Avneesh Mishra

Hey @gmberton, Thanks for pointing out the speed issue. We're looking into it, alongside some repository restructuring. I'll update this issue after delivering a patch on the `torch.hub` pipeline soon.

The `torch.hub` model is released [here](https://github.com/AnyLoc/DINO). The README contains a tutorial for usage. Other things like DINO (v1) and PCA are coming soon.

Hey @euncheolChoi Thanks for taking an interest in our work. I'll first review the vocabulary terminology, then answer your two questions. ## Vocabulary Terminology Vocabulary is a "superset" of images...

Hey @euncheolChoi, We didn't experience this error before. Are you trying this from a clean install? Make sure your torch hub directory - usually `~/.cache/torch/hub` - doesn't have anything before...

We use the GeM descriptor’s PCA projection to identify distinct regions in the (PCA projected) descriptor space. The idea is that these regions form a good representative sample. The vocabularies...

Hey @MAX-OTW, Thanks for taking an interest in our work. The `.npy` files for other datasets are available in our [Public Release](https://iiitaphyd-my.sharepoint.com/:f:/g/personal/robotics_iiit_ac_in/EtpBLzBFfqdHljqQMnm6xdoBzW-4KFLXieXDVN4vPg84Lg?e=BP6ZW1) (the `Datasets-All` folder has `.tar.gz` files that contains...

Hey @babyporgrammer, Thanks for taking an interest in our work. I might have misunderstood your question about the recall rate, but I'll try my best to answer. > I am...

Hey @Waycn, thanks for taking an interest in our work. ## AnyLoc-VLAD-DINO If you insist on using AnyLoc-VLAD-DINO (using features from DINOv1, **not** DINOv2), we haven't created a simple demo...

Hey there, there seems to be an issue with our IIIT-H Microsoft OneDrive. I'm in the process of sorting this out with the college. In the meantime, I have hosted...

Hey @rosejn, Thanks for your interest in our work. We're working on releasing the PCA parameters too on [torch.hub](https://github.com/AnyLoc/DINO) (it's still experimental). In the meanwhile, you can achieve the PCA...