subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1

[MrLinNing]

File "/DATE/env/lib/python3.5/site-packages/torch/utils/cpp_extension.py", line 949, in _build_extension_check=True)
File "/usr/lib/python3.5/subprocess.py", line 708, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1

[donnyyou]

https://github.com/donnyyou/torchcv

[MrLinNing]

Thank you ! How to fix this bug?

File "main.py", line 185, in <module>
runner = runner_selector.seg_runner()
File "/torchcv/runner/runner_selector.py", line 104, in seg_runner
return SEG_METHOD_DICT[key](self.configer)
File "/torchcv/runner/seg/fcn_segmentor.py", line 45, in __init__
self._init_model()
File "/torchcv/model/seg/nets/pspnet.py", line 83, in __init__
self.valid_loss_dict = LOSS_TYPE[configer.get('loss', 'loss_type')]
NameError: name 'LOSS_TYPE' is not defined

[donnyyou]

I have updated the code!