MatthieuCourbariaux / BinaryNet

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
BSD 3-Clause "New" or "Revised" License
1.04k stars 346 forks source link

Any example not using GPU XOR to perform runtime inference? #27

Open eerobert opened 6 years ago

eerobert commented 6 years ago

Instead, using the Train-time binary_net.py and binarized weights to perform inference

I tried to modify the original train-time cifar10.py to do inference, but without success.