Code Monkey home page Code Monkey logo

york-sdcnlab / ghost-deblurgan Goto Github PK

View Code? Open in Web Editor NEW
36.0 36.0 9.0 118.89 MB

This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size and a rapid inference time. The motivation is to boost marker detection in robotic applications, however, you may use it for other applications definitely.

License: MIT License

Python 100.00%
apriltag benchmark deblurgan deblurganv2 deblurring deep-learning fiducial-markers gan ghostnet iros motion-blur motion-blur-elimination pytorch pytorch-implementation robotics

ghost-deblurgan's People

Contributors

amaldevhari avatar yorklyb avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

ghost-deblurgan's Issues

about dataset

I THINK THE TRAIN AND TEST OF THE GOPRO DATASET MAY HAVE A PROBLEM WITH CLASSIFICATION INCONSISTENCIES. Can I ask you how to deal with this dataset?

lateral2 is not matched

RuntimeError: The size of tensor a (135) must match the size of tensor b (136) at non-singleton dimension 2

test result

Does anyone reproduce the test results in the paper?PSNR:28.79 SSIM: 0.919
My test results on the GoPro dataset are PSNR: 27.53 SSIM: 0.917

'AttributeError' occurs when training

When running train.py, the following error occurs:

W0227 13:02:02.246692 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\albumentations\imgaug\transforms.py:222: FutureWarning: IAASharpen is deprecated. Please use Sharpen instead
  warnings.warn("IAASharpen is deprecated. Please use Sharpen instead", FutureWarning)

W0227 13:02:02.247689 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\albumentations\imgaug\transforms.py:165: FutureWarning: This augmentation is deprecated. Please use Emboss instead
  warnings.warn("This augmentation is deprecated. Please use Emboss instead", FutureWarning)

W0227 13:02:02.248687 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\albumentations\augmentations\transforms.py:688: FutureWarning: This class has been deprecated. Please use CoarseDropout
  warnings.warn(

W0227 13:02:02.249684 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\albumentations\augmentations\transforms.py:913: FutureWarning: This class has been deprecated. Please use ImageCompression
  warnings.warn(

I0227 13:02:02.259657 380692 dataset.py:28] Subsampling buckets from 0 to 100, total buckets number is 100
I0227 13:02:02.261652 380692 dataset.py:71] Dataset has been created with 1243 samples
I0227 13:02:02.280601 380692 dataset.py:28] Subsampling buckets from 0 to 100, total buckets number is 100
I0227 13:02:02.283593 380692 dataset.py:71] Dataset has been created with 1243 samples
W0227 13:02:02.285588 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\torchvision\models\_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.  
  warnings.warn(

W0227 13:02:02.286585 380692 warnings.py:109] D:\anaconda3\envs\deblur-gan\lib\site-packages\torchvision\models\_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG19_Weights.IMAGENET1K_V1`. You can also use `weights=VGG19_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

I0227 13:02:03.317861 380692 helpers.py:183] Loading pretrained weights from url (https://github.com/huawei-noah/CV-backbones/releases/download/ghostnet_pth/ghostnet_1x.pth)
Epoch 0, lr 0.0001:   0%|                                 | 0/2000 [00:01<?, ?it/s]Traceback (most recent call last):

  File "<string>", line 1, in <module>
Traceback (most recent call last):
  File "d:\deblur\Ghost-DeblurGAN\train.py", line 187, in <module>
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\spawn.py", line 116, in spawn_main
    trainer.train()
  File "d:\deblur\Ghost-DeblurGAN\train.py", line 40, in train
    exitcode = _main(fd, parent_sentinel)
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\spawn.py", line 126, in _main
    self._run_epoch(epoch)
  File "d:\deblur\Ghost-DeblurGAN\train.py", line 65, in _run_epoch
    self = reduction.pickle.load(from_parent)
EOFError:     Ran out of inputfor data in tq:

  File "D:\anaconda3\envs\deblur-gan\lib\site-packages\tqdm\std.py", line 1185, in __iter__
    for obj in iterable:
  File "D:\anaconda3\envs\deblur-gan\lib\site-packages\torch\utils\data\dataloader.py", line 444, in __iter__
    return self._get_iterator()
  File "D:\anaconda3\envs\deblur-gan\lib\site-packages\torch\utils\data\dataloader.py", line 390, in _get_iterator
    return _MultiProcessingDataLoaderIter(self)
  File "D:\anaconda3\envs\deblur-gan\lib\site-packages\torch\utils\data\dataloader.py", line 1077, in __init__
    w.start()
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\process.py", line 121, in start
    self._popen = self._Popen(self)
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\context.py", line 224, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\context.py", line 327, in _Popen
    return Popen(process_obj)
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\popen_spawn_win32.py", line 93, in __init__
    reduction.dump(process_obj, to_child)
  File "D:\anaconda3\envs\deblur-gan\lib\multiprocessing\reduction.py", line 60, in 
dump
    ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'get_corrupt_function.<locals>.process'  

GOPRO dataset not downloadable

I tried to download the dataset but it fails at 99% every time. My internet speed is good and of high config. Later on I found this message. Can you please mention away to download the dataset?
Thank you.
image

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.