Closed PeterNg15 closed 3 weeks ago
Hi, thanks for your trying! I think this could be a bug of viewer. You can try to train without open the viewer in website, and we may try to fix it later. Best
Hi, this resolved my issue. Thanks!
Same issue here! Thanks for trying to solve this. Also, I found a line in dynamic_annotation.py will keep printing log info like
@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ frame_id is a portion of the whole sequence, use frame_id 1552671567297042
when the viewer is on.
Hi @LightwheelAI , I tried running your project on a 4090 and I have been getting the same error at step ~10-25%. I trained on sequences
2094681306939952000, [20,115]
and8398516118967750070, [0,160]
, and use all variations ofpoints3D_*.bin
but I would still get the same error. In the traceback I got an assertion error thatmodel_name not in self.visible_model_names
. Subsequently, my code terminates due to tensor mismatch. So I'm not sure if this dimension mismatch is due to floaters since I am already using the cleaned initial point clouds provided.Here's the running summary:
Thanks in advance for your help. Best