Could you please provide pretrained Mobilenetv2 model?

[yanliv]

I have tried to train SNIPER_Mobilenetv2 with my own datasets ,but I got this error:

Traceback (most recent call last):
  File "main_train.py", line 92, in <module>
    sym = sym_inst.get_symbol_rpn(config) if config.TRAIN.ONLY_PROPOSAL else sym_inst.get_symbol_rcnn(config)
  File "/home/neuiva1/yanli/001github_project/SNIPER.mobilenet/symbols/faster/mobilenetv2_e2e.py", line 379, in get_symbol_rcnn
    name='multi_proposal_target')
  File "<string>", line 107, in MultiProposalTarget
  File "SNIPER-mxnet/python/mxnet/_ctypes/symbol.py", line 135, in _symbol_creator
    s._compose(name=name, **kwargs)
  File "SNIPER-mxnet/python/mxnet/symbol/symbol.py", line 481, in _compose
    self.handle, name, num_args, keys, args))
  File "SNIPER-mxnet/python/mxnet/base.py", line 149, in check_call
    raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [10:13:00] src/core/symbolic.cc:72: Symbol.ComposeKeyword argument name crowd_boxes not found.
Candidate arguments:
	[0]cls_prob
	[1]bbox_pred
	[2]im_info
	[3]gt_boxes
	[4]valid_ranges

This seems because the layers name you setted in you code is not match with the downloaded pretrained model in MXNet Zoo. I find some people got the same problem, so could you please provide your pretrained Mobilenetv2 model?