the porblem of training the model

[guangqianqin]

L:\Anaconda\envs\py3\python.exe E:/Gavin/SiamFC-PyTorch-master/siamfc/train.py
0%| | 0/6650 [00:00<?, ?it/s]Traceback (most recent call last):
File "E:/Gavin/SiamFC-PyTorch-master/siamfc/train.py", line 135, in
train(0 , 'E:\Gavin\data\ILSVRC_VID_CURATION')
File "E:/Gavin/SiamFC-PyTorch-master/siamfc/train.py", line 101, in train
for i, data in enumerate(tqdm(trainloader)):
File "L:\Anaconda\envs\py3\lib\site-packages\tqdm_tqdm.py", line 1005, in iter
for obj in iterable:
File "L:\Anaconda\envs\py3\lib\site-packages\torch\utils\data\dataloader.py", line 501, in iter
return _DataLoaderIter(self)
File "L:\Anaconda\envs\py3\lib\site-packages\torch\utils\data\dataloader.py", line 289, in init
w.start()
File "L:\Anaconda\envs\py3\lib\multiprocessing\process.py", line 105, in start
self._popen = self._Popen(self)
File "L:\Anaconda\envs\py3\lib\multiprocessing\context.py", line 212, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "L:\Anaconda\envs\py3\lib\multiprocessing\context.py", line 313, in _Popen
return Popen(process_obj)
File "L:\Anaconda\envs\py3\lib\multiprocessing\popen_spawn_win32.py", line 66, in init
reduction.dump(process_obj, to_child)
File "L:\Anaconda\envs\py3\lib\multiprocessing\reduction.py", line 59, in dump
ForkingPickler(file, protocol).dump(obj)
_pickle.PicklingError: Can't pickle <class 'Transaction'>: attribute lookup Transaction on builtins failed
Traceback (most recent call last):
File "", line 1, in
File "L:\Anaconda\envs\py3\lib\multiprocessing\spawn.py", line 106, in spawn_main
exitcode = _main(fd)
File "L:\Anaconda\envs\py3\lib\multiprocessing\spawn.py", line 116, in _main
self = pickle.load(from_parent)
EOFError: Ran out of input

[mellthebs]

Run this program in linux would fix it, pytorch implements different solutions in function DataLoaderIter ,so it can't work well in windows.

[guangqianqin]

Thanks a lot!

…

------------------ 原始邮件 ------------------ 发件人: "mellthebs"; 发送时间: 2019年7月5日(星期五) 下午5:22 收件人: "StrangerZhang/SiamFC-PyTorch"; 抄送: "guangqianqin"<[email protected]>;"Author"; 主题: Re: [StrangerZhang/SiamFC-PyTorch] the porblem of training the model(#23) Run this program in linux would fix it, pytorch implements different solutions in function DataLoaderIter ,so it can't work well in windows. &mdash; You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

[briliantnugraha]

Hi, in case that you are still interested to run it in Windows 10 again.
Here is a tested solution ( I have tested it on 3 PC with AMD/intel CPU and NVIDIA GPUS, so just give it a shot...).

To fix the issue, change your num_worker in config.py to 0 so that it will use the main thread (only one process) ->(multithreading/process related error is a common issue in Window).