Visual-Attention-Network / SegNeXt

Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)
Apache License 2.0
795 stars 85 forks source link

about AttentionModule #58

Open qiaoqiangPro opened 1 year ago

qiaoqiangPro commented 1 year ago

Hello, I would like to ask if it is possible to split a 77 convolution kernel into (17) and (7*1) convolution kernels in 2D, how should I do it if it is a 3D image, I would like to ask you for advice.