Skip to content
This repository has been archived by the owner on Apr 17, 2023. It is now read-only.

Catching up new OTE refactoring for detection task #7

Merged
merged 9 commits into from
Mar 30, 2022

Conversation

goodsong81
Copy link
Collaborator

No description provided.

@goodsong81 goodsong81 merged commit 72df641 into develop Mar 30, 2022
@goodsong81 goodsong81 deleted the refactor/det-new-ote-style branch March 30, 2022 14:42
goodsong81 and others added 9 commits March 31, 2022 06:36
* Clear OTEseg dependency

* Remove build files

* Remove sampler config

* Remove lite-hrnet utils

* Flake8

* Update trainer ckpt
* add new sample codes and fix some issues

* train infer fix

* stage unit test fix

* fix export issue

* minor refactoring

* rename MPADataset to MPADetDataset

* _init_ change

* code review apply
goodsong81 pushed a commit that referenced this pull request Apr 4, 2022
* Fix sample & add mobilenet templates

* Fix stats

Co-authored-by: JihwanEom <[email protected]>
goodsong81 added a commit that referenced this pull request Apr 4, 2022
…tion (#8)

* Task implementation for classification (#1)

* 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 (#6)

* 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]>

* Temp remove LFS pointer files

* Merge branch 'ote' of https://github.com/intel-innersource/frameworks.ai.algorithms.model-preparation-algorithm into ote-public

* Move tasks/templates to OTE. Revert cls model cfgs. Remove irrelevant files

* Classification sample update & add mobilenet templates (#7)

* Fix sample & add mobilenet templates

* Fix stats

Co-authored-by: JihwanEom <[email protected]>

* class-incremental learning for semantic segmentation template with ote_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]>

* Fix: enable multi-output export / non-incremental training

* Merge remote-tracking branch 'origin/ote' into ote-public

* Merge branch 'ote' of https://github.com/intel-innersource/frameworks.ai.algorithms.model-preparation-algorithm into ote-public

* Fix reference from mmseg to segmentation_task

Signed-off-by: Songki Choi <[email protected]>

* Update README & constraints.txt

Co-authored-by: Jihwan Eom <[email protected]>
Co-authored-by: harimkan <[email protected]>
Co-authored-by: Emily Chun <[email protected]>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants