OSError: [Errno 12] Cannot allocate memory

[Lmoer]

epoch: 2 iter: 659/662 lr: 0.006748 loss: 0.5660 (0.4378)
epoch: 2 iter: 660/662 lr: 0.006748 loss: 0.3179 (0.4366)
epoch: 2 iter: 661/662 lr: 0.006748 loss: 0.4615 (0.4369)
epoch: 2 iter: 662/662 lr: 0.006748 loss: 0.6110 (0.4386)
Traceback (most recent call last):
File "main_gpu.py", line 190, in
main()
File "main_gpu.py", line 123, in main
for i, (inputs, target) in enumerate(dataset_loader):
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 193, in iter
return _DataLoaderIter(self)
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 469, in init
w.start()
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/multiprocessing/process.py", line 105, in start
self._popen = self._Popen(self)
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/multiprocessing/context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/multiprocessing/context.py", line 277, in _Popen
return Popen(process_obj)
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/multiprocessing/popen_fork.py", line 20, in init
self._launch(process_obj)
File "/home/lijingyuan/.conda/envs/deeplabv3/lib/python3.6/multiprocessing/popen_fork.py", line 67, in _launch
self.pid = os.fork()
OSError: [Errno 12] Cannot allocate memory

I have train 2 epochs,but it shows 'Cannot allocate memory'.how to handle with this error?

[jmzelectronica]

Your cuda memory is not enough for your dataset, change your batchsize.