using ImageNet class for ImageNet-1K

[Dhia-naouali]

this edited section is instructing how to train on the ImageNet-1k dataset Fast setup: training DINOv3 ViT-L/16 on ImageNet-1k while passing ImageNet22k to the cli command which will instanciate the ImageNet22k class and not the intended ImageNet class as per dataloader.py :

    if name == "ImageNet":
        class_ = ImageNet
        if "split" in kwargs:
            kwargs["split"] = ImageNet.Split[kwargs["split"]]
    elif name == "ImageNet22k":
        class_ = ImageNet22k

edited section:

 PYTHONPATH=${PWD} python -m dinov3.run.submit dinov3/train/train.py \
  --nodes 4 \
  --config-file dinov3/configs/train/vitl_im1k_lin834.yaml \
  --output-dir <PATH/TO/OUTPUT/DIR> \
  train.dataset_path=ImageNet22k:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>
                             ^^^