xinge008 / Cylinder3D

Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Apache License 2.0
859 stars 180 forks source link

test.py #31

Closed libozan closed 3 years ago

libozan commented 3 years ago

@xinge008 Thank you so much for sharing the code.

I am currently implementing your code repeatedly. Due to the limitation of 2080Ti, the memory during training is not enough and the batch size can only be set to 1. I want to test my training results and consider whether it needs to be implemented on 3090, but I did not find a test .py file, I don’t know if I can use PolarSeg/test_pretrain_SemanticKITTI.py to test.

xinge008 commented 3 years ago

For inference on SemanticKITTI or nuScenes, you can refer code in https://github.com/xinge008/Cylinder3D/blob/master/train_cylinder_asym.py#L82-L107;

BTW, you can also use PolarSeg/test_pretrain_SemanticKITTI.py with some modification;

libozan commented 3 years ago

thank you very much for your help.