Is there a pretrained DINOV2 model trained on the ImageNet-1k dataset available?
I would like to utilize the DinoV2 model pretrained on the ImageNet-1k dataset as the backbone for my research, specifically for comparing it with other methods in my research domain. However, I am facing limitations in terms of computational resources, which are insufficient to support the training process.
There are pretrained backbones provided. Please refer to the ReadMe
There are pretrained backbones provided. Please refer to the
ReadMe
I have reviewed the readme again, and I would like to clarify that I means a backbone pre-trained on the ImageNet-1k dataset, rather than on the LVD-142M dataset.
I would like to utilize the DinoV2 model pretrained on the ImageNet-1k dataset as the backbone for my research, specifically for comparing it with other methods in my research domain. However, I am facing limitations in terms of computational resources, which are insufficient to support the training process.
Hello, may I ask if your issue has been resolved? I also want to train my own dataset based on its pre trained weights