Seokjin Go

DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism

Depth-wise Separable Convolution (DSConv) has a powerful representation even with fewer parameters and computation, leading to its adoption by almost all of the state-of-the-art CNN models. DSConv models are already compact making it hard to apply pruning, and there are few previous pruning techni…