ForkingPickler(file, protocol).dump(obj) AttributeError: Can't pickle local object 'main.<locals>.<lambda>'

[QuincyQAQ]

Why do I get the following error when I set numworkers to 10 (by default):

Traceback (most recent call last):
File "D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\train_semseg.py", line 294, in
main(args)
File "D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\train_semseg.py", line 180, in main
for i, (points, target) in tqdm(enumerate(trainDataLoader), total=len(trainDataLoader), smoothing=0.9):
File "D:\Anaconda\envs\y8\lib\site-packages\torch\utils\data\dataloader.py", line 438, in iter
return self._get_iterator()
File "D:\Anaconda\envs\y8\lib\site-packages\torch\utils\data\dataloader.py", line 386, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\Anaconda\envs\y8\lib\site-packages\torch\utils\data\dataloader.py", line 1039, in init
w.start()
File "D:\Anaconda\envs\y8\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "D:\Anaconda\envs\y8\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\Anaconda\envs\y8\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(process_obj)
File "D:\Anaconda\envs\y8\lib\multiprocessing\popen_spawn_win32.py", line 93, in init
reduction.dump(process_obj, to_child)
File "D:\Anaconda\envs\y8\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'main..'

And when I set numworkers to 0, an error will be reported:

D:\Anaconda\envs\y8\python.exe D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\train_semseg.py
PARAMETER ...
Namespace(batch_size=16, decay_rate=0.0001, epoch=32, gpu='0', learning_rate=0.001, log_dir=None, lr_decay=0.7, model='pointnet_sem_seg', npoint=4096, optimizer='Adam', step_size=10, test_area=5)
start loading training data ...
[nan nan nan nan nan nan nan nan nan nan nan nan nan]
Totally 0 samples in train set.
start loading test data ...
[nan nan nan nan nan nan nan nan nan nan nan nan nan]
Totally 0 samples in test set.
0it [00:00, ?it/s]
D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\data_utils\S3DISDataLoader.py:37: RuntimeWarning: invalid value encountered in divide
labelweights = labelweights / np.sum(labelweights)
0it [00:00, ?it/s]
The number of training data is: 0
The number of test data is: 0
No existing model, starting training from scratch...
**** Epoch 1 (1/32) ****
Learning rate:0.001000
BN momentum updated to: 0.100000
0it [00:00, ?it/s]
Traceback (most recent call last):
File "D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\train_semseg.py", line 295, in
main(args)
File "D:\Pointnet_Pointnet2_pytorch-master\Pointnet_Pointnet2_pytorch-master\train_semseg.py", line 204, in main
log_string('Training mean loss: %f' % (loss_sum / num_batches))
ZeroDivisionError: division by zero