Goto

Collaborating Authors

 soumith convnet-benchmark


soumith/convnet-benchmarks

#artificialintelligence

A summary is provided in the section below. I pick some popular imagenet models, and I clock the time for a full forward backward pass. I ignored dropout and softmax layers. The CuDNN benchmarks are done using Torch bindings. One can also do the same via Caffe bindings or bindings of any other library.