Open Cadene opened 6 years ago
I may have found a fix: _allowed_border = 50
https://github.com/longcw/faster_rcnn_pytorch/blob/master/faster_rcnn/rpn_msr/anchor_target_layer.py#L69
I hope it will converge nicely.
Have you fix this problem? I have the same question and change the _allowed_border from 0 to 50 dose not solve it.Though I use the code in tensorflow. it will be so great if you can tell me how to fix it. Thanks so much.
In my case, this error occurs when there is no gt box. (I am using a custom dataset) Removing such samples from the dataset fixed the problem.
@SilencerChen @Jongchan hi,I met the same problem,did you fix it?can you tell me how to solve it? thanks so much!!!!
hi, everybody, I met the same problem, what caused my program occured error is that my DataFrame contains np.NAN. Hope it will help you! :-) ps: I'm not using faster_rcnn_pytorch, I'm just operating the DataFram.
I am trying to train a model on my custom dataset (formatted like Pascal VOC). The model is training for several iterations and then this error occurs.
Obviously it is due to the fact that
all_anchors
contains anchors which are not "inside the image". https://github.com/longcw/faster_rcnn_pytorch/blob/master/faster_rcnn/rpn_msr/anchor_target_layer.py#L118 I can't figure out how to fix this...