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

Qdtrack #183

Merged
merged 45 commits into from
Jul 19, 2021
Merged

Qdtrack #183

merged 45 commits into from
Jul 19, 2021

Conversation

mageofboy
Copy link
Contributor

No description provided.

@ICGog
Copy link
Contributor

ICGog commented Jun 3, 2021

@mageofboy Is this PR ready for review?

@mageofboy
Copy link
Contributor Author

@mageofboy Is this PR ready for review?

Sorry for the delayed response. Yes, it is mostly ready, outside of some reformatting

Copy link
Contributor

@ICGog ICGog left a comment

Choose a reason for hiding this comment

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

It's looking good, but please address my comments before we merge in the PR.

@@ -15,7 +15,7 @@
--simulator_num_people=200
--simulator_num_vehicles=10
######### Other config #########
--visualize_tracked_obstacles
# --visualize_tracked_obstacles
Copy link
Contributor

Choose a reason for hiding this comment

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

Can you please revert changes to this config file. I think it's best if this config file uses sort by default because it's a well tested tracker that doesn't have many dependencies.

'Path to the model')
flags.DEFINE_string(
'qd_track_config_path',
'dependencies/qdtrack/configs/qdtrack-frcnn_r50_fpn_12e_bdd100k.py', #FIX
Copy link
Contributor

Choose a reason for hiding this comment

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

Why is there a fix comment?

flags.DEFINE_string(
'qd_track_config_path',
'dependencies/qdtrack/configs/qdtrack-frcnn_r50_fpn_12e_bdd100k.py', #FIX
'Path to the model')
Copy link
Contributor

Choose a reason for hiding this comment

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

I guess this is the Path to the model configuration.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yea, it's the qd track model path but it's currently the path to the bdd model, rather than the waymo model

scripts/lanenet_data_postprocess.py Outdated Show resolved Hide resolved
pylot/perception/tracking/qd_track_operator.py Outdated Show resolved Hide resolved
git clone https://github.com/mageofboy/qdtrack.git
git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection
python3 setup.py develop #need to add mmcv
Copy link
Contributor

Choose a reason for hiding this comment

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

How reliable is mmdetection's installation? Did it work out of the box for you?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

unfortunately it is not reliable and installation depends on torch and cuda version

@ICGog
Copy link
Contributor

ICGog commented Jul 14, 2021

Also, can you please make the code style changes necessary to ensure that the CI passes? You can see the suggested changes here: https://github.com/erdos-project/pylot/pull/183/checks?check_run_id=2488080643

Copy link
Contributor

@ICGog ICGog left a comment

Choose a reason for hiding this comment

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

Looks good to me! There's only one comment left to address.

configs/tracking.conf Outdated Show resolved Hide resolved
@ICGog ICGog merged commit fdba024 into erdos-project:master Jul 19, 2021
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.

2 participants