holmes-alan/abpn

Attention based Back Projection Network (ABPN) for image ultra-resolution in ICCV2019

abpn's Issues

Memory error

Thank you for the great work and sharing the code!
However, when I adopt space attention in other SR models, there is no problem in training, but will have memory error in validation phase.
Can u help me solve this problem? Thanks!

ValueError: operands could not be broadcast together with shapes (2032,1348) (1348,2032)

Dear author,
I ran the code "python main_4x.py" successfully, but when I ran "eval_4x.py", error occured. I cannot find the reason of this problem. Could you please help me solve this problem?

multi-upscales and split_img_tensor

Hello!

First I want to thank you for the great work and code, I was recently trying to understand what self-attention blocks did in SISR tasks, and it's very interesting to see ways in which it can be used with amazing results.

I did want to ask a question, about the reason images are flipped and rotated before averaging them at inference time. I did test and upscaling only once can result in artifacts in some of the chopped patches, which are smoothed when all 8 upscales are aggregated. The question is if there's an explanation behind the artifacts and the other is about the logic behind the 8 flipped-rotated upscales. I also tested the same forward chop with other models and seams are much more apparent in other cases than in ABPN, which leads me to believe upscales are more consistent (particularly at the edges), but I was wondering about those artifacts.

Another comment is about split_img_tensor(), which is great on it's own to deal with limited VRAM, but I found it to be slow for some reason. I haven't done much debugging, but I did test swapping it out with patchify_tensor() from https://github.com/sunreef/BlindSR/blob/master/src/image_utils.py and it was much faster for me, with the same behavior, in case you want to test it out.

Cheers!

About model structure

Nice work.While, the model structure is not clear according the paper downloaded from arxiv. According the code in main_4x.py, the model ABPNv5 is the used model, which is far from the model described in the paper. As the 'weight_up', 'weight_down' are not mentioned in the paper, which introduce much skip connections between BP stages. Can author give an explanation for this problem?

issues while testing using demo_8x.py

Firstly, thanks for your efforts and the code. While trying to test the model using demo_8x,py it gives an error of importing ABPN_v6 that when I trace the error in the model.py file, I found no class in that was found.

Error when running python demo_4x.py

Hi Guys!

Thanks for the code.
I am having an issue when executing python demo_4x.py

I am running it on windows, it is not specified in the page.
Any idea how to solve this ?

