AI-Huang / AdderNet-tf

TensorFlow implementation for paper "AdderNet: Do We Really Need Multiplications in Deep Learning?"
BSD 3-Clause "New" or "Revised" License
5 stars 0 forks source link

AdderNet

TensorFlow implementation for paper "AdderNet: Do We Really Need Multiplications in Deep Learning?"

Notes

Warning! Not test yet

This code repository has not been tested well following the original paper.

Method of Differentiation

Is set to automatic (signSGD) rather than by full-precision gradient.

References