-
Notifications
You must be signed in to change notification settings - Fork 541
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
feat(lidar_transfusion): add lidar_transfusion 3D detection package #6890
base: main
Are you sure you want to change the base?
feat(lidar_transfusion): add lidar_transfusion 3D detection package #6890
Conversation
Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
Signed-off-by: Amadeusz Szymko <amadeusz.szymko@tier4.jp>
Comments:
|
@scepter914 |
@knzo25 |
Apologies 🙇 |
Thank you @knzo25 for your review. Let me investigate the kernels first to find mentioned leak. Regarding the NaN output, as you suggested we will:
|
Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
@knzo25 |
Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for PR.
Overall very readable code and rich documentation is so great. 👍
I took a quick look at whole code and I ask you to add some members for maintainers because development will be robuster and smoother if multiple people can maintain it.
As the rest of my work, I'll test with some rosbag and I'll approve after I confirm the operation with some Rosbag.
I apologize for the inconvenience, would you fix DCO? |
Co-authored-by: Satoshi Tanaka <16330533+scepter914@users.noreply.github.com> Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
8506f8a
to
f5e8146
Compare
Signed-off-by: amadeuszsz <amadeusz.szymko@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I confirm the perform with other rosbags.
After kenzo-san's review and uploading model, we can merge this PR. 👍
Signed-off-by: Kenzo Lobos-Tsunekawa <kenzo.lobos@tier4.jp>
…re.universe into feat/lidar_transfusion
@amadeuszsz |
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
…sing Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
3cd4249
to
8434721
Compare
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
I modified the code as you suggested. The preprocessing decreased from 2.15 ± 0.55 to 1.21 ± 0.25 [ms] with two clouds in cache (performance differs from PR's init benchmark due to different load). The breaking changes make harder to keep host processing (you predict that before 😃), therefore I just removed it.
Changed. Now the package is not compatible with other point cloud formats. However, there is init validation and we throw exception with appropriate logs. 98e31a9 |
perception/lidar_transfusion/lib/preprocess/pointcloud_densification.cpp
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@amadeuszsz
Thank you for handling all the comments. before merging the PR though, can you turn back the default model to centerpoint?
(checked the runtime and there are no issues)
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM !
🚀
@YoshiRi |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM for launcher part
|
||
| Name | Type | Default Value | Description | | ||
| -------------------------------- | ------------ | ------------- | -------------------------------------------------------------------------------------------------- | | ||
| `class_names` | list[string] | - | Class names for 3D object detection. | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@amadeuszsz
Sorry for the late comment, but since you added the schema file, could you change the README.md so it uses the schema instead?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done 👍🏻
Signed-off-by: amadeuszsz <amadeusz.szymko.2@tier4.jp>
Description
The PR adds a new
lidar_transfusion
package which brings a new 3D detection component based on TransFusion[1].lidar_transfusion_demo-2024-04-25_15.56.14.mp4
Related links
[1] Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu and Chiew-Lan Tai. "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers." arXiv preprint arXiv:2203.11496 (2022)
[2] rosbag (TIER IV internal link)
[3] helper files (TIER IV internal link)
[4] TransFusion onnx model (TIER IV internal link)
Tests performed
Notes for reviewers
The package can best tested with rosbag file. If data needed, you can use this rosbag[2] and copy helper files[3] to the
launch
directory oflidar_transfusion
package before building. The default path foronnx
model is~/autoware_data/lidar_transfusion/transfusion.onnx
. The model awaits for deployment, temporary please use attached link[4].To start, run commands:
Interface changes
Effects on system behavior
Pre-review checklist for the PR author
The PR author must check the checkboxes below when creating the PR.
In-review checklist for the PR reviewers
The PR reviewers must check the checkboxes below before approval.
Post-review checklist for the PR author
The PR author must check the checkboxes below before merging.
After all checkboxes are checked, anyone who has write access can merge the PR.