Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Fix for ssd #2197

Merged
merged 7 commits into from
May 30, 2023
Merged

Fix for ssd #2197

merged 7 commits into from
May 30, 2023

Conversation

jaegukhyun
Copy link
Contributor

@jaegukhyun jaegukhyun commented May 25, 2023 •
edited
Loading

Summary

This PR is for recovering SSD performance in various datasets.
This PR recovered anchor clustering algorithm and reverted model's loss from FocalLoss to CrossEntropyLoss.

General experiments summary is below

Dataset Original(lr 0.01) After patching(lr: 0.01) After patching(lr:0.001) After patching(lr:0.0001)
bccd 0.649213 0.89527 0.62499 0.54375
bccd-small 0.583053 0.65477 0.55037 0.16545
fish 0.764477 0.92602 0.93547 0.91042
fish-small 0.368733 0.71402 0.6381 0.0
pothole 0.524933 0.6536 0.63977 0.43677
pothole-small 0.359793 0.56047 0.35459 0.06723
vitens 0.6608 0.76366 0.77472 0.67276
vitens-small 0.544617 0.62937 0.4723 0.06667
coco 0.108813 0.17965 0.23709 0.2417
voc 0.25117 0.34927 0.42455 0.3571

How to test

Checklist

  • I have added unit tests to cover my changes.​
  • I have added integration tests to cover my changes.​
  • I have added e2e tests for validation.
  • I have added the description of my changes into CHANGELOG in my target branch (e.g., CHANGELOG in develop).​
  • I have updated the documentation in my target branch accordingly (e.g., documentation in develop).
  • I have linked related issues.

License

  • I submit my code changes under the same Apache License that covers the project.
    Feel free to contact the maintainers if that's a concern.
  • I have updated the license header for each file (see an example below).
# Copyright (C) 2023 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

Bump up 1.3.1
cf8e31e 
Signed-off-by: Songki Choi <songki.choi@intel.com>
@github-actions github-actions bot added the ALGO Any changes in OTX Algo Tasks implementation label May 25, 2023
@jaegukhyun jaegukhyun added this to the 1.3.0 milestone May 25, 2023
@eunwoosh
bugfix: auto adapt batch size doesn't work with cls incr case (openvi…
14caa3c 
…notoolkit#2199)

* auto adapt consider cls incremental case

* align with pre-commit

* update changelog
@github-actions github-actions bot added the TEST Any changes in tests label May 26, 2023
@jaegukhyun jaegukhyun modified the milestones: 1.3.0, 1.4.0 May 26, 2023
@github-actions github-actions bot added the DOC Improvements or additions to documentation label May 26, 2023
@jaegukhyun jaegukhyun marked this pull request as ready for review May 26, 2023 05:16
@jaegukhyun jaegukhyun requested a review from a team as a code owner May 26, 2023 05:16
goodsong81
goodsong81 previously approved these changes May 26, 2023
View reviewed changes
Copy link

@goodsong81 goodsong81 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Impressive!

sungmanc
sungmanc previously approved these changes May 26, 2023
View reviewed changes
@sungmanc
Copy link
Contributor

BTW, how about changing the target of this PR to 1.3.1? @jaegukhyun , @goodsong81 . This is Huge improvements so introducing to external release is a good option for us

@goodsong81
Copy link

BTW, how about changing the target of this PR to 1.3.1? @jaegukhyun , @goodsong81 . This is Huge improvements so introducing to external release is a good option for us

I'm OK for 1.3.1, but it's up to @jaegukhyun as the experiments were based on the develop branch, right?

