search

Pointcept / PointTransformerV3

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
MIT License
816 stars 47 forks source link

prediction convertion? #110

Open bututoubaobei-0108 opened 3 weeks ago

bututoubaobei-0108 commented 3 weeks ago

Hello,

I try to run the code of testing, and use the model "mode_best.pth" in hugging face for s3dis segmentation: https://huggingface.co/Pointcept/PointTransformerV3/tree/main/s3dis-semseg-pt-v3m1-0-rpe/model However, when I apply the predicted label on the coordinates of the point clouds, for example, on area5_hallway9, the obtained hallway form does not correspond to the one obtained when I apply the groud truth label on the same coordinates of the point clouds.

For example, in the point clouds with the predicted labels, the roof has holes, and the hallway has some obstacles, which do not appear in the point clouds with the ground truth labels.

However, when I do not apply the labels to the point clouds, and only visualize the point clouds, the form is different from both the point clouds with predicted labels and those with groud truth labels.

Do you know what the problem is?

https://github.com/user-attachments/assets/769f35f9-e010-4ecf-acf8-9cc7730f2fd7

https://github.com/user-attachments/assets/1e7af0e2-af9b-4b88-b5fe-69a92549fd53

https://github.com/user-attachments/assets/f0d427b5-cbac-4f89-b387-b6b7c4bfbcdf

Gofinge commented 3 weeks ago

Nice visualization, how about first check the number metric of testing is matched? The released weight is for PTv3 is with Pointcept v1.5.1. I remember there exist a small gap between current version.

jtj01 commented 3 weeks ago

Hello, I would like to ask, how do you visualize it? I am using the same pre trained model as you. I am unable to visualize it, and I am not sure if the result I ran is incorrect or for some reason. I hope you can help me answer this, thank you very much! 屏幕截图 2024-10-31 142604

bututoubaobei-0108 commented 3 weeks ago

Nice visualization, how about first check the number metric of testing is matched? The released weight is for PTv3 is with Pointcept v1.5.1. I remember there exist a small gap between current version.

Thank you for the suggestion. I will check it out about the metric value. In addition, do you have the latest version of the model of ptv3 for dataset s3dis?

bututoubaobei-0108 commented 3 weeks ago

Hello, I would like to ask, how do you visualize it? I am using the same pre trained model as you. I am unable to visualize it, and I am not sure if the result I ran is incorrect or for some reason. I hope you can help me answer this, thank you very much! 屏幕截图 2024-10-31 142604

the output is the label of each point. You should create a file in which you define a color for each label. In this way, each point has its corresponding color, and you can visualize it. I visualize it based on open3d library

jtj01 commented 3 weeks ago

Thank you very much for your reply. I ran it successfully! Thank you！