语义分割代码实现时，出现好多错误，有代码级需要单独配置的，也有环境方面的。
1.如下面，代码之类。直接调代码即ok
【Traceback (most recent call last):
File "evaluate.py", line 6, in <module>
from networks.CE2P import Res_Deeplab
File "/networks/CE2P.py", line 13, in <module>
from libs import InPlaceABN, InPlaceABNSync
File "libs/__init__.py", line 9, in <module>
from networks import Res_Deeplab
ImportError: cannot import name 'Res_Deeplab'
】
2.下面之类错误， 因为cuda版本与 pytorch可能不一致 。之前 cuda10，装cuda9，就ok了
【
Traceback (most recent call last):
File "train.py", line 13, in <module>
from networks.CE2P import Res_Deeplab
File "networks/CE2P.py", line 13, in <module>
from libs import InPlaceABN, InPlaceABNSync
File "/libs/__init__.py", line 1, in <module>
from .bn import ABN, InPlaceABN, InPlaceABNWrapper, InPlaceABNSync, InPlaceABNSyncWrapper
File "/libs/bn.py", line 15, in <module>
from .functions import inplace_abn, inplace_abn_sync
File "libs/functions.py", line 5, in <module>
from . import _ext
File "libs/_ext/__init__.py", line 3, in <module>
from .__ext import lib as _lib, ffi as _ffi
ImportError: /libs/_ext/__ext.so: undefined symbol: __cudaPopCallConfiguration
】
https://github.com/liutinglt/CE2P