@jaegukhyun jaegukhyun dismissed stale reviews from sungmanc and goodsong81 via 30ea730 May 26, 2023 06:17
@github-actions github-actions bot added the API Any changes in OTX API label May 26, 2023
@jaegukhyun jaegukhyun changed the base branch from develop to releases/1.3.1 May 26, 2023 06:18
@jaegukhyun
Copy link
Contributor Author

@goodsong81 @sungmanc I changed base to 1.3.1

sungmanc
sungmanc previously approved these changes May 26, 2023
View reviewed changes
goodsong81
goodsong81 previously approved these changes May 26, 2023
View reviewed changes
@jaegukhyun jaegukhyun modified the milestones: 1.4.0, 1.3.0 May 30, 2023
@jaegukhyun jaegukhyun modified the milestones: 1.3.0, 1.3.1 May 30, 2023
@jaegukhyun jaegukhyun dismissed stale reviews from goodsong81 and sungmanc via 21b29dc May 30, 2023 01:05
@github-actions github-actions bot removed the API Any changes in OTX API label May 30, 2023
@jaegukhyun jaegukhyun merged commit 8a3efaa into openvinotoolkit:releases/1.3.1 May 30, 2023
@jaegukhyun jaegukhyun deleted the ssd-fix branch June 2, 2023 01:10
goodsong81 pushed a commit that referenced this pull request Jun 5, 2023
@jaegukhyun @vinnamkim
@sungmanc @eunwoosh @sungchul2 @yunchu @JihwanEom @eugene123tw @sovrasov @djdameln
Merge back 1.3.1 to develop (#2218)
dbeb59a 
* Fix e2e (#2179)

* Fix iseg e2e (#2173)

* Fix det e2e (#2176)

* Update noisy label det docs for detection task (#2183)

* Fix iseg e2e (#2173)

* Fix det e2e (#2176)

* Add supcon seg for regression (#2177)

* Fix iseg e2e (#2173)

* Fix det e2e (#2176)

* Update regression test config (#2186)

* Fix for anomaly regression test (#2188)

* Fix iseg regression (#2190)

* Set path to save pseudo masks into workspace (#2185)

* Temporary fix override_configs bug (#2187)

* Fix iseg e2e (#2173)

* Fix det e2e (#2176)

* Cleaned up skip/xfail TCs on the classification e2e tests (#2196)

* Added csv output to export dependencies (#2178)

* Fix typo and enlarge the threshold for KPI tests (#2198)

* bugfix: auto adapt batch size doesn't work with cls incr case (#2199)

* Fix for ssd (#2197)

* Turn off persistent worker if num_worker is zero in classification task (#2208)

* Update test cases of common_semantic_segmentation_dataset (#2210)

* Optimize counting train & inference speed and memory consumption (#2172)

* Do not skip full img tile classifier + Fix Sequencial Export Issue (#2174)

* Add warning message to tiling parameter (#2193)

* Change the way to pad for instance-segmentation

* Hotfix: use 0 confidence threshold when computing best threshold based on F1

* Fix possible bw issue in exportable code (#2212)

* Fix ellipse load (#2214)

* Fix GT vs prediction order mismatch due to different sorting result (#2216)

* Return raw anomaly maps as metadata (#2217)

* Fix merge error, revert to pymongo w/o version spec

---------

Signed-off-by: Songki Choi <songki.choi@intel.com>
Signed-off-by: Kim, Vinnam <vinnam.kim@intel.com>
Co-authored-by: Jaeguk Hyun <jaeguk.hyun@intel.com>
Co-authored-by: Vinnam Kim <vinnam.kim@intel.com>
Co-authored-by: Sungman Cho <sungman.cho@intel.com>
Co-authored-by: Eunwoo Shin <eunwoo.shin@intel.com>
Co-authored-by: Kim, Sungchul <sungchul.kim@intel.com>
Co-authored-by: Yunchu Lee <yunchu.lee@intel.com>
Co-authored-by: Jihwan Eom <jihwan.eom@intel.com>
Co-authored-by: Eugene Liu <eugene.liu@intel.com>
Co-authored-by: sungmanc <sungmanc@intel.com>
Co-authored-by: Vladislav Sovrasov <sovrasov.vlad@gmail.com>
Co-authored-by: Dick Ameln <dick.ameln@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@goodsong81 goodsong81 goodsong81 approved these changes

@sungmanc sungmanc sungmanc approved these changes

Assignees
No one assigned
Labels
ALGO Any changes in OTX Algo Tasks implementation DOC Improvements or additions to documentation TEST Any changes in tests
Projects
None yet
Milestone
1.3.1
Development

Successfully merging this pull request may close these issues.
4 participants
@jaegukhyun @sungmanc @goodsong81 @eunwoosh