a simple binary neural network for SISR(base on EDSR official code)

if you want to try different binary function, you need to :

1. add new script to model/binarize and modify model/init.py to choose your binary function.
2. edit run.sh(view this script for more detail), choose one function you want to run.
3. run sh run.sh

an example binary function: bianrize/WApproxASTE.py:

forward:

backward,use approxsign (bireal-net's method)

forward:

backward,STE

add an Tanh() function before binact. It helps to transfer a nonlinear gradient after STE.

compare to Efficient Super Resolution Using Binarized Neural Network(Ma et.al.)

use pretrain