Papers of the day   All papers

Fast Sparse ConvNets


Nov 26 2019 DeepMind

“Fast Sparse ConvNets”, a collaboration w/ @GoogleAI [], implements fast Sparse Matrix-Matrix Multiplication to replace dense 1x1 convolutions in MobileNet architectures. The sparse networks are 66% the size and 1.5-2x faster than their dense equivalents.
2 replies, 486 likes

Nov 26 2019 arxiv

Fast Sparse ConvNets.
0 replies, 36 likes

Nov 26 2019 Utku

6) A common concern is: “But sparse networks are hard to accelerate!”. Check out Fast Sparse ConvNets (📃 which achieves large speedups on mobile CPUs for inference with sparse MobileNets and stay tuned for more!
1 replies, 18 likes