This repository was archived by the owner on Apr 17, 2023. It is now read-only.
Conversation
harimkang
changed the title
harimkang
changed the title
* MPA cls baseline * fix flake8
… technique (#94) * Initial refactoring stage.py to support multiple training algorithms * Initial changes for enabling semisl detection * Modify semi-sl stage * Modify semi-sl recipe * Remove unnecessary changes * Modification for linking otx * Change polymorphism stage * Revert an eval hook change * Rename semi_stage and move semisl model config to otx * Revert unnecessary changes of finuetune.py * Remove breakpoint in trainer.py * Change pseudo label validation directory path * Remove debug code, create incremental folder for incr_stage and modify task adapt hook for semisl * Move unlabeled data configuration from base stage to semi-sl stage * Rename incremental/incr_stage.py to incremental/stage.py
* Add SupCon recipes for multilabel classification * Update batch size in two crop data * Refactor the BarlowTwinsLoss for extensibility * Add task_adapt to SupCon recipe * Fix bug in topk when it's larger than num_classes Also rename the linear member to fc and fc_feats to cls_score for better alignment with the rest of the code. * Remove extract_prob method to align with SAMImageClassifier * Simplify multilabel and hierarchical kwargs logic
* feat: add initial ov plugin * feat: add neck and head for cls * fix: pop node properly * feat: new ov modules * feat: add ov plugin for seg task * feat: add multiheaders classifier * fix: group convolution * fix: change normalization * fix: change adaptive batchnorm max iter * feat: add omz downloader * fix: import error * refactor: make it global variable * chore: comment imports out * feat: add optional feature for detection heads
…sed learning in segmentation & Refactor stage.py to separate task configs (#103)
* make cls incremental sampler condiser multi gpu * add gpu utilization getter process * transport distributed realted setup to OTX side * change time measurement place * enable multi-gpu inference * enable multi gpu to seg * cls outermost multigpu * multigpu refactor code * make gpu_ids length 1 if not using multi gpu * remove part related to experiment * remove unused import * load weight to proper cuda if distributed training * Shuffle indices in sampler * sampler revised * remove random * revert sampler suffle * organize import in mpa/cls/inferrer.py Co-authored-by: Lee, Soobee <soobeele@intel.com>
…kbone (#112) * Fix classification classifier & stage for public backbone enable * Relocate out last layer feat * Fix when outputs : list case
* disenable validation during warmstart * add recipe for warmstart classification * enable LARS * update data pipelines * update recipe * update recipes * remove seed and deterministic in the recipe * update batch size to match otx * add custom_hooks in warmstart recipe * update validation condition * warmstart -> selfsl & update pipeline * update data pipeline
* make single gpu cls use first gpu * apply bug fix to seg
* xai detection support * to select explainer type & fix flake8 * full inference -> backbone inference, code clean * classwise saliency map integration * add exception for tiling det case * OTX detection integration * detection class-wise saliency map update * otx det class-wise saliency map support * class-wise saliency map for otx * added mpa explainer * added mpa explainer * added MPA explainer * develop sync for class-wise saliency map * detector simple test postprocess fix * minor fix * default reciprocam * fix bug with tensor shape * merge for multi gpu * code clean
* Update inferrer.py
* disable validation during warmstart * update seg warmstart recipe * change input size for warmstart * update seg recipe * update `warmstart` -> `selfsl` * remove seed * disenable task_adapt during pretraining & enable training w/o val
* fixed multilabel configs (#67) * Tiling Module (#40) * Feature/val batch and seed (#69) * workaround bug (#70) * Kp/devide runners (#71) * move ema model to hook (#73) * Appley release/OTE_0.3.0 changes (#77) * Per-group softmax output (#74) * Move drop_last in cls trainer.py (#79) * Removed unnecessary mim version constraint for networkx package (#80) * Revert "Removed unnecessary mim version constraint for networkx package (#80)" (#82) * Don't apply activations on export in classification (#83) * Delete unused code (#84) * Replace current saliency map generation with Recipro-CAM for cls (#81) * Class-wise saliency map generation for the detection task (#97) * [XAI] hot-fix of error in Detection XAI support (#98) * [XAI] hot-fix of error in Detection XAI support (#99) * Replace only the first occurrence in the state_dict keys (#91) * [OTE / XAI] Handle two stage detector in the inferrer.py (#104) * [XAI] hot-fix of error in Detection XAI support (#98) * [OTE / XAI][Develop] Handle two stage detector in the inferrer.py (#107) * [XAI] hot-fix of error in Detection XAI support (#99) * Merge OTE side XAI update to OTX (#109) * Merge back releases/OTE_0.4.0 to develop (#116) * [XAI] hot-fix of error in Detection XAI support (#99) * [OTE / XAI] Handle two stage detector in the inferrer.py (#104) * [XAI] hot-fix of error in Detection XAI support (#98) * [Hot-fix] Fix zero-division error in one cycle lr scheduler in multilabel classification * Fix extra activations when exporting nonlinear hierarchical head (#118) * Fix get_train_data_cfg -> get_data_cfg Signed-off-by: Songki Choi <songki.choi@intel.com> Co-authored-by: Prokofiev Kirill <kirill.prokofiev@intel.com> Co-authored-by: Eugene Liu <eugene.liu@intel.com> Co-authored-by: Sungman Cho <sungman.cho@intel.com> Co-authored-by: Jihwan Eom <jihwan.eom@intel.com> Co-authored-by: Yunchu Lee <yunchu.lee@intel.com> Co-authored-by: Vladislav Sovrasov <vladislav.sovrasov@intel.com> Co-authored-by: Evgeny Tsykunov <e.tsykunov@gmail.com> Co-authored-by: dongkwan-kim <dongkwan.kim@intel.com> Co-authored-by: Adria Arrufat <adria.arrufat@intel.com> Co-authored-by: Soobee Lee <soobee.lee@intel.com>
Contributor
Author
|
Because of this, there is no need to keep this PR. so closed. |
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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
6 participants
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.
Summary:
This PR includes: