-
Notifications
You must be signed in to change notification settings - Fork 29
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
NMS doesn‘t seem to work. The visualization of 3D boundingbox in SUNRGBD dataset contains lots of overlapped boxes. #24
Comments
Hi @XIDIANPQZ , Can you please try with |
The system environment is as follows: cuda11.0, python3.8, pytorch1.7.0, torchvision0.8.0, mmdetection3D 0.8.0, mmdet2.8.0, mmcv1.2.5. |
Thanks. I have tried with different score_thr. The network with high score_thr only detects a bed, but still produces many overlapped boxes |
The 'Error' is printed after each sample completes inference. When I debug the code step by step, I find that the cause is in "mmdet3D/ops/iou3d/iou3d_utils.py". I am not sure if this is caused by the version of Sofaware. |
This error may be from iou3d.cpp. |
Never met this before. This message is produced by |
Will this error cause NMS to fail? |
Yes it can be the reason. Can you please try with |
Thank you. I will try the suggest version again. |
I have tried torch==1.6.0 and cuda10.1. But the result is still bad. Can you help me check the software version again in the below?
In the installation process, the code is as follows. Can you please check the errors?
In the testing process, I don't know whether the error is from the config or checkpoints. The code is run in the root dictionary of imvoxelnet-master: |
Are you still getting this Also the installation process is a bit strange. E.g. you first install I tried to build the |
I still get this |
I want to try to build the docker-file from scratch. However, I am not familiar to docker. Can you please provide the tutorials of the installation and running? Thank you. |
Unfortunately have no ideas how to help you, as all package versions are fine :( About docker, you first need to install nvidia-docker. Commands to build and run can be found in |
Thank you for taking the time to help me anyway. |
The only difference is the test data. Can you please send your test file by email? The address is |
In the issue of mmdetection3D, there are the similar result in Issue771. |
Will send you
It is also probably not about Btw, you can try to run |
Through Docker, the visualization results are great. |
🎉 Nice to hear. |
The text was updated successfully, but these errors were encountered: