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.

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] fix SECOND Waymo results #363

Merged
merged 2 commits into from
Mar 23, 2021

Conversation

happynear
Copy link
Contributor

@happynear happynear commented Mar 16, 2021

The results of SECOND on Waymo do not match the log file. The results on README are too low.

README:
| [SECFPN]|5|3 Class|2x|8.12||58.0|53.5|51.5|48.3|log|
| above @ Car|||2x|8.12||58.5|57.9|51.6|51.1| |
| above @ Pedestrian|||2x|8.12||63.9|54.9|56.0|48.0| |
| above @ Cyclist|||2x|8.12||48.6|47.6|46.8|45.8| |

LOG:
{"mode": "val", "epoch": 24, "iter": 1977, "lr": 1e-05, "Vehicle/L1 mAP": 0.67149, "Vehicle/L1 mAPH": 0.66598, "Vehicle/L2 mAP": 0.58660, "Vehicle/L2 mAPH": 0.58173, "Pedestrian/L1 mAP": 0.68099, "Pedestrian/L1 mAPH": 0.59131, "Pedestrian/L2 mAP": 0.59516, "Pedestrian/L2 mAPH": 0.51546, "Sign/L1 mAP": 0.0, "Sign/L1 mAPH": 0.0, "Sign/L2 mAP": 0.0, "Sign/L2 mAPH": 0.0, "Cyclist/L1 mAP": 0.60655, "Cyclist/L1 mAPH": 0.59519, "Cyclist/L2 mAP": 0.58416, "Cyclist/L2 mAPH": 0.57321, "Overall/L1 mAP": 0.65301, "Overall/L1 mAPH": 0.61749, "Overall/L2 mAP": 0.58864, "Overall/L2 mAPH": 0.55680}

@CLAassistant
Copy link

CLAassistant commented Mar 16, 2021

CLA assistant check
All committers have signed the CLA.

@happynear happynear changed the title fix SECOND Waymo results [fix] fix SECOND Waymo results Mar 16, 2021
@Tai-Wang
Copy link
Member

Thanks for your kind correction. I just found the PR for enhancing SECOND results on Waymo in the changelog has also incorrect PR number/link (Improvements in v0.8.0, Enhance SECOND benchmark on Waymo with stronger baselines. (#166) -> Enhance SECOND benchmark on Waymo with stronger baselines. (#205) ). Could you please also modify it in this PR?

@Tai-Wang Tai-Wang self-requested a review March 16, 2021 02:59
@happynear
Copy link
Contributor Author

Seems that this PR(#205) didn't modify the results in README, but changed the log.

@Tai-Wang
Copy link
Member

Seems that this PR(#205) didn't modify the results in README, but changed the log.

Yes it's my carelessness at that time (both the PR number in the changelog & the PR for updating benchmark not changing the README). I just want you to help modify the changelog by the way.

@happynear
Copy link
Contributor Author

OK, I changed the PR number.

@codecov
Copy link

codecov bot commented Mar 16, 2021

Codecov Report

Merging #363 (0528c1f) into master (440e44a) will not change coverage.
The diff coverage is n/a.

Impacted file tree graph

@@           Coverage Diff           @@
##           master     #363   +/-   ##
=======================================
  Coverage   49.69%   49.69%           
=======================================
  Files         174      174           
  Lines       11758    11758           
  Branches     1838     1838           
=======================================
  Hits         5843     5843           
  Misses       5555     5555           
  Partials      360      360           
Flag Coverage Δ
unittests 49.69% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.


Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 440e44a...0528c1f. Read the comment docs.

@happynear happynear changed the title [fix] fix SECOND Waymo results [Fix] fix SECOND Waymo results Mar 16, 2021
@ZwwWayne ZwwWayne merged commit 22c47ac into open-mmlab:master Mar 23, 2021
tpoisonooo pushed a commit to tpoisonooo/mmdetection3d that referenced this pull request Sep 5, 2022
…on (open-mmlab#363)

* fix wrong buffer which will case onnxruntime-gpu crash with segmentaion

* fix check

* fix build error

* remove unused header
@OpenMMLab-Assistant-007
Copy link

Hi!
@happynear
First of all, we want to express our gratitude for your significant PR in the OpenMMLab project. Your contribution is highly appreciated, and we are grateful for your efforts in helping improve this open-source project during your personal time. We believe that many developers will benefit from your PR.

We would also like to invite you to join our Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us :https://discord.gg/UjgXkPWNqA

If you have WeChat account,welcome to join our community on WeChat. You can add our assistant :openmmlabwx. Please add "mmsig + Github ID" as a remark when adding friends:)
Thank you again for your contribution❤

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants