AttributeError: Can't pickle local object 'preprocess_dataset.<locals>.<lambda>'

[Zbless]

hi,Please ask me a question. I really run your code on the Windows platform. When I download the data and process it, the following problems occur. How can I solve them? You know, I look forward to your reply.
Pre-processing data...
INFO:root:Processed: 0 / 133885...
Traceback (most recent call last):
File "D:/py_project/cG-SchNet/gschnet_cond_script.py", line 976, in
main(args)
File "D:/py_project/cG-SchNet/gschnet_cond_script.py", line 861, in main
load_additionally=load_additionally)
File "D:\py_project\cG-SchNet\qm9_data.py", line 109, in init
units=self.units, download=download)
File "D:\software\Anaconda3\envs\cgschnet\lib\site-packages\schnetpack\datasets_init_.py", line 56, in init
self.download()
File "D:\software\Anaconda3\envs\cgschnet\lib\site-packages\schnetpack\datasets_init_.py", line 72, in download
self._download()
File "D:\py_project\cG-SchNet\qm9_data.py", line 225, in _download
works = works and self._preprocess_qm9()
File "D:\py_project\cG-SchNet\qm9_data.py", line 336, in _preprocess_qm9
invalid_list=invalid_list)
File "D:\py_project\cG-SchNet\preprocess_dataset.py", line 425, in preprocess_dataset
threads[-1].start()
File "D:\software\Anaconda3\envs\cgschnet\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "D:\software\Anaconda3\envs\cgschnet\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\software\Anaconda3\envs\cgschnet\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "D:\software\Anaconda3\envs\cgschnet\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "D:\software\Anaconda3\envs\cgschnet\lib\multiprocessing\reduction.py", line 62, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'preprocess_dataset..'

[NiklasGebauer]

Hi,
it seems as if the multi-threading in the pre-processing does not work on your machine (not sure if it is a problem of packages or Windows in general as I only tested the code on Linux systems).
You can deactivate the multi-threading by setting n_threads=0 in line 310 of qm9_data.py:

cG-SchNet/qm9_data.py

Line 310 in 53d7383

n_threads=8, n_mols_per_thread=125, logging_print=True,

Pre-processing will take a bit longer but this should prevent the error.

[Zbless]

Thank you very much. It works