Hello sir, I have interesting image deblurring and i searched your code.

I checked your code. I found that your network needs paired images (blurred image vs sharp image vs etc. ) I want to know input-data information.

This is your config.py.

    # data dir
    # config.data_offset = '/data1/junyonglee/defocus_deblur'
    config.data_offset = 'datasets/defocus_deblur'
    config.c_path = os.path.join(config.data_offset, 'DPDD/train_c')
    config.l_path = os.path.join(config.data_offset, 'DPDD/train_l')
    config.r_path = os.path.join(config.data_offset, 'DPDD/train_r')

I have blurred images only. Can i try to train your code??

Thanks, Edward Cho.

Hi! Dear author: I currently have some 1280x960 clear industrial product images. Now I need to solve the problem of defocus blur during equipment operation. Do you know how to make a dataset and train it with your network？ Thanks!

Traceback (most recent call last): File "D:/python/SCI/IFAN-main/IFAN-main/run.py", line 308, in with open('{}/config.txt'.format(config.LOG_DIR.config)) as json_file: FileNotFoundError: [Errno 2] No such file or directory: '/Bean/logs/junyonglee\IFAN_CVPR2021\IFAN\config/config.txt' Laoding Config for evaluation

Hi @HyeongseokSon1 ,

I have an issue by running the latest code using this command : python run.py --mode IFAN --network IFAN --config config_IFAN --data DPDD --ckpt_abs_name ckpt/IFAN.pytorch --cpu --data_offset ./test --output_offset ./test_out

Basically I would like to test my 1 .jpg image and store in ./test

The error is shown like this:

Here is my directory list:

Do you know what is the problem ? or maybe I am doing wrong ?

Hi Lee, Thanks for your kindly share the code I train your model on my own data, it works well on most case,but on resolutioncard may introduce artifact,it show on img,can you help me?

Thanks

hello Junyong Lee: Thanks to your great work! I have a question about lines 35 to 36 in 'models/IAC.py':kernel2 = kernel2.permute(0, 2, 3, 1).view(N, H, W, channels, ksize) feat_in = torch.sum(torch.mul(feat_in, kernel1), -1) Is it supposed to be this way:kernel2 = kernel2.permute(0, 2, 3, 1).view(N, H, W, channels, ksize) feat_in = torch.sum(torch.mul(feat_in, **kernel2**), -1) Thank you for your help! @codeslake

Thank you for this very interesting project. I would like to ask you to add an easier way to implement scripts - something like python run.py --input_path --output_path. - add ability to be able to specify the folder with the incoming image and the folder with the result. I think when there will be a full demo then more people will pay attention to this project, unfortunately, not everyone uses Google Collab.

Hi,

I faced config is undefined while trying to train the model. It looks like line 298 in https://github.com/codeslake/IFAN/blob/main/models/trainers/trainer.py should be self.config.mode instead of config.mode

edit: 278->298

Hi @codeslake Thank you for sharing great and interesting project. I am testing your code with some blurred image input on Google colab and output great result. One quick question, currently It is running on top of GPU show fast result the performance around 30 - 40 ms. Just curious, is it possible to run your model inference using CPU ? Thank you very much.

when I test it, the following error has been reported, can you tell me the reason?

No module named 'models.archs.' File "C:\Program Files\Python3\Lib\importlib_init_.py", line 127, in import_module return _bootstrap.gcd_import(name[level:], package, level) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\models\trainers\trainer.py", line 39, in init lib = importlib.import_module('models.archs.{}'.format(config.network)) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\models_init.py", line 5, in create_model model = lib.Model(config) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\eval.py", line 44, in init model = create_model(config) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\eval.py", line 75, in eval_quan_qual input_c_file_path_list, input_l_file_path_list, input_r_file_path_list, gt_file_path_list = init(config, mode) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\eval.py", line 187, in eval eval_quan_qual(config) File "D:\virtualenv\pytorch19\code\defocus\IFAN-main\run.py", line 338, in eval(config) File "C:\Program Files\Python3\Lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Program Files\Python3\Lib\runpy.py", line 96, in _run_module_code mod_name, mod_spec, pkg_name, script_name) File "C:\Program Files\Python3\Lib\runpy.py", line 263, in run_path pkg_name=pkg_name, script_name=fname) File "C:\Program Files\Python3\Lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Program Files\Python3\Lib\runpy.py", line 193, in _run_module_as_main (Current frame) "main", mod_spec)

Hi, I notice that in your paper, the test results of DPDNet is different from the original paper, where in the original paper PSNR is 25.13,and in your paper PSNR is 25.23. I wonder what causes the difference?