🛠 Modify `get_loggers` function to also get csv logger.

* ✏️ Remove blank line.
@ashwinvaidya17
WIP Refactor test (#197)
4f98857 
* Refactor test

* fix key issue

* Change from Path to str

* Check for empty path

* Set default path to None
@LukasBommes
fixed Dockerfile (#172)
2ab29ce 
Co-authored-by: LukasBommes <[email protected]>
@djdameln @samet-akcay
Fix visualization issue for fully defected images (#194)
fd692ea 
* fix visualization of fully defected masks

* add test case

Co-authored-by: Samet Akcay <[email protected]>
@ashwinvaidya17
✨ Add hpo search using wandb (#82)
aa08a99
@ashwinvaidya17
Merge branch 'development' into development
1c587df
@ashwinvaidya17 ashwinvaidya17 merged commit a70b156 into ashwinvaidya17:development Apr 6, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@ashwinvaidya17 @alexriedel1 @samet-akcay @LeonidBeynenson @djdameln @AlexanderDokuchaev @LukasBommes