search

rbgirshick / py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
Other
8.13k stars 4.11k forks source link

Error about train py-faster-rcnn with end2end. #807

Open crazyLeeab opened 6 years ago

crazyLeeab commented 6 years ago

Beacause some matter about numpy version,I changed the type into int and when I modified the code that "fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image.astype(np.int)#modify",then the error was appeared. Please give me suggestion,thx a lot.

I0416 21:20:02.793213 5832 layer_factory.cpp:58] Creating layer roi-data File "D:\py-faster-rcnn\tools..\lib\rpn\proposal_target_layer.py", line 69 labels, rois, bbox_targets, bbox_inside_weights = _sample_rois(all_rois, gt_boxes, fg_rois_per_image,rois_per_image, self._num_classes) ^ SyntaxError: invalid syntax Traceback (most recent call last): File "./tools\train_net.py", line 115, in max_iters=args.max_iters) File "D:\py-faster-rcnn\tools..\lib\fast_rcnn\train.py", line 160, in train_net pretrained_model=pretrained_model) File "D:\py-faster-rcnn\tools..\lib\fast_rcnn\train.py", line 46, in init self.solver = caffe.SGDSolver(solver_prototxt) SystemError: NULL result without error in PyObject_Call

HilmiK commented 6 years ago

could you solve the problem ?

Leebanana commented 5 years ago

I met the same problem，do you have fixed it?