This repository was archived by the owner on Apr 17, 2023. It is now read-only.
Add Class-Incremental Learning features for Classification & Segmentation #8
Conversation
This file contains hidden or 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
* Sample test enable - temporary save * Pass sample test * Pass sample test * Add segmentation sample code * Refactor clssification & add segmentation proto * Remove demo files * Remove seg files * Remove seg files - 2 * Code review feedback * Minor Fix * Rebase * Enable task impl - temporary commit to save * Temporary commit to save * Delete deterministic.txt * Reflect code review & bug fix * Flake8 * Temporary commit to rebase * Fix export bug * Minor fix * Minor fix * Minor fix * Reflect review comment * Update state dick hook * Export bugfix & add effnet template * Weight mixing * Bugfix on num_classes * fix det samples * Export bugfix & integration test * Sample update & bugfix * Minor fix * Update mobilenet 0.75x -> 1x * Update Expoert, EMAv2 hook * Reflect code review feedback Co-authored-by: JihwanEom <[email protected]> Co-authored-by: harimkan <[email protected]>
* vfnet template added * remove sample ckpt & initial model training added into sample * sample check with vfnet * minor fix Co-authored-by: Harim Kang <[email protected]>
* Fix sample & add mobilenet templates * Fix stats Co-authored-by: JihwanEom <[email protected]>
…e_cli (#5) * merge Jihwan's task implementation * remove debugging code * add class incremental learning recipe & ignore mode for seg * (WIP) update codes to run ote_cli * (WIP) update stage for OTE * update ote dataset * ote rebase * update ote integration part * enable bg_aware in loss * update task to remove bg for OTE * update config setting * update loss structure (keep using mmseg pixcel_base) * merge latest * MPASegIncrDataset fix * update mpa_pixcel_base * fixed accuracy drop issue * stage, dataset classes align * seg sample test * update evaluation metric to mIoU * code refactoring in stage & add adaptable loss config for ignore mode * update missing arg * fix sample ckpt & dataset domain * remove sample ckpts * fix wrong domain info in label_schema * remove class_sensitive_copy_state_dict in inferrer * add output_logit true settings in exporter/inferrer * fix force-close issue in evaluation after adding output_logits=True setting for ote-cli * reflect BaseTask correction * add seg samples * apply code review feedback * add the removed file * apply code review feedback * update code review feedback * revert the removed parameter(using) * sample code update * sample code update * remove some comments * fix flake8 issues * update code review feedback (using cpu) * remove cityscape dataset for product (need more implementation) * add cityscape dataset * remove ckpt files * sample initial training freeze remove * add integ test pths Co-authored-by: harimkan <[email protected]> Co-authored-by: Jihwan Eom <[email protected]>
Signed-off-by: Songki Choi <[email protected]>
goodsong81
pushed a commit
that referenced
this pull request
Apr 7, 2022
* Move tasks & model templates to OTE repo * Update external/training_extension to MPA PR * Remove external/mmdetection * Update init_venv.sh * Update README.md * Enable non-incremental learning * TODO: Remove OTE SDK/Task dependency
harimkang
added a commit
that referenced
this pull request
Apr 7, 2022
* Apply MPA public repo changes to inner source (#8) * Move tasks & model templates to OTE repo * Update external/training_extension to MPA PR * Remove external/mmdetection * Update init_venv.sh * Update README.md * Enable non-incremental learning * TODO: Remove OTE SDK/Task dependency * Update mpa's minor issue and add model (#10) * Add det/seg OTELoggerHook & OTEProgressHook * Add effnetv2 template & seg export config update * Add ote hooks * Add metrics score to best_acc * Fix some pretrained var conf * Separate mpa changes and apis task changes * Update SamClassifier & seg weight mixing * Minor fix * Update segmentation configuration * Update sam_classifier.py * Merge remote-tracking branch 'origin/ote' into ote-public Co-authored-by: Harim Kang <[email protected]> Co-authored-by: Jihwan Eom <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
No description provided.