**Note: for network definitions, we directly use `timm.models.ResNet` and [official ConvNeXt](https://github.com/facebookresearch/ConvNeXt/blob/048efcea897d999aed302f2639b6270aedf8d4c8/models/convnext.py).**
It is **required** to specify your experiment_name `<experiment_name>` ImageNet data folder `--data_path`, model name `--model`, and checkpoint file path `--resume_from` to run fine-tuning.
All the other configurations have their default values, listed in [downstream_imagenet/arg.py#L13](https://github.com/keyu-tian/SparK/blob/main/downstream_imagenet/arg.py#L13).
Note that the first argument `<experiment_name>` is the name of your experiment, which would be used to create an output directory named `output_<experiment_name>`.