search

tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
https://tamarott.github.io/SinGAN.htm
Other
3.29k stars 608 forks source link

How to calculate "diversity" ? #151

Open YeeDer opened 3 years ago

YeeDer commented 3 years ago

I try to calculate diversity according to the paper " To quantify the diversity of the generated images, for each training example we calculated the standard deviation (std) of the intensity values of each pixel over 100 generated images, averaged it over all pixels, and normalized by the std of the intensity values of the training image."

I train the model by the default setting according to the code, and get the SIFID 0.1138 ( the coarsest level ), Diversity 0.3371. But I am not sure if my calculation is correct. If you can supply the code about "diversity", I would be appreciated!

Thank you very much. Looking forward to your reply.

DonghweeYoon commented 2 years ago

I request the same thing. It is difficult to reproduce "diversity" with the description of the paper alone. I would appreciate it if you could provide the code for calculating diversity.