Thanks in advance,

Regards

===> Building model ABPN
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:38:48.846 : Params number: 2514757
20-08-06 11:38:48.847 : LR
20-08-06 11:38:48.847 : Result
20-08-06 11:38:48.847 : ---1--> LR\téléchargement.jpg
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:38:52.695 : Params number: 2514757
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:38:52.760 : Params number: 2514757
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:38:52.777 : Params number: 2514757
Pre-trained SR model is loaded.
LogHandlers setup!
Pre-trained SR model is loaded.
LogHandlers setup!
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:38:52.785 : Params number: 2514757
20-08-06 11:38:52.834 : LR
20-08-06 11:38:52.834 : LR
20-08-06 11:38:52.834 : LR
20-08-06 11:38:52.937 : LR
20-08-06 11:38:52.938 : Result
20-08-06 11:38:52.938 : Result
20-08-06 11:38:52.939 : Result
20-08-06 11:38:52.939 : Result
20-08-06 11:38:52.940 : ---1--> LR\téléchargement.jpg
Traceback (most recent call last):
20-08-06 11:38:52.942 : ---1--> LR\téléchargement.jpg
20-08-06 11:38:52.940 : ---1--> LR\téléchargement.jpg
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
20-08-06 11:38:52.941 : Params number: 2514757
20-08-06 11:38:52.942 : Params number: 2514757
20-08-06 11:38:52.941 : ---1--> LR\téléchargement.jpg
20-08-06 11:38:53.012 : LR
20-08-06 11:38:53.012 : LR
20-08-06 11:38:53.013 : Result
20-08-06 11:38:53.013 : Result
20-08-06 11:38:53.014 : ---1--> LR\téléchargement.jpg
20-08-06 11:38:53.015 : ---1--> LR\téléchargement.jpg
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
Traceback (most recent call last):
File "", line 1, in
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
Traceback (most recent call last):
return _run_module_code(code, init_globals, run_name,
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
exitcode = _main(fd, parent_sentinel)
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
exec(code, run_globals)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
Traceback (most recent call last):
Traceback (most recent call last):
_fixup_main_from_path(data['init_main_from_path'])
return _run_module_code(code, init_globals, run_name,
Traceback (most recent call last):
File "", line 1, in
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
_run_code(code, mod_globals, init_globals,
exitcode = _main(fd, parent_sentinel)
return _run_module_code(code, init_globals, run_name,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
exec(code, run_globals)
prepare(preparation_data)
_run_code(code, mod_globals, init_globals,
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
_fixup_main_from_path(data['init_main_from_path'])
exec(code, run_globals)
eval()
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
main_content = runpy.run_path(main_path,
return _run_module_code(code, init_globals, run_name,
pred, time = chop_forward(LR, model, start, end)
main_content = runpy.run_path(main_path,
eval()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
return _run_module_code(code, init_globals, run_name,
_run_code(code, mod_globals, init_globals,
for iteration, batch in enumerate(test_dataloader, 1):
return _run_module_code(code, init_globals, run_name,
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
_run_code(code, mod_globals, init_globals,
exec(code, run_globals)
_run_code(code, mod_globals, init_globals,
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
exec(code, run_globals)
eval()
exec(code, run_globals)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
eval()
pred, time = chop_forward(LR, model, start, end)
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
for iteration, batch in enumerate(test_dataloader, 1):
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
return _MultiProcessingDataLoaderIter(self)
return _MultiProcessingDataLoaderIter(self)
return _MultiProcessingDataLoaderIter(self)
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
return _MultiProcessingDataLoaderIter(self)
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
w.start()
w.start()
w.start()
w.start()
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
self._popen = self._Popen(self)
self._popen = self._Popen(self)
self._popen = self._Popen(self)
self._popen = self._Popen(self)
self._popen = self._Popen(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
return _default_context.get_context().Process._Popen(process_obj)
return _default_context.get_context().Process._Popen(process_obj)
return _default_context.get_context().Process._Popen(process_obj)
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
return Popen(process_obj)
return Popen(process_obj)
return Popen(process_obj)
return Popen(process_obj)
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prep_data = spawn.get_preparation_data(process_obj._name)
prep_data = spawn.get_preparation_data(process_obj._name)
prep_data = spawn.get_preparation_data(process_obj._name)
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
prep_data = spawn.get_preparation_data(process_obj._name)
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
_check_not_importing_main()
_check_not_importing_main()
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
raise RuntimeError('''
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
raise RuntimeError('''
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.RuntimeError:
    An attempt has been made to start a new process before the
    current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.RuntimeError:
    An attempt has been made to start a new process before the
    current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.    raise RuntimeError('''

RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.RuntimeError:
    An attempt has been made to start a new process before the
    current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Traceback (most recent call last):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 761, in _try_get_data
data = self._data_queue.get(timeout=timeout)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\queues.py", line 108, in get
raise Empty
_queue.Empty

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "demo_4x.py", line 205, in
eval()
File "demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
File "demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 345, in next
data = self._next_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 841, in _next_data
idx, data = self._get_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 808, in _get_data
success, data = self._try_get_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 774, in _try_get_data
raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str))
RuntimeError: DataLoader worker (pid(s) 9020, 18452, 18360, 2696, 14664, 16972) exited unexpectedly

(leotorch) C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master>python demo_4x.py
===> Building model ABPN
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:40:59.937 : Params number: 2514757
20-08-06 11:40:59.937 : LR
20-08-06 11:40:59.938 : Result
20-08-06 11:40:59.938 : ---1--> LR\téléchargement.jpg
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
===> Building model ABPN
Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:41:03.180 : Params number: 2514757
20-08-06 11:41:03.180 : LR
20-08-06 11:41:03.180 : Result
20-08-06 11:41:03.181 : ---1--> LR\téléchargement.jpg
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Pre-trained SR model is loaded.
LogHandlers setup!
20-08-06 11:41:03.249 : Params number: 2514757
20-08-06 11:41:03.250 : LR
20-08-06 11:41:03.251 : Result
20-08-06 11:41:03.252 : ---1--> LR\téléchargement.jpg
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
Pre-trained SR model is loaded.
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
LogHandlers setup!
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
20-08-06 11:41:03.293 : Params number: 2514757
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
20-08-06 11:41:03.294 : LR
20-08-06 11:41:03.295 : Result
return _MultiProcessingDataLoaderIter(self)
20-08-06 11:41:03.296 : ---1--> LR\téléchargement.jpg
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
Pre-trained SR model is loaded.
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
LogHandlers setup!
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

