Hi. I'm sorry to bothering you. Does this paper contain information about eigen values and rotate angles of the blur kernels in Tab.3 ? I can see just shapes.

Hi, author. Thank you for your excellent work. But I'm a little confused about the code which calculate PSNR and SSIM metric. For PSNR, why the diff is multipide by a convert coefficient and shave the border when benchmarch is set to True. For SSIM, why not directly use api from skimage? Waiting for your response, sincerely.

Hi,

I am highly interested in your work and code. I am trying to use another training dataset (SiblingsDB) to train your DASR model. However, when I tried to run the main.sh file for training after I changed the dir_data to my _data_path and put my dataset in my_data_path/DF2K/HR, the following error occurs in line 65 of multiscalesrdata.py: "self.repeat = args.test_every // (len(self.images_hr) // args.batch_size) ERROR: ZeroDivisionError: integer division or modulo by zero".

Do you know what the problem is?

Thank you in advance.

Hi, thank you for this impressive work!

May I ask to which range will the converged loss value fall when training the representation network? (e.g., based on parameters in your paper, the ultimately converged loss value is less than 5, or less than 1, or 0.1 ? ) This can be helpful during training.

Thank you a lot!

作者您好！我今天想继续训练，bash文件如下所示 python main.py --dir_data='./dataset'
--model='blindsr'
--scale='2'
--blur_type='iso_gaussian'
--noise=0.0
--sig_min=0.2
--sig_max=2.0
--save='bldsr_repro2'
--resume=319 但是输出文件显示从epoch1重新开始训练了。我找不到bug在哪里，请问这是为什么呢

RuntimeError: CUDA out of memory. Tried to allocate 4.46 GiB (GPU 0; 11.00 GiB total capacity; 6.78 GiB already allocated; 2.39 GiB free; 6.79 GiB reserved in total by PyTorch) By 'nvidia-smi', my GPU memory is shown below. Why this issue happened?

I got this error while training the model using my own dataset:

F:\DASR-main\dataset\benchmark\Set14\HR F:\DASR-main\dataset\benchmark\Set14\LR_bicubic Making model... Preparing loss function: 1.000 * L1 [Epoch 1] Learning rate: 1.00e-3 Traceback (most recent call last): File "main.py", line 19, in t.train() File "F:\DASR-main\trainer.py", line 63, in train for batch, (hr, _, idx_scale) in enumerate(self.loader_train): File "C:\Users\anaconda3\envs\DASR\lib\site-packages\torch\utils\data\dataloader.py", line 582, in next return self._process_next_batch(batch) File "C:\Users\anaconda3\envs\DASR\lib\site-packages\torch\utils\data\dataloader.py", line 608, in _process_next_batch raise batch.exc_type(batch.exc_msg) ValueError: Traceback (most recent call last): File "F:\DASR-main\dataloader.py", line 38, in _ms_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "F:\DASR-main\dataloader.py", line 38, in samples = collate_fn([dataset[i] for i in batch_indices]) File "F:\DASR-main\data\multiscalesrdata.py", line 120, in getitem hr, filename = self._load_file(idx) File "F:\DASR-main\data\multiscalesrdata.py", line 154, in _load_file hr = np.load(_f)[0]['image'] File "C:\Users\anaconda3\envs\DASR\lib\site-packages\numpy\lib\npyio.py", line 444, in load raise ValueError("Cannot load file containing pickled data " ValueError: Cannot load file containing pickled data when allow_pickle=False

Hi, Longguang! Thanks for your interesting work and sharing your code! As we reproduce your code, the best PSNR results on Set14 as sigma=3.6 is 27.01 dB while what your paper claimed is 27.45 dB! I know your model can perform well as sigma is small. However, as the sigma become large, there is a big performance gap between our reproduced results and your paper giving results. My colleague also reproduce your code many times, but the same problems still exists!

The same problems seems proposed in the https://github.com/The-Learning-And-Vision-Atelier-LAVA/DASR/issues/38. So can your tell me the error of our training command, shown as below? If there is no problem, for your academic reputation, I hope you reproduce your code again and evaluate your model on 4x Set14! Thanks!

training: python main.py --dir_data='/media/datasets'
--model='blindsr'
--scale='4'
--blur_type='iso_gaussian'
--noise=0.0
--sig_min=0.2
--sig_max=4.0
--sig 3.6
--n_GPUs 2 test: python test.py --test_only
--dir_data='/media/datasets'
--data_test='Set14'
--model='blindsr'
--scale='4'
--resume=600
--n_GPUs=1
--save 'test'
--blur_type='iso_gaussian'
--sig=3.6