search

keroro824 / HashingDeepLearning

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"
MIT License
1.07k stars 169 forks source link

logloss in `Network::ProcessInput` #1

Open bkj opened 5 years ago

bkj commented 5 years ago

Right now, logloss in Network::ProcessInput is just hardcoded to zero -- is there an easy way to actually compute and return this?