dinov2 issues

Results 171 dinov2 issues

Sort by recently updated

No module named 'dinov2

I was having trouble running dinov2 after running I would appreciate it if you could let me know if there is a solution ``` (dinov2) abe@ganesa:~/kuma-ssl/dinov2$ python dinov2/run/train/train.py --nodes 1...

abebe9849

documentation

CUDA check before importing xFormers.

I don't know how useful this might be, but in some cases attempts to run DINOv2 on CPU would fail because the xformers requirement could be satisfied, but the model...

alihassanijr

CLA Signed

ConvNext

Hello, Have you considered using the ConvNext architecture for training DINOv2? ConvNext has shown to have improved performance and lower latency on tasks such as CLIP. For example, in the...

SimJeg

enhancement

Classification and segmentation performance comparing to traditional CNN

Correct me if I was wrong, seems the paper did not mention a performance comparison with other supervised CNN models?

kail85

High resolution image result with NaN features

Hello, I'm having an issue with Dinov2 while trying to use it with high-resolution images like the one available at [this link](https://unsplash.com/photos/Nyvq2juw4_o). The problem is that the features returned by...

TurtleSmoke

Train vit-L16 in ImageNet-1k, got confusing files.

https://github.com/facebookresearch/dinov2/blob/main/dinov2/data/datasets/image_net.py#L103-L110 what does those file come from? f"entries-{split.value.upper()}.npy" f"class-ids-{split.value.upper()}.npy" f"class-names-{split.value.upper()}.npy"

JoJoistheBestOne

documentation

How to prevent image redundancy when use the retrieval step to augment your data?

Thanks for the valuable contribution to the community. In Paper's A.4, you describe a retrieval step to augment different dataset with uncurated data. How do you avoid image redundancy when...

XiaohuJoshua

How to use DINOv2 pretrained ViT model for Downstream Task ?

Thanks for your great work and it impresses me ! I wanna to have a try in my research. Specificly, I wanna to use ViT-small to replace the ImageNet pretrained...

kaixinbear