Song Han is an associate professor at MIT EECS and distinguished scientist at NVIDIA. His research interest is efficient AI computing.
-
MIT, NVIDIA
- songhan.mit.edu
- @songhan_mit
- in/songhanmit
-
Deep-Compression-AlexNet Public
Deep Compression on AlexNet
-
SqueezeNet-Residual Public
residual-SqueezeNet
-
DSD Public
DSD model zoo. Better accuracy models from DSD training on Imagenet with same model architecture
-
SqueezeNet-Deep-Compression Public
-
SqueezeNet-Generator Public
SqueezeNet Generator
-
-
-
haDNN Public
Forked from ppwwyyxx/haDNNProof-of-Concept CNN in Halide
-
SqueezeNet Public
Forked from forresti/SqueezeNetSqueezeNet: AlexNet-level accuracy with 50x fewer parameters
-
Halide Public
Forked from ravi-teja-mullapudi/Halidea language for image processing and computational photography
-
-
convnet-benchmarks Public
Forked from soumith/convnet-benchmarksEasy benchmarking of all public open-source implementations of convnets
-
neural-style Public
Forked from jcjohnson/neural-styleTorch implementation of neural style algorithm
Lua MIT License UpdatedSep 5, 2015