-
Notifications
You must be signed in to change notification settings - Fork 444
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
[FIX] Arrange scale between bbox preds and bbox targets in ATSS #1880
Conversation
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. Thanks for your work :)
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.
Could you follow the PR template?
e.g. openvinotoolkit/datumaro#854
Isn't same bugfix needed to release branch? |
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.
I've left a comment. Please let me know your opinion.
Arrange scale between bbox preds and bbox targets
* Fix ote_config -> otx_config * [FIX] hang issue when tracing a stack in certain scenario (#1868) fix: use primitive library * [FIX][POT] Set stat_requests_number parameter to 1 (#1870) Set POT stat_requests_number parameter to 1 in order to lower RAM footprint * [FIX] Training error when batch size is 1 (#1872) fix: drop last batch * Recover detection num_workers=2 * Remove nbmake from base requirements * Add py.typed in package * [FIX] Arrange scale between bbox preds and bbox targets in ATSS (#1880) Arrange scale between bbox preds and bbox targets --------- Co-authored-by: Inhyuk Cho <andy.inhyuk.jo@intel.com> Co-authored-by: Nikita Savelyev <nikita.savelyev@intel.com> Co-authored-by: Jaeguk Hyun <jaeguk.hyun@intel.com>
* [RELEASE][DOC] Fix wrong info in documentation (#1849) * updated dataset formats info. Fix for multilabel classification * revert file * revert file. minor * added warning to instance segmentation * revert changes * [Enhance] Separate installation for each tasks on release task (#1869) * separte_import * align with pre commit * update unit test code * add separate task env pre merge test & aplly it to github action * add multiprocess to requirement * [FIX][REL1.0] Fix Geti integration issues (#1885) * Fix ote_config -> otx_config * [FIX] hang issue when tracing a stack in certain scenario (#1868) fix: use primitive library * [FIX][POT] Set stat_requests_number parameter to 1 (#1870) Set POT stat_requests_number parameter to 1 in order to lower RAM footprint * [FIX] Training error when batch size is 1 (#1872) fix: drop last batch * Recover detection num_workers=2 * Remove nbmake from base requirements * Add py.typed in package * [FIX] Arrange scale between bbox preds and bbox targets in ATSS (#1880) Arrange scale between bbox preds and bbox targets * [FIX][RELEASE1.0] Remove cfg dump in ckpt (#1895) * Remove cfg dump in ckpt * Fix pre-commit * Release v1.0.1 * [FIX] Prevent torch 2.0.0 installation (#1896) * Add torchvision & torchtext in requirements/anomaly.txt with fixed version * Update requirements/anomaly.txt * Fix _model_cfg -> _recipe_cfg due to cfg merge --------- Signed-off-by: Songki Choi <songki.choi@intel.com> Co-authored-by: Prokofiev Kirill <kirill.prokofiev@intel.com> Co-authored-by: Eunwoo Shin <eunwoo.shin@intel.com> Co-authored-by: Inhyuk Cho <andy.inhyuk.jo@intel.com> Co-authored-by: Nikita Savelyev <nikita.savelyev@intel.com> Co-authored-by: Jaeguk Hyun <jaeguk.hyun@intel.com> Co-authored-by: Jihwan Eom <jihwan.eom@intel.com>
Cause
Bbox encode or decode status is not matched between bbox preds and bbox targets in ATSS
Solution
Check self.reg_decoded_bbox value. If self.reg_decoded_bbox is True, then ATSS has to decode bbox_pred values since bbox_target values are not encoded