dvlab-research / LargeKernel3D

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)
https://arxiv.org/abs/2206.10555
Apache License 2.0
197 stars 8 forks source link

About SpatialGroupconv and SpatialGroupconvV2 #14

Open completezealous opened 11 months ago

completezealous commented 11 months ago

Hi, I'm interested in your work. I looked at your paper and code and I have a question. Regarding Figure 3, in the paper you replaced the normal convolutional layer with SW__LK, 7X7 at training time and 3X3 at inference time, is that right? And the convolutional layer corresponding to spatialgroupconv and spatialgroupconvV2 in the code for training and inference stages respectively? Or should we just use spatialgroupconvV2 for training and inference?