20-08-06 11:41:03.317 : Params number: 2514757
20-08-06 11:41:03.318 : LR
20-08-06 11:41:03.319 : Result
20-08-06 11:41:03.319 : ---1--> LR\téléchargement.jpg
Pre-trained SR model is loaded.
LogHandlers setup!
Traceback (most recent call last):
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
Pre-trained SR model is loaded.
exitcode = _main(fd, parent_sentinel)
LogHandlers setup!
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
20-08-06 11:41:03.329 : Params number: 2514757
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
20-08-06 11:41:03.330 : LR
20-08-06 11:41:03.331 : Result
_fixup_main_from_path(data['init_main_from_path'])
20-08-06 11:41:03.331 : ---1--> LR\téléchargement.jpg
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
20-08-06 11:41:03.335 : Params number: 2514757
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
20-08-06 11:41:03.336 : LR
exec(code, run_globals)
20-08-06 11:41:03.338 : Result
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
20-08-06 11:41:03.338 : ---1--> LR\téléchargement.jpg
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
Traceback (most recent call last):
self._popen = self._Popen(self)
File "", line 1, in
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
prepare(preparation_data)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.
return _run_module_code(code, init_globals, run_name,

File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
Traceback (most recent call last):
File "", line 1, in
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
exec(code, run_globals)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
eval()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
Traceback (most recent call last):
File "", line 1, in
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 116, in spawn_main
prepare(preparation_data)
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
exitcode = _main(fd, parent_sentinel)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 125, in _main
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
prepare(preparation_data)
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 236, in prepare
return _run_module_code(code, init_globals, run_name,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
self._popen = self._Popen(self)
main_content = runpy.run_path(main_path,
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 265, in run_path
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
_run_code(code, mod_globals, init_globals,
return _run_module_code(code, init_globals, run_name,
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 97, in _run_module_code
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
exec(code, run_globals)
_run_code(code, mod_globals, init_globals,
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\runpy.py", line 87, in _run_code
eval()
_check_not_importing_main()
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval
exec(code, run_globals)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 205, in
raise RuntimeError('''
for iteration, batch in enumerate(test_dataloader, 1):
eval()
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.  File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in __iter__

File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 102, in eval

return _MultiProcessingDataLoaderIter(self)

File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
pred, time = chop_forward(LR, model, start, end)
File "C:\Users\leoso\OneDrive\Documents\Notebooks\SuperResolution\ABPN-master\demo_4x.py", line 184, in chop_forward
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 279, in iter
self._popen = self._Popen(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 719, in init
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
w.start()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\process.py", line 121, in start
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
self._popen = self._Popen(self)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 224, in _Popen
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\context.py", line 326, in _Popen
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
return Popen(process_obj)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\popen_spawn_win32.py", line 45, in init
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.
prep_data = spawn.get_preparation_data(process_obj._name)

File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Traceback (most recent call last):
File "demo_4x.py", line 205, in
eval()
File "demo_4x.py", line 102, in eval
pred, time = chop_forward(LR, model, start, end)
File "demo_4x.py", line 184, in chop_forward
for iteration, batch in enumerate(test_dataloader, 1):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 345, in next
data = self._next_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 841, in _next_data
idx, data = self._get_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 808, in _get_data
success, data = self._try_get_data()
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\site-packages\torch\utils\data\dataloader.py", line 761, in _try_get_data
data = self._data_queue.get(timeout=timeout)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\queues.py", line 107, in get
if not self._poll(timeout):
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\connection.py", line 257, in poll
return self._poll(timeout)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\connection.py", line 330, in _poll
return bool(wait([self], timeout))
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\connection.py", line 879, in wait
ready_handles = _exhaustive_wait(waithandle_to_obj.keys(), timeout)
File "C:\Users\leoso\Anaconda3\envs\leotorch\lib\multiprocessing\connection.py", line 811, in _exhaustive_wait
res = _winapi.WaitForMultipleObjects(L, False, timeout)