search

PRBonn / lidar-bonnetal

Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving
http://semantic-kitti.org
MIT License
959 stars 206 forks source link

BrokenPipeError: [Errno 32] Broken pipe #82

Closed urbansound8K closed 2 years ago

urbansound8K commented 3 years ago

Traceback (most recent call last): File "", line 1, in Traceback (most recent call last): File "train.py", line 114, in File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 105, in spawn_main trainer = Trainer(ARCH, DATA, FLAGS.dataset, FLAGS.log, FLAGS.pretrained) File "../..\tasks\semantic\modules\trainer.py", line 69, in init exitcode = _main(fd) File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 115, in _main shuffle_train=True) File "../..//tasks/semantic/dataset/kitti/parser.py", line 272, in init self = reduction.pickle.load(from_parent) ModuleNotFoundError: No module named 'parserModule' self.trainiter = iter(self.trainloader) File "C:\Users*\anaconda3\envs\lidar\lib\site-packages\torch\utils\data\dataloader.py", line 352, in iter return self._get_iterator() File "C:\Users*\anaconda3\envs\lidar\lib\site-packages\torch\utils\data\dataloader.py", line 294, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "C:\Users*\anaconda3\envs\lidar\lib\site-packages\torch\utils\data\dataloader.py", line 801, in init w.start() File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) BrokenPipeError: [Errno 32] Broken pipe

any solution??

jbehley commented 3 years ago

We tested our framework under Ubuntu 18.04 or 20.04. Apparently, you are running it under Windows, which expects a different path format. The important part of the abovementioned error is:

File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 105, in spawn_main
trainer = Trainer(ARCH, DATA, FLAGS.dataset, FLAGS.log, FLAGS.pretrained)
File "../..\tasks\semantic\modules\trainer.py", line 69, in init
exitcode = _main(fd)
File "C:\Users*\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 115, in _main
shuffle_train=True)
File "../..//tasks/semantic/dataset/kitti/parser.py", line 272, in init
self = reduction.pickle.load(from_parent)
ModuleNotFoundError: No module named 'parserModule'

I fixed this error by using os.path.join to account for the difference between ../..//tasks/semantic/dataset/kitti/parser.py, which is a valid path under unix-based operating systems, and ..\..\tasks\semantic\dataset\kitti\parser.py, which is a valid path under windows. Let us know if this fix resolves your issue.

urbansound8K commented 3 years ago

aaaaaaa

the path is fine as you can see but the problem is still there?

urbansound8K commented 3 years ago

Traceback (most recent call last): File "train.py", line 114, in File "C:\Users\3DFRAhmed\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 105, in spawn_main trainer = Trainer(ARCH, DATA, FLAGS.dataset, FLAGS.log, FLAGS.pretrained) File "....\tasks\semantic\modules\trainer.py", line 73, in init exitcode = _main(fd) File "C:\Users\3DFRAhmed\anaconda3\envs\lidar\lib\multiprocessing\spawn.py", line 115, in _main shuffle_train=True) File "....\tasks\semantic\dataset\kitti\parser.py", line 274, in init self = reduction.pickle.load(from_parent) AttributeError: Can't get attribute 'SemanticKitti' on <module 'parser' (built-in)> self.trainiter = iter(self.trainloader)

I am getting this error?

jbehley commented 3 years ago

It's hard for me to diagnose the problem as I haven't a Windows environment setup. We run the code mainly under Ubuntu 20.04 or 18.04. Sorry that we cannot provide support for Windows.

urbansound8K commented 3 years ago

thanks

I was able to run the code on Ubuntu

do you have any idea how to measure the distance of detected objects? I mean how to display the distance of an object after the segmentation?