VOTR
VOTR copied to clipboard
PointsCoder
Voxel Transformer for 3D object detection
I try to train my module votr_ssd with a single GPU and make my batch size as 2, which needs 50 hours. The problem is that the result is false...
Hello, do you think VOTR can be migrated to other tasks? such as scene completion Is this difficult to achieve?THX
**My setting is torch: 1.10 cuda: 11.3** **error:** Traceback (most recent call last): | 0/1856 [00:00
I am trying to train the model with fp16 input. Could you please guide me to work around votr.ops that requires fp32? Thanks!
Thank you for your contribution to the field. Is the techniques presented in this paper can be applied to voxels generated using SimpleBEV technique? Best regards,
求问：在模型训练过程中，一瞬间直接显示训练完成所有epoch，然后Wait 30 seconds for next check，这是什么原因呢？During model training, it suddenly displays that all epochs have completed, then shows “Waiting 30 seconds for the next check.” What could be causing this?
