hpi-xnor / BNext

Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket
Apache License 2.0
56 stars 4 forks source link

what is the meaning of the self.temperature used in the binarization process of weights? #5

Closed Alexrich961210 closed 1 year ago

NicoNico6 commented 1 year ago

Thanks for your attention to this work.

As described in the paper, we use the progressive weight binarization technique [0] and the self.temperature in HardBinaryConv class controls the binarization degree during training. It starts from 1.0 and evolves to 0.0 following an exponential decay scheme.

Wish this is helpful for you.

[0] BoolNet: Minimizing The Energy Consumption of Binary Neural Networks