Mario Avolio
Mario Avolio
So, actually we can't execute training on a custom dataset?
> Any news here? Nope for now, someone that know how to make self-distillation using the [train file](https://github.com/facebookresearch/dinov2/blob/44abdbe27c0a5d4a826eff72b7c8ab0203d02328/dinov2/train/train.py) in the repo ?
@usryokousha your code has a little error when using copy.deepcopy on a ModuleDict with PyTorch models. `(, RuntimeError('Only Tensors created explicitly by the user (graph leaves) support the deepcopy protocol...
Hi, Thanks for your reply! Yes, I’ve checked the example files you mentioned, including the *sonar_example.blend*. They are helpful in understanding the general workflow, but I’m still unclear on the...
Hi, Do you mean something like this? 
Hi, regarding the sentence: > "the images in the paper are simple screenshots of Blender after performing the scan while having a top down view of the scene." Could you...