Giters

mit-han-lab / torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

Home Page:https://torchsparse.mit.edu

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Can the shape of convolutional kernels be designed by users themselves ？

huohuohuohuohuohuohuohuo opened this issue · comments

commented

Can the shape of convolutional kernels be designed by users themselves ？

commented

Yes. Just specify the kernel shape (e.g., kernel_size = (1,3,3)) when defining the conv layer.