Run, Don‘t Walk: Chasing Higher FLOPS for Faster Neural Networks(CVPR2023)
过去工作存在的不足我们的工作主要贡献(待参考)RelatedworkCNNViT,MLP,andvariantsDesignofPConvandFasterNetPreliminaryPartialconvolutionasabasicoperatorPConvfollowedbyPWConvFasterNetasageneralbackboneEx