Inference error

[jasuriy]

Hi I am trying to run inference but getting this error: can you please help me fix it? thank you in advance

command: # inference !python inference/inference_dfdnet.py --upscale_factor 1 --test_path datasets/upload/ --official_adaption True

Traceback (most recent call last): File "/content/BasicSR/inference/inference_dfdnet.py", line 114, in net = DFDNet(64, dict_path=args.dict_path).to(device) File "/content/BasicSR/basicsr/archs/dfdnet_arch.py", line 77, in init self.dict = torch.load(dict_path) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1040, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1262, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '<'.

[thd-ux]

When I inference with inference/inference_basicvsr.py, the input and output results look the same, only the resolution is different. Do you have this problem?

[jasuriy]

I could not even get this far. Please let me know if you can solve this problem.

On Mon, Dec 16, 2024 at 5:13 PM thd-ux @.***> wrote:

When I inference with inference/inference_basicvsr.py, the input and output results look the same, only the resolution is different. Do you have this problem?

— Reply to this email directly, view it on GitHub https://github.com/XPixelGroup/BasicSR/issues/698#issuecomment-2544876352, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQKLHTX3ET4R6QZACRLGKIL2F2DQZAVCNFSM6AAAAABMGCY3Z2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBUHA3TMMZVGI . You are receiving this because you authored the thread.Message ID: @.***>