search

valeoai / xmuda

Cross-Modal Unsupervised Domain Adaptationfor 3D Semantic Segmentation
Other
192 stars 36 forks source link

Pseudo label generation part #12

Closed torchlidar closed 3 years ago

torchlidar commented 3 years ago

Hi, Thank you for the nice code!

I have a question about the Pseudo label generation part I did python xmuda/test.py --cfg=configs/a2d2_semantic_kitti/xmuda.yaml --pselab @/model_2d_100000.pth @/model_3d_100000.pth DATASET_TARGET.TEST "('train',)" VAL.BATCH_SIZE 1

But, I got an empty train.npy ..... Is there no Pseudo label generation part in this code? So is there any way I can do it?

I'll wait for your answer. Thank you.

maxjaritz commented 3 years ago

Can you put a breakpoint here and check that you indeed append data during the test.py execution: https://github.com/valeoai/xmuda/blob/8b39f8f77f048cd4c086323dd89fbf9710335d35/xmuda/data/utils/validate.py#L79