ZXP-S-works
ZXP-S-works
Hi Stephen, C2F-ARM is an ingenious method and I tried to replicate the learning curves in the paper. However, I failed in achieving the same performance as the paper for...
Hi traveller, Thanks for the great work! I think the following features could nice to have: 1. Upsampling layer. Although there is spconv.SparseInverseConv3d(), it seems limited to upsampling a stride-convoluted...
Hi SS-Conv authors, It's nice to see calumnies' great work! I also graduated from SCUT. I am curious that do you have U-net implementation using this network? Specifically, upsampling layers,...