This is the PyTorch implementation of our paper "Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition". (Note that this is the code for image recognition on ImageNet. For semantic image segmentation/parsing refer to this repository:…
The main features of iduta/pyconv are: Plug and Play Modules.
Open-source alternatives to iduta/pyconv include: andrew-qibin/spnet — This repository is a PyTorch implementation for our CVPR2020 paper (non-commercial use only). d-li14/psconv — [ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer. dingxiaoh/acnet — Update (Aug 17, 2021): refactored the code of ACB. The readability has been greatly improved. You may call… goatmessi7/rfbnet — By Songtao Liu, Di Huang, Yunhong Wang. hszhao/pspnet — by Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia, details are in project page. jiaxiongq/slimconv — This repository contains the code (in PyTorch) for SlimConv: Reducing Channel Redundancy in Convolutional Neural…
ECCV 2020 PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Update (Aug 17, 2021): refactored the code of ACB. The readability has been greatly improved. You may call switchtodeploy of an ACB to convert it to the inference-time structure. If you use ACB in your own model, the conversion is as easy as `` for m in yourmodel.modules(): if hasattr(m,…
This repository is a PyTorch implementation for our CVPR2020 paper (non-commercial use only).
