aoi-hosizora / ffdnet_pytorch Goto Github PK

File "E:/FFDNet_pytorch-master/ffdnet.py", line 303, in main
train(args)
File "E:/FFDNet_pytorch-master/ffdnet.py", line 109, in train
for batch_idx, batch_data in enumerate(train_dataloader):
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\site-packages\torch\utils\data\dataloader.py", line 355, in iter
return self._get_iterator()
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\site-packages\torch\utils\data\dataloader.py", line 914, in init
w.start()
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\multiprocessing\popen_spawn_win32.py", line 65, in init
reduction.dump(process_obj, to_child)
File "C:\D_installation_packet\Anaconda\installion_package\envs\Yolov5\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
BrokenPipeError: [Errno 32] Broken pipe

这个数据集如何获取，你给链接无法访问

Hi, I was wondering if you can help with implementing non-uniform noise level map in the Pytorch version. Thanks!

你好！这个project的model有没有，能不能给一份我测试一下降噪效果？谢谢！

I have a problem when running this code with cuda_enable, the error comes up with the state "Cuda running out of memory". I've been watching the process through "htop". While in the training session it took only 1GB+ , but when it trying to validate (after 5 epochs of training), the error always rises, no matter what size of my training data. DO you have any suggest to solve this problem? Thank you
FYI : My GPU has 4GB of VRAM