hitzhangyu / Self-supervised-Image-Enhancement-Network-Training-With-Low-Light-Images-Only

Self-supervised Image Enhancement Network: Training With Low Light Images Only
137 stars 18 forks source link

some problems in my practice #5

Open peiyaoooo opened 4 years ago

peiyaoooo commented 4 years ago

hi yu, I tried your code and find some minor issues.

  1. pylab module in utils.py is not given. But it seems not necessary and can be commented.
  2. The channel in Decom.conv0 should be represented as 'channel//2' to keep this variable an interger. The usage of python3.7 may result in this.
hitzhangyu commented 4 years ago

thank you, I will modify it later 1、I deleted some things that I have tried before, some may not be deleted, and I will check the code again later. 2、This is indeed caused by the python version. In python2, / can guarantee that the result is an integer when it is an integer/integer,in python3,it should be //