SPConv.pytorch

[ IJCAI-20 ] Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution

This repo provides Pytorch implementation of IJCAI 2020 paper Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution

Pretrained models will be released soon.

Requirements

• Python 3
• Pytorch 1.1
• NVIDIA DALI for GPU dataloader
• NVIDIA APEX for mixed precision

Introduction of SPConv

Redundancy in Feature Maps

SPConv Module

Performance

Outperforms STOA baselines in both accuracy and inference time on GPU, with FLOPs and parameters dropped sharply.

Small Scale Classification

Large Scale Classification