pip install mxnet-cu100 == 1.5.0

[FZhao-chd]

Hello, my computer is configured as follows, mxnet: pip install mxnet-cu100 == 1.5.0, the problems that occur during training are as follows：
Traceback (most recent call last):
File "D:/07_CodeFire/Flow-Guided-Feature-Aggregation-master/experiments/fgfa_rfcn/fgfa_rfcn_end2end_train_test.py", line 20, in
train_end2end.main()
File "D:/07_CodeFire/Flow-Guided-Feature-Aggregation-master/experiments/fgfa_rfcn....\fgfa_rfcn\train_end2end.py", line 178, in main
config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step)
File "D:/07_CodeFire/Flow-Guided-Feature-Aggregation-master/experiments/fgfa_rfcn....\fgfa_rfcn\train_end2end.py", line 171, in train_net
arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch)
File "D:/07_CodeFire/Flow-Guided-Feature-Aggregation-master/experiments/fgfa_rfcn....\fgfa_rfcn\core\module.py", line 997, in fit
self.set_params(arg_params, aux_params)
File "E:\04_anaconda\envs\py27\lib\site-packages\mxnet\module\base_module.py", line 699, in set_params
allow_extra=True)
TypeError: init_params() got an unexpected keyword argument 'allow_extra'
[01:40:59] C:\Jenkins\workspace\mxnet-tag\mxnet\src\engine\threaded_engine_perdevice.cc:99: Ignore CUDA Error [01:40:59] c:\jenkins\workspace\mxnet-tag\mxnet\3rdparty\mshadow\mshadow./tensor_gpu-inl.h:35: Check failed: e == cudaSuccess: CUDA: initialization error
[01:40:59] C:\Jenkins\workspace\mxnet-tag\mxnet\src\engine\threaded_engine_perdevice.cc:99: Ignore CUDA Error [01:40:59] c:\jenkins\workspace\mxnet-tag\mxnet\3rdparty\mshadow\mshadow./tensor_gpu-inl.h:35: Check failed: e == cudaSuccess: CUDA: initialization error