Xiaoyang Wu

Hi, as with any MSA-based attention, the training parameter is sensitive. Also, we don't recommend training the model with a small batch size.

Hi, I have the same question. Could you explain the meaning of 8, 16, 512. Assume the meaning of 3 is coordination of point clouds.

Hi, as the crop is random, it can cover the whole point cloud with a larger epoch, and the randomness is good for the final result.

So, one tech for training attention is scaling the learning rate of the attention block to 1/10 of the default learning rate.

Thanks for your contribution. I will process your PR this weekend.

Hi, could you explain the meaning of "the length of the sequence", also an explanation of batch data here (https://github.com/Pointcept/Pointcept?tab=readme-ov-file#offset) might be helpful.

Hi, the error was caused by an incorrect offset definition. From your description, you can try the following sudocode: ```python B, T, N, _ = x.shape x = x.reshape(-1, N,...

Hi, Regarding how to employ a custom dataset, the discussion here might be helpful (https://github.com/Pointcept/Pointcept/issues/108)

Change ``` x = x.reshape(-1, N, 3) ``` to ``` x = x.reshape(-1, 3) ```

Hi, if the original shape of x is `torch.Size([8, 16, 512, 3])` as your discribed, the shape of x after resize (`x.reshape(-1, 3)`) should be `torch.Size([65536, 3])`, so the size...