fld
fld copied to clipboard
marcojira
PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.
When the dataset is larger,raise error: Datasets files num is: 1344726 Datasets path is: /root/autodl-tmp/MDT/log_chekpoints/sampleImage/2024_05_10_9 Datasets files num is: 50000 Traceback (most recent call last): File "evaluations/fld/eval_image.py", line 81, in...
The FLD I calculated is negative(for example “-1581.340”). Is this wrong? I see that the range you wrote is [0, 100].
When the number of training images is over 250_000, here (in class MoG.fit()) seems to have a bug? cached_dists is None.
