strange output

[vcvishal]

when I run this code the following output is given C:\Users\HI\Desktop\ature-master>python main.py Total Params: 31042434 [0, 0, 0, 0] what is it, how I get the correct output I am using windows

[sraashis]

• Total Params: 31042434 is the number of parameters in UNET. It is printed at the end of unet/module.py file
• [0, 0, 0, 0] is supposed to be the precision , recall and accuracy on all of the test dataset. Which I guess is empty in your case. It is at the end of unet/init.py file.

[vcvishal]

i am not sure where i am doing wrong would you please help me path is incorrect? image not found? or else?

[sraashis]

Just wanted to make sure. Are you trying on DRIVE dataset or your own dataset?

[vcvishal]

yes i am using DRIVE

this time Total Params: 31042434

SPLIT FOUND: data\DRIVE\splits\UNET-DRIVE.json Loaded

CRITICAL!!! logs\DRIVE\UNET-DRIVE-TEST.csv" already exists.

Override? [Y/N]: y

CRITICAL!!! logs\DRIVE\UNET-DRIVE-TRAIN.csv" already exists.

Override? [Y/N]: y

CRITICAL!!! logs\DRIVE\UNET-DRIVE-VAL.csv" already exists.

Override? [Y/N]: y

GPU not found.

Patches: 135 Patches: 9 Patches: 9 Patches: 9 Patches: 9 Patches: 9 Training... Traceback (most recent call last): File "C:\Users\vcvis\Desktop\ature-master\testarch\unet__init.py", line 44, in run epoch_run=drive_trainer.epoch_ce_loss) File "C:\Users\vcvis\Desktop\ature-master\nbee\torchbee.py", line 82, in train epoch_run(epoch=epoch, data_loader=data_loader) File "C:\Users\vcvis\Desktop\ature-master\nbee\torchbee.py", line 210, in epoch_ce_loss for i, data in enumerate(kw['data_loader'], 1): File "D:\miniconda\lib\site-packages\torch\utils\data\dataloader.py", line 819, in iter__ return _DataLoaderIter(self) File "D:\miniconda\lib\site-packages\torch\utils\data\dataloader.py", line 560, in init w.start() File "D:\miniconda\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "D:\miniconda\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\miniconda\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "D:\miniconda\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "D:\miniconda\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) _pickle.PicklingError: Can't pickle <function at 0x00000264BA7F5598>: attribute lookup on testarch.unet.runs failed [0, 0, 0, 0]

C:\Users\vcvis\Desktop\ature-master>Total Params: 31042434 Traceback (most recent call last): File "", line 1, in File "D:\miniconda\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "D:\miniconda\lib\multiprocessing\spawn.py", line 115, in _main self = reduction.pickle.load(from_parent) EOFError: Ran out of input

error might be due to multi threading issue where should i modifier for it

[vcvishal]

thank you problem solved by setting number of workers =0

[sraashis]

Awesome, Thanks for pointing out. I never ran in CPU so hadn't encounter it before.