search

ByChelsea / VAND-APRIL-GAN

[CVPR 2023 Workshop] VAND Challenge: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
193 stars 22 forks source link

Can we test without loading pre-trained weights? #21

Open liyiyue2021 opened 9 months ago

liyiyue2021 commented 9 months ago

Can I test without loading pre-trained weights, and how do I set the checkpoint_path?

ByChelsea commented 9 months ago

You must have pre-trained weights to perform the test. You can set either an absolute or relative path, just by changing the checkpoint_path in test_zero_shot.sh.

liyiyue2021 commented 9 months ago

Thank you for your very prompt reply. What I mean is, is it possible to train the model without loading weights from other pre-trained data (eg, Visa or MVTec datasets)? I would like to test it using the original CLIP weights.

ByChelsea commented 8 months ago

As mentioned in WinCLIP, directly using the weights of CLIP does not yield good results (the first line of Table 8). Are you referring to this experiment?

liyiyue2021 commented 7 months ago

Got it, thank you.