Request of 'pth' or 'tar' file corresponding to each MVTec AD class

[YeongHyeon]

I would like to perform only the inference function without training with the provided RealNet. A message appears that there are no pre-trained models for each class in MVTec AD. I have downloaded all the checkpoints of the provided classifier and diffusion model and saved them in a designated location. Where can I find the additional 'tar' compressed file I need to download?

y --dataset MVTec-AD --class_name bottle
Traceback (most recent call last):
  File "evaluation_realnet.py", line 182, in <module>
    main()
  File "evaluation_realnet.py", line 99, in main
    state_dict=torch.load(args.model_path)
  File "/notebooks/users/1004613/objupyterlabgpu-1004613/py38/lib/python3.8/site-packages/torch/serialization.py", line 791, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "/notebooks/users/1004613/objupyterlabgpu-1004613/py38/lib/python3.8/site-packages/torch/serialization.py", line 271, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "/notebooks/users/1004613/objupyterlabgpu-1004613/py38/lib/python3.8/site-packages/torch/serialization.py", line 252, in __init__
    super().__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'experiments/MVTec-AD/realnet_checkpoints/bottle/ckpt_best.pth.tar'

[cnulab]

We have not yet released models fine-tuned on specific anomaly detection datasets, but we may upload these checkpoints in the coming weeks.

[YeongHyeon]

Thank you for your kind response. I look forward to your model upload.

[cnulab]

We have uploaded the checkpoints trained on MVTec. They can be downloaded at the following link: mvtec checkpoints

[YeongHyeon]

Thank you very much! I will try this.