Regarding ImageNet regeneration

[Kim-Dongjun]

Hi,

thank you for your contribution to the community!
I am currently having trouble regenerating the performance on ImageNet dataset.
For now, I am thinking of ImageNet64, but the FID is 1.97.

My commend is
python gen_class_samplesheet.py --outdir=sample_sheets --trunc=1.0 --network=https://s3.eu-central-1.amazonaws.com/avg-projects/stylegan_xl/models/imagenet64.pkl --samples-per-class 50 --classes 0-99 --grid-width 32 --centroids-path=https://s3.eu-central-1.amazonaws.com/avg-projects/stylegan_xl/models/imagenet_centroids.npy

Could you help me regenerating the performance of 1.51?