how to run resnet50 and how to set dataset to cifar10

[martin0310]

Run resnet50:

when i run the command:
python imagenet.py --gpus 0 --arch resnet50 --job_dir ./experiment --data_path image_dir --pretrained_model pretrained_model/resnet50.pth --pr_target 0.5 --N 4 --conv_type BlockL1Conv --train_batch_size 256 --eval_batch_size 256 --rearrange --num_epochs 2 --export_onnx

the output in terminal shows:
==> Preparing data..
==> Conv Type: BlockL1Conv
==> BN Type: LearnedBatchNorm
Traceback (most recent call last):
/1xN/imagenet.py", line 455, in
main()
/1xN/imagenet.py", line 292, in main
model, pr_cfg = get_model(args)
^^^^^^^^^^^^^^^
/1xN/imagenet.py", line 238, in get_model
ckpt = torch.load(args.pretrained_model, map_location=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
/anaconda3/envs/new_torch/lib/python3.11/site-packages/torch/serialization.py", line 1028, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
/anaconda3/envs/new_torch/lib/python3.11/site-packages/torch/serialization.py", line 1231, in legacy_load
return legacy_load(f)
^^^^^^^^^^^^^^
/anaconda3/envs/new_torch/lib/python3.11/site-packages/torch/serialization.py", line 1158, in legacy_load
tensor = torch.tensor([], dtype=storage.dtype).set(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Attempted to set the storage of a tensor on device "cpu" to a storage on different device "cuda:0". This is no longer allowed; the devices must match.

set data to cifar10:

Is there any complete example command for setting dataset to cifar10?