vtab1k Dataset accuracy about vpt HOT 12 CLOSED

Yes, the demo can be used well, now the experimental results are the same as those in the paper. Thank you!

from vpt.

Hi, @111chengxuyuan , to debug, I wonder if you can use the one of the 3 vtab-datasets in the demo.ipynb, and see if the results are the same.

from vpt.

After a quick check on the config, the feature is different: should be "sup_vitb16_imagenet21k" instead of "sup_vitb16_224".

But I still recommend using the 3 vtab datasets in demo as a starting point for reproducing our results.

from vpt.

OK,thank you,I'll try

from vpt.

let me know how it goes! btw, could you use the lr, wd, seed values specified in the demo as well?

from vpt.

Awesome! I'm glad to hear that! Will close the issue for now, feel free to reopen if you have other questions!

from vpt.

After a quick check on the config, the feature is different: should be "sup_vitb16_imagenet21k" instead of "sup_vitb16_224".

But I still recommend using the 3 vtab datasets in demo as a starting point for reproducing our results.

what is the difference between these two models? using different datasets to pre-train?

the link provided in README, is it sup_vitb16_imagenet21k or sup_vitb16_224?

from vpt.

sup_vitb16_imagenet21k is not supported since you did not provide imagenet21k_ViT-B_16.npz.
I can only set "sup_vitb16" as the pretrained model.

from vpt.

sup_vitb16_imagenet21k is not supported since you did not provide imagenet21k_ViT-B_16.npz. I can only set "sup_vitb16" as the pretrained model.

can you be more specific? i don't quite understand you.

from vpt.

sup_vitb16_imagenet21k is not supported since you did not provide imagenet21k_ViT-B_16.npz. I can only set "sup_vitb16" as the pretrained model.

can you be more specific? i don't quite understand you.

I am asking the similar questions like yours.

from vpt.

I cannot run with the feature set to sup_vitb16_imagenet21k.

from vpt.

@qianlanwyd @zhaoedf I see that there is some confusion over the feature names. The link provided in README is for ViT-Base pre-trained with ImageNet-21k, which is the main pre-trained model we used in the paper.

Due to legacy issue, I renamed the downloaded ckpt to imagenet21k_ViT-B_16.npz from ViT-B_16.npz. The new ckpt name is used for building the model. If you don't rename the checkpoint and set DATA.FEATURE = "sup_vitb16_imagenet21k", you will get a FileNotFound error.

There are two solutions:
(1) rename the downloaded ckpt to imagenet21k_ViT-B_16.npz.
(2) change L35 of src/models/build_vit_backbone.py to ViT-B_16.npz.

I recommend to use solution (1). I also added a note in README about this.

from vpt.