Imaginary component with more than 2048 images

[bertinma]

Hi,

I am facing the Imaginary component issue unless I have more than 2048 images in each folder.

I use this line of code to compute it.
fid_score = fid.compute_fid(source, target, mode="clean", verbose=True, dataset_split="custom", use_dataparallel=False)

The weird thing is that happens only on validation set, on a subset of training set it works well. Unless I perform exact same operations on both, as saving model predictions and targets using torchvision.

I am using clean-fid==0.1.35
CUDA 11.8
Python 3.10.13
numpy==1.26
torch==2.0.1
Debian 11

Thanks for tyour help in advance ;)

[vinesmsuic]

Hi, encountered same error here. Did you figure out how to solve this?

[vinesmsuic]

scipy has to be 1.11.1 instead of 1.11.2 . Just downgrade it with:

pip install scipy==1.11.1

[GaParmar]

Thanks for finding the cause of this issue!

[SantiagoDGarcia]

Thanks @vinesmsuic

[Luciennnnnnn]

It may because this PR.