[Feature] Adding Vehicle Pose estimation using CARFUSION Dataset

[dineshreddy91]

trafficstars

Motivation

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

Before PR:

• [x] I have read and followed the workflow indicated in the CONTRIBUTING.md to create this PR.
• [x] Pre-commit or linting tools indicated in CONTRIBUTING.md are used to fix the potential lint issues.
• [x] Bug fixes are covered by unit tests, the case that causes the bug should be added in the unit tests.
• [ ] New functionalities are covered by complete unit tests. If not, please add more unit tests to ensure correctness.
• [ ] The documentation has been modified accordingly, including docstring or example tutorials.

After PR:

• [x] CLA has been signed and all committers have signed the CLA in this PR.

[CLAassistant]

All committers have signed the CLA.

[codecov[bot]]

Codecov Report

Base: 84.47% // Head: 84.34% // Decreases project coverage by -0.13% :warning:

Coverage data is based on head (42a2d1b) compared to base (afb37d4). Patch coverage: 71.56% of modified lines in pull request are covered.

:exclamation: Current head 42a2d1b differs from pull request most recent head c80e7d4. Consider uploading reports for the commit c80e7d4 to get more accurate results

Additional details and impacted files

@@             Coverage Diff              @@
##           dev-0.29    #1510      +/-   ##
============================================
- Coverage     84.47%   84.34%   -0.14%     
============================================
  Files           236      238       +2     
  Lines         20036    20237     +201     
  Branches       3602     3642      +40     
============================================
+ Hits          16925    17068     +143     
- Misses         2231     2273      +42     
- Partials        880      896      +16     

Flag	Coverage Δ
unittests	84.24% <71.56%> (-0.14%)	:arrow_down:

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

Impacted Files	Coverage Δ
mmpose/datasets/__init__.py	100.00% <ø> (ø)
mmpose/datasets/datasets/top_down/__init__.py	100.00% <ø> (ø)
mmpose/models/backbones/resnet.py	100.00% <ø> (ø)
mmpose/models/backbones/vipnas_resnet.py	93.95% <ø> (ø)
mmpose/apis/inference_3d.py	76.64% <50.00%> (-0.94%)	:arrow_down:
...sets/datasets/vehicle/topdown_carfusion_dataset.py	71.79% <71.79%> (ø)
mmpose/datasets/datasets/__init__.py	100.00% <100.00%> (ø)
mmpose/datasets/datasets/vehicle/__init__.py	100.00% <100.00%> (ø)
mmpose/apis/inference_tracking.py	61.71% <0.00%> (+0.30%)	:arrow_up:

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[jin-s13]

Thank you very much for your contribution! We will review the codes ASAP. It seems that the lint check fails. Could you please follow https://github.com/open-mmlab/mmpose/blob/master/.github/CONTRIBUTING.md this guide to use pre-commit to format your codes?

[jin-s13]

Also, we would appreciate it, if you could add some basic unittest. You may refer to https://github.com/open-mmlab/mmpose/blob/master/tests/test_datasets/test_top_down_dataset.py Thanks!

[jin-s13]

Have you already trained the HRNet model using MMPose? Could you upload the trained models and logs to google drive or onedrive? This will be very helpful for our accuracy verification.

[dineshreddy91]

The data and the config file can be found here: https://drive.google.com/drive/folders/1ikzZ6QXVS5U0kruBX843tMlKpCDWDRU5?usp=sharing

[dineshreddy91]

Fixed the indentation errors and the comments and uploaded the test files. Unittest has been updated as well.

[dineshreddy91]

update-model-index.......................................................Failed

• hook id: update-model-index
• exit code: 1
• files were modified by this hook

When updating the file with accuracy number I face this issue during git commit. Code corresponding to this is given below. Results on Carfusion test dataset

Arch	Input Size	AP	AP50	AP75	AR	AR50	ckpt	log
pose_hrnet_w32	384x288	0.493	0.915	0.489	0.548	0.925	ckpt	log

let me know how to fix this.

[jin-s13]

You may run pre-commit run --all-files locally before commit to fix lint errors.

[jin-s13]

Hi @dineshreddy91, I noticed that you updated the codes a few days ago. If you are still interested, let's work together to fix the remaining issues and merge this PR in Nov.

[OpenMMLab-Assistant-004]

Hi @dineshreddy91 ！We are grateful for your efforts in helping improve mmpose open-source project during your personal time.

Welcome to join OpenMMLab 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 a 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❤