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

SparseResUNet42 should have LAYERS = (2, 3, 4, 6, 2, 2, 2, 2) instead of LAYERS = (2, 2, 2, 2, 2, 2, 2, 2)

YilmazKadir opened this issue · comments

From my understanding, in the original Spatiotemporal Segmentation paper MinkowskiNet42 (Res16UNet34C) has LAYERS = (2, 3, 4, 6, 2, 2, 2, 2). However, your SparseResUNet42 implementation has LAYERS = (2, 2, 2, 2, 2, 2, 2, 2). Is there a mistake in the naming or am I missing a detail?

Our implementation serves as a reference point. We didn't adhere to the exact settings of MinkowskiNet.