My command in terminal is: python datasets/combine_A_and_B.py --fold_A ./train --fold_B ./val --fold_AB ./results and there is error message shown below [fold_A] = ./train [fold_B] = ./val [fold_AB] = ./results [num_imgs] = 1000000 [use_AB] = False Traceback (most recent call last): File "datasets/combine_A_and_B.py", line 23, in img_list = os.listdir(img_fold_A) NotADirectoryError: [Errno 20] Not a directory: './train/2163.jpg'

Can anyone please help m with this? Thank you.

When I run train.py in command line,I meet this problem. What shold I do?

(E:\programs\Anaconda\envs\python) D:\cv2\DeblurGAN-master>python train.py --dataroot blurred_sharp/ --continue_train ------------ Options ------------- batchSize: 1 beta1: 0.5 checkpoints_dir: ./checkpoints continue_train: True dataroot: blurred_sharp/ dataset_mode: aligned display_freq: 100 display_id: 1 display_port: 8097 display_single_pane_ncols: 0 display_winsize: 256 epoch_count: 1 fineSize: 256 gan_type: wgan-gp gpu_ids: [0] identity: 0.0 input_nc: 3 isTrain: True lambda_A: 100.0 lambda_B: 10.0 learn_residual: False loadSizeX: 640 loadSizeY: 360 lr: 0.0001 max_dataset_size: inf model: content_gan nThreads: 2 n_layers_D: 3 name: experiment_name ndf: 64 ngf: 64 niter: 150 niter_decay: 150 no_dropout: False no_flip: False no_html: False norm: instance output_nc: 3 phase: train pool_size: 50 print_freq: 100 resize_or_crop: resize_and_crop save_epoch_freq: 5 save_latest_freq: 5000 serial_batches: False which_direction: AtoB which_epoch: latest which_model_netD: basic which_model_netG: resnet_9blocks -------------- End ---------------- CustomDatasetDataLoader dataset [AlignedDataset] was created Traceback (most recent call last): File "train.py", line 56, in model = create_model(opt) File "D:\cv2\DeblurGAN-master\models\models.py", line 11, in create_model model.initialize(opt) File "D:\cv2\DeblurGAN-master\models\conditional_gan_model.py", line 34, in initialize opt.which_model_netG, opt.norm, not opt.no_dropout, self.gpu_ids, use_parallel, opt.learn_residual) File "D:\cv2\DeblurGAN-master\models\networks.py", line 52, in define_G netG.cuda(device_id=gpu_ids[0]) TypeError: cuda() got an unexpected keyword argument 'device_id'

Just like the above image, the grid effect exists in the generate images, which make the generate images seem to be not natural. Would you meet this situation, and how to fix it?

Thank you.

I meet the error util/html.py", line 1, in import dominate ModuleNotFoundError: No module named 'dominate'

By the way, if I want to run it on CPU,where I need to change?

Thank you.

I encountered the following error when using wgan-gp as discriminator and everything went well whe using other discriminator: Traceback (most recent call last): File "train.py", line 42, in model.optimize_parameters() File "/home/gasoon/code/research/VideoDeblur/models/conditional_gan_model.py", line 136, in optimize_parameters self.backward_D() File "/home/gasoon/code/research/VideoDeblur/models/conditional_gan_model.py", line 110, in backward_D self.loss_D.backward() File "/home/gasoon/anaconda3/envs/vd/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/gasoon/anaconda3/envs/vd/lib/python3.6/site-packages/torch/autograd/init.py", line 89, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed. Specify retain_graph=True when calling backward the first time.

I'm using the data generated by myself whose resolution is 640*480. Does anyone know the way to solve it? Thank you so much!

Hello, I test the model on my images (1333x764) using following command , but I get 256x256 deblurred images, how can I get deblurred images of original resolution ？

python test.py --dataroot /.path_to_your_data --model test --dataset_mode single --learn_residual

It seems that the model cropped the image ，but i dont know how to avoid it.

Hello! When I run train.py in command line,I meet this problem. What shold I do?

python test.py --dataroot ./test --model test --dataset_mode single --learn_residual

Traceback (most recent call last): File "test.py", line 10, in from ssim import SSIM ImportError: cannot import name 'SSIM'

When I train DeblurGAN,I received this error ,while test no this error. ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /events (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f32c9ce9950>: Failed to establish a new connection: [Errno 111] Connection refused',)) How to solve this problem?

https://github.com/KupynOrest/DeblurGAN/search?utf8=%E2%9C%93&q=use_parallel&type=

https://github.com/KupynOrest/DeblurGAN/blob/master/models/test_model.py#L18

flake8 testing of https://github.com/KupynOrest/DeblurGAN on Python 2.7.14

$ flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics

./models/test_model.py:18:105: F821 undefined name 'use_parallel'
                                      opt.which_model_netG, opt.norm, not opt.no_dropout, self.gpu_ids, use_parallel,
                                                                                                        ^

Hello, I am a beginner. How can I add dataroot to the environment, and I want to turn my blurred picture into clear image. Which folder should I put into it and and what commands to input to Python?

