search

The-Learning-And-Vision-Atelier-LAVA / SMSR

[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference
238 stars 30 forks source link

Sparse Convolution #3

Closed HaihuaQiu closed 3 years ago

HaihuaQiu commented 3 years ago

Hello， can you introduce Sparse Convolution details?

HaihuaQiu commented 3 years ago

I can not undestand 'Implementation of Sparse Convolution' that you write in github... Thank you

LongguangWang commented 3 years ago

Hi @HaihuaQiu, thanks for your interest in our work. The key idea of our sparse convolution implementation is to divide the convolution into 4 branches (i.e., dense->dense, dense->sparse, sparse->dense & sparse->sparse ). Maybe you can make the question more specific that I can better help you to understand our code.