https://github.com/PaddlePaddle/PGL/blob/main/examples/graphsage/train.py

图神经网络官方例子运行报错， window10下，conda

Connected to pydev debugger (build 201.7846.77)
[INFO] 2020-12-03 09:58:45,073 [mp_reader.py: 23]: ujson not install, fail back to use json instead
[INFO] 2020-12-03 09:58:45,077 [ train.py: 304]: Namespace(batch_size=128, epoch=10, graphsage_type='graphsage_mean', hidden_size=128, lr=0.01, normalize=False, sample_workers=5, samples_1=25, samples_2=10, symmetry=False, use_cuda=False)
[INFO] 2020-12-03 09:58:50,935 [ train.py: 64]: Feature shape (232965, 602)
[INFO] 2020-12-03 09:59:06,757 [ train.py: 181]: preprocess finish
[INFO] 2020-12-03 09:59:06,757 [ train.py: 182]: Train Examples: 152410
[INFO] 2020-12-03 09:59:06,757 [ train.py: 183]: Val Examples: 23699
[INFO] 2020-12-03 09:59:06,758 [ train.py: 184]: Test Examples: 55334
[INFO] 2020-12-03 09:59:06,758 [ train.py: 185]: Num nodes 232965
[INFO] 2020-12-03 09:59:06,758 [ train.py: 186]: Num edges 11606919
[INFO] 2020-12-03 09:59:06,758 [ train.py: 187]: Average Degree 49.82258708389672
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\paddle\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\site-packages\paddle\reader\decorator.py", line 313, in read_worker
for d in r:
File "E:\code\paddle\PGL-main\examples\graphsage\reader.py", line 128, in work
for data in rd():
File "C:\ProgramData\Anaconda3\envs\paddle\lib\site-packages\pgl\utils\mp_reader.py", line 146, in pipe_reader
p.start()
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\popen_spawn_win32.py", line 89, in __init__
reduction.dump(process_obj, to_child)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'multiprocess_reader.._read_into_pipe'
Exception in thread Thread-13:
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\paddle\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "C:\ProgramData\Anaconda3\envs\paddle\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\site-packages\paddle\reader\decorator.py", line 313, in read_worker
for d in r:
File "E:\code\paddle\PGL-main\examples\graphsage\reader.py", line 128, in work
for data in rd():
File "C:\ProgramData\Anaconda3\envs\paddle\lib\site-packages\pgl\utils\mp_reader.py", line 146, in pipe_reader
p.start()
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\popen_spawn_win32.py", line 89, in __init__
reduction.dump(process_obj, to_child)
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'multiprocess_reader.._read_into_pipe'

[INFO] 2020-12-03 10:02:13,251 [mp_reader.py: 23]: ujson not install, fail back to use json instead
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\envs\paddle\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input

Process finished with exit code -1