The following is my mistake [-h] --dataroot DATAROOT [--batchSize BATCHSIZE] [--loadSizeX LOADSIZEX] [--loadSizeY LOADSIZEY] [--fineSize FINESIZE] [--input_nc INPUT_NC] [--output_nc OUTPUT_NC] [--ngf NGF] [--ndf NDF] [--which_model_netD WHICH_MODEL_NETD] [--which_model_netG WHICH_MODEL_NETG] [--learn_residual] [--gan_type GAN_TYPE] [--n_layers_D N_LAYERS_D] [--gpu_ids GPU_IDS] [--name NAME] [--dataset_mode DATASET_MODE] [--model MODEL] [--which_direction WHICH_DIRECTION] [--nThreads NTHREADS] [--checkpoints_dir CHECKPOINTS_DIR] [--norm NORM] [--serial_batches] [--display_winsize DISPLAY_WINSIZE] [--display_id DISPLAY_ID] [--display_port DISPLAY_PORT] [--display_single_pane_ncols DISPLAY_SINGLE_PANE_NCOLS] [--no_dropout] [--max_dataset_size MAX_DATASET_SIZE] [--resize_or_crop RESIZE_OR_CROP] [--no_flip] [--ntest NTEST] [--results_dir RESULTS_DIR] [--aspect_ratio ASPECT_RATIO] [--phase PHASE] [--which_epoch WHICH_EPOCH] [--how_many HOW_MANY] test.py: error: the following arguments are required: --dataroot

I am trying to run the test code but I keep getting some dependency errors which I am pretty sure is happening because I got the wrong version of some package. It would be great if you could upload the requirements text file. Thanks a lot! @KupynOrest

Thank you for your awesome code!

I am hoping you might open-source the log files you have from training. Maybe the training and validation loss as a function of epoch (and/or batch) with an estimate of the runtime?

Testing out DeblurGAN on macOS Big Sur using anaconda and python 3.7.

I got the error using the basic test command or a command with more flags with flag set for CPU:

## either command will timeout
python test.py --dataroot blur_test --model test --dataset_mode single --gpu_ids -1

python test.py --dataroot blur_test --model test --dataset_mode single --gpu_ids -1 --resize_or_crop scale_width --loadSizeX 720 --loadSizeY 960 --fineSize 720

I tried setting --nThreads 1 but got the same error. However, I was able to bypass this by adding an environment variable to the command:

### both of these commands work
OMP_NUM_THREADS=1 python test.py --dataroot blur_test --model test --dataset_mode single --gpu_ids -1

OMP_NUM_THREADS=1 python test.py --dataroot blur_test --model test --dataset_mode single --gpu_ids -1 --resize_or_crop scale_width --loadSizeX 720 --loadSizeY 960 --fineSize 720

Any way to avoid this error?

Here is the full error and traceback:

model [TestModel] was created
[2021-11-11 15:22:47,942] WARNING: Setting up a new session...
[2021-11-11 15:22:47,961] INFO: Visdom successfully connected to server
[W ParallelNative.cpp:214] Warning: Cannot set number of intraop threads after parallel work has started or after set_num_threads call when using native parallel backend (function set_num_threads)
[2021-11-11 15:22:48,107] DEBUG: STREAM b'IHDR' 16 13
[2021-11-11 15:22:48,108] DEBUG: STREAM b'pHYs' 41 9
[2021-11-11 15:22:48,109] DEBUG: STREAM b'IDAT' 62 380148
^CTraceback (most recent call last):
  File "test.py", line 31, in <module>
    for i, data in enumerate(dataset):
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1186, in _next_data
    idx, data = self._get_data()
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1152, in _get_data
    success, data = self._try_get_data()
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 990, in _try_get_data
    data = self._data_queue.get(timeout=timeout)
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/multiprocessing/queues.py", line 104, in get
    if not self._poll(timeout):
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/multiprocessing/connection.py", line 257, in poll
    return self._poll(timeout)
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/multiprocessing/connection.py", line 414, in _poll
    r = wait([self], timeout)
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/multiprocessing/connection.py", line 921, in wait
    ready = selector.select(timeout)
  File "/opt/anaconda3/envs/DEBLURGAN/lib/python3.7/selectors.py", line 415, in select
    fd_event_list = self._selector.poll(timeout)
KeyboardInterrupt