PnPInversion
PnPInversion copied to clipboard
How evaluate excessive change?
Hello,
Thank you for your excellent project.
However, I have a question. When I ran the experiment, I noticed that some evaluation metrics returned NaN values in cases like the one shown in the image below. From what I understand, the metrics mentioned in the paper seem to involve calculating the average over the generated images. In cases like this, how did you handle such situations?
Thank you.