search

Owen718 / ECCV22-Perceiving-and-Modeling-Density-for-Image-Dehazing

ECCV'22 Oral | Perceiving and Modeling Density for Single Image Dehazing.
MIT License
55 stars 6 forks source link

Need your model to complete comparison #2

Closed nbbllxx0 closed 2 years ago

nbbllxx0 commented 2 years ago

I would like to compare your model with my VIT in my conference paper, I wonder when the model could be released?

Owen718 commented 2 years ago

Hi！ We already release the testing code in the _InferenceCode.

nbbllxx0 commented 2 years ago

Thanks for the reply, the test.py seems unable to read .png or.rgb files, though the _testlist can be recognized and printed correctly.

G:\anaconda3\envs\pytorch\python.exe G:/ECCV22-Perceiving-and-Modeling-Density-for-Image-Dehazing-main/Inference_Code/test.py --pk_path PMNET_Haze4k.tjm --save_path dehaze --test_path hazy ['1.png', '2.png', '3.png', '4.png', '5.png'] Traceback (most recent call last): File "G:\ECCV22-Perceiving-and-Modeling-Density-for-Image-Dehazing-main\Inference_Code\test.py", line 42, in Net=torch.jit.load(opt.pk_path,map_location=torch.device('cuda:0')).eval().cuda() File "G:\anaconda3\envs\pytorch\lib\site-packages\torch\jit_serialization.py", line 161, in load cpp_module = torch._C.import_ir_module(cu, str(f), map_location, _extra_files) RuntimeError: Unknown type name 'NoneType': Serialized File "code/torch/model/TSANet16.py", line 156 def forward(self: torch.model.TSANet16.MixScale, argument_1: Tensor, argument_2: Tensor) -> NoneType:


    _53 = self.factor
    _54 = (self.mixblock).forward(_53, )

Process finished with exit code 1
Owen718 commented 2 years ago

Okay~

zhenyuan1234 commented 1 year ago

Did you successfully test the code ?