qasfb
qasfb
what is the actual value between the top-left image vs the bottom-left image in your grid ? also, can you describe what you mean by "the last 384 dimensions" ?...
essentially what i'm trying to understand is if we are in the case where: - all images in a given row (with different lighting / shadows) have similarities > 0.4...
"high" compared to what ? Would you be able to provide the similarity scores across images (of different rows) ?
Sorry for the late reply; if this problem persists, does this PR fix it for you by any chance ? https://github.com/facebookresearch/dinov2/pull/195
Can you give me more detail about how you obtain these results ? Which checkpoint did you evaluate ? The command line in the readme evaluates the checkpoint at 25k...
It seems you are evaluating the checkpoint at 25k iterations ?
The code does not allow distillation at the moment, you would need to hack a little bit inside, such that you: - initialize and freeze a teacher along with its...
how bad ? can you plot the loss and eval curves ?
Please ask the lightly library maintainers for this information, we don't have expertise with this library.
would you be able to share more details ?