关于运行Faster Rcnn 训练出错

按照之前博文 的 Win10 + Matlab2017 + Cuda8.0 +Caffe +faster ，跑demo时没有错误，但是训练出现如下错误：

Error using caffe_
glog check error, please check log and clear mex

Error in caffe.get_solver (line 7)
pSolver = caffe_('get_solver', solver_file);

Error in caffe.Solver (line 21)
        self = caffe.get_solver(varargin{:});

Error in proposal_train (line 49)
    caffe_solver = caffe.Solver(opts.solver_def_file);% 第一次报错

Error in Faster_RCNN_Train.do_proposal_train (line 7)
    model_stage.output_model_file = proposal_train(conf, dataset.imdb_train, dataset.roidb_train, ...

Error in script_faster_rcnn_VOC0712_VGG16 (line 50)
model.stage1_rpn            = Faster_RCNN_Train.do_proposal_train(conf_proposal, dataset,
model.stage1_rpn, opts.do_val);

经过进一步查看log，获得如下信息：

F1203 10:07:42.648193  6884 layer.hpp:385] Check failed: ExactNumBottomBlobs() == bottom.size() (2 vs. 3) S