Evaluation with FID

[nanggn]

I hope to know whether you evaluated the generated images with FID . I try it and it shows 91.16 . It is too high compared with stackGAN++ model . Is it my codes' fault ? Or it is normal ?
Thanks for your reading.

[dashayushman]

@nanggn If I were you, I would throughly go through my code again :)

[nanggn]

Thanks for your reply.
I follow your advice to go through the code again with the same parameters you provided, but the FID value turns out to be 93. Would you like to share the accurate FID value and some fid.py code?
Thanks for your reading.