Shang Yang

Thank you for your interest in TorchSparse. Can you provide more information about your wordload? For example, what is the input resolution and batch sizes?

Hi. We haven't implemented those pooling kernels yet. We will consider to implement them. Thank you for reaching out!

Hi @pycoco , thanks for your interest. `bfloat16` is typically used for training jobs. However, we have launched many training jobs and found that `float16` will not affect the accuracy....

@pycoco . Hi! Thank you for the feedback. Can you provide more details about the 'certain scenario'? Actually we have launched a lot of training jobs on segmentation/detection tasks and...

Hi, thanks for your interest in TorchSparse. Can you provide more details about the error? What is the error message you received here?

Hi @ZzTodd22! Thanks for your interests in TorchSparse! This is a very good question! We do have some unit tests demonstrating that the sparse convolution can be mapped to the...

Hi all, I started from the code provided by @ZXP-S-works. It seems that the error was caused by the wrong initialization of `spatial_range` when initializing the `SparseTensor`. Since the `spatial_range`...

Hi @ybc-ybc , could you please provide a snippet code for reproduction? Thank you.

I see. I'll take a look.

No. I didn’t observe the same situation on my server. I think this problem might be caused by dataloader library rather than torchsparse. I would suggest you check the version...