test on Rain100L,PSNR
I'm using the official model.ckpt on Rain100L and measured a PSNR of 37.44, which is significantly different from the paper report. Could you explain why?
What should I do to correct this error?
TypeError: The classmethod `PromptIRModel.load_from_checkpoint` cannot be called on an instance. Please call it on the class type and make sure the return value is used.
=================================
ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal to the smaller side of your images. If your images are multichannel (with color channels), set channel_axis to the axis number corresponding to the channels.
I have exactly same issue for Rain100L, PSNR 37.44.
What should I do to correct this error?
TypeError: The classmethod
PromptIRModel.load_from_checkpointcannot be called on an instance. Please call it on the class type and make sure the return value is used.ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal to the smaller side of your images. If your images are multichannel (with color channels), set channel_axis to the axis number corresponding to the channels.
Have you solve this problem? I have met the same Error.
What should I do to correct this error?
TypeError: The classmethod
PromptIRModel.load_from_checkpointcannot be called on an instance. Please call it on the class type and make sure the return value is used.ValueError: win_size exceeds image extent. Either ensure that your images are at least 7x7; or pass win_size explicitly in the function call, with an odd value less than or equal to the smaller side of your images. If your images are multichannel (with color channels), set channel_axis to the axis number corresponding to the channels.
Have you solve this problem? I have met the same Error.
Check skimage version is "scikit-image==0.19.3" or not 👍
change net = PromptIRModel().load_from_checkpoint(ckpt_path).to(device) to net = PromptIRModel.load_from_checkpoint(ckpt_path).to(device) can solve the problem
I'm using the official model.ckpt on Rain100L and measured a PSNR of 37.44, which is significantly different from the paper report. Could you explain why?
请问这个数据集Rain100L 你们是从哪里获取的