About running yolo on apollo8.0

[fpeanut]

We appreciate you go through Apollo documentations and search previous issues before creating an new one. If neither of the sources helped you with your issues, please report the issue using the following form. Please note missing info can delay the response time.

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 18.04):18.04
• Apollo installed from (source or binary):
• Apollo version (3.5, 5.0, 5.5, 6.0):8.0
• Output of apollo.sh config if on master branch:

Steps to reproduce the issue:

• Please use bullet points and include as much details as possible:
• I want to run the yolo model 3d-r4-half_caffe on apollo8.0, but after I added the yolo module to pipline.cc and modified the configuration file, I ran the yolo test with the official data package but no results were found. What is the reason?

Supporting materials (screenshots, command lines, code/script snippets):

What is the correct way to run yolo and other 2d detection in apollo8.0

[daohu527]

we don't have any 2d detection algorithm in Apollo, but 3d detection. The planning module needs 3d(x,y,z) coordinates to plan the trajectory.

If you need 2d detection, you can write a separate module to support it

[fpeanut]

Apollo 中没有任何 2d 检测算法，但有 3d 检测。规划模块需要 3d(x,y,z) 坐标来规划轨迹。

如果需要二维检测，可以编写单独的模块来支持它

感谢您的回复，就是我发现你们不管是yolo还是smoke的模型，他们的输出都会额外带一个feat_blob，请问这个很重要吗。我如果用常规的smoke或者yolo3d模型是不是不能在apollo里面部署.

[hjlhhh-eng]

我们在 Apollo 中没有任何 2D 检测算法，而是 3D 检测。规划模块需要 3d（x，y，z） 坐标来规划轨迹。

如果需要 2D 检测，可以编写单独的模块来支持它 May I ask if starting Apollo's obstacle detection module with the default configuration results in an error message when auto outputs=net_. forward (torch_inputs). toDuple() ->elements? The main error message is CUDA: invalid argument. How should this be resolved？