-
Notifications
You must be signed in to change notification settings - Fork 445
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.
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
Integrate new ignored loss in semantic segmentation #2055
Integrate new ignored loss in semantic segmentation #2055
Conversation
…kit#2011) Revert segmentation ignore=True
* prevent timeout during init phase
* Edit regression tests * Change the dataset root * Miss typo * Fix pre-commit
* Add missing __init__.py * Change license
…oolkit#2023) * Add workaround solution * Fix minor * Remove str int
fix: change default to configdict Signed-off-by: Inhyuk Andy Cho <andy.inhyuk.jo@intel.com>
* Update cls, det datsets * Remove useless files * Change action datasets * Edit action dataset * change dir * Add xml files * Remove useless * Edite tets * Fix tests * Fix tests * Remove ptc * Remove * Fix precommit * Update dataset, fix cls bug * Remove useless dataset * Edit drop_last * Fix missed part * Change threshold values to unifying * bugfix: squeezing to 1 dimenetion * Change threshold for deployment * Fix multi-gpu issue, e2e tests * Decrease num_workers for tiling test and tiling processes * Revert num_workers for tests * Fix datsets --------- Co-authored-by: eunwoosh <eunwoo.shin@intel.com>
…emantic segmentation (openvinotoolkit#2020)
…_extensions into seg-ignore-loss-integration
Could you change the PR as a draft if it's in progress? |
I'm ready to review. Let me add related unit tests in other PR. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall codes look good to me. Thank you for your effort. Could you check my comments. I want you to add type-hint for new classes.
otx/algorithms/segmentation/adapters/mmseg/models/heads/custom_fcn_head.py
Outdated
Show resolved
Hide resolved
otx/algorithms/segmentation/adapters/mmseg/models/heads/custom_fcn_head.py
Outdated
Show resolved
Hide resolved
otx/algorithms/segmentation/adapters/mmseg/models/heads/custom_fcn_head.py
Outdated
Show resolved
Hide resolved
otx/algorithms/segmentation/adapters/mmseg/models/losses/cross_entropy_loss_with_ignore.py
Show resolved
Hide resolved
otx/algorithms/segmentation/adapters/mmseg/models/heads/custom_fcn_head.py
Show resolved
Hide resolved
otx/algorithms/segmentation/adapters/mmseg/models/losses/cross_entropy_loss_with_ignore.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot for your hard work and quick implmentation :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM! The test cases look enough for the sanity check. Thank you :)
…2055) * HOT-FIX: Revert segmentation model's ignore mode in CLI (openvinotoolkit#2011) Revert segmentation ignore=True * Improve tiling preprocess (openvinotoolkit#2013) * prevent timeout during init phase * Fix reg tests (openvinotoolkit#2008) * Edit regression tests * Change the dataset root * Miss typo * Fix pre-commit * Fix openvino import error due to Tiler init import (openvinotoolkit#2015) Remove init import for Tiler to prevent OpenVINO import * Bump up version to 1.2.0 (openvinotoolkit#2017) * Set the python version to "3.10" for code-scan workflow * Add missing __init__.py (openvinotoolkit#2019) * Add missing __init__.py * Change license * Release 1.2.0rc1 * Fix issue that str2bool not being applied in certain cases (openvinotoolkit#2023) * Add workaround solution * Fix minor * Remove str int * Fix default dict (openvinotoolkit#2025) fix: change default to configdict Signed-off-by: Inhyuk Andy Cho <andy.inhyuk.jo@intel.com> * Convert dummy datasets to toy datasets (openvinotoolkit#1988) * Update cls, det datsets * Remove useless files * Change action datasets * Edit action dataset * change dir * Add xml files * Remove useless * Edite tets * Fix tests * Fix tests * Remove ptc * Remove * Fix precommit * Update dataset, fix cls bug * Remove useless dataset * Edit drop_last * Fix missed part * Change threshold values to unifying * bugfix: squeezing to 1 dimenetion * Change threshold for deployment * Fix multi-gpu issue, e2e tests * Decrease num_workers for tiling test and tiling processes * Revert num_workers for tests * Fix datsets --------- Co-authored-by: eunwoosh <eunwoo.shin@intel.com> * Fix E2E tests (openvinotoolkit#2032) * Optimize data preprocessing time and enhance overall performance in semantic segmentation (openvinotoolkit#2020) * add unit test * exp * intg agg * implement ignore label * no update in model.py * ignore in label * only updated ignored loss * final * final * exp * refactor * refactor ignore loss * revert * default mode is ignore false * unit test revised * model update * revise detcon * fix error in intg test * test case revised * make run in semisl * add type hints * update docs * test case added --------- Signed-off-by: Inhyuk Andy Cho <andy.inhyuk.jo@intel.com> Co-authored-by: Harim Kang <harim.kang@intel.com> Co-authored-by: Eugene Liu <eugene.liu@intel.com> Co-authored-by: Sungman Cho <sungman.cho@intel.com> Co-authored-by: Songki Choi <songki.choi@intel.com> Co-authored-by: Yunchu Lee <yunchu.lee@intel.com> Co-authored-by: Jaeguk Hyun <jaeguk.hyun@intel.com> Co-authored-by: Inhyuk Cho <andy.inhyuk.jo@intel.com> Co-authored-by: eunwoosh <eunwoo.shin@intel.com> Co-authored-by: Lee, Soobee <soobeele@intel.com>
Summary
This PR includes new ignored cross entropy loss for semantic segmentation.
Optimization for segmentation
Results

How to test
Checklist
License
Feel free to contact the maintainers if that's a concern.