Open CMY-CTO opened 5 months ago
This is the evaluation result printed in the log, but why does the .yaml
file show so many nan values?
And why the difference in the FID score can be as much as ten times……
There may be too many questions to bother you, and looking forward to the help~ Thanks in advance!
Hi!
When I ran the eval part, I met a few problems about unconstrained, and hope you can help me.
The process is carried out, and no error is reported to stop the program.
The first problem is that there is no KID value, which can refer to the screenshot from the
evaluation_results_iter450000_samp1000_scale1_a2m.yaml
file that is the evaluated result for the best model.In the
.yaml
file, there are many nan values, including accuracy_gen, accuracy_gt, accuracy_gt2, fid_unconstrained, kid_unconstrained, multimodality_gen, multimodality_gt, multimodality_gt2, precision_unconstrained, and recall_unconstrained.To double-check the problem, I also evaluated the best model given by the official zip, i.e.
./save/unconstrained/model000450000.pt
But the problems still exist.Finally, I want to know why we need gt and gt2, which means two ground truths.
Thanks in advance, and looking forward to your early reply~
evaluation_results_iter450000_samp1000_scale1_a2m.yaml
file attached here