Abhishek Pal

Results 20 comments of Abhishek Pal

I am getting an error ` Fix VGG16 layers.. Fixed. iter: 20 / 70000, total loss: 0.839219 >>> rpn_loss_cls: 0.482955 >>> rpn_loss_box: 0.259976 >>> loss_cls: 0.071895 >>> loss_box: 0.024393 >>>...

Do you want to run the demo or do you want the pretrained VGG model to start training? the pretrained vgg for training can be downloaded here : https://drive.google.com/file/d/0ByuDEGFYmWsbNVF5eExySUtMZmM/view You...

Same problem. Any solution? Any help would be appreciated. @acgtyrant @kduy

Yeah first it gives a runtime warning: ``` RuntimeWarning: invalid value encountered in greater_equal keep = np.where((ws >= min_size) & (hs >= min_size))[0] ```

Yeah I am using 2.7. You are running it on your own dataset?

Yeah but what all do I have to adjust? I just changed the classes in pascal_voc.py and prepared the dataset according to the Pascal VOC 2007 set.

https://github.com/rbgirshick/py-faster-rcnn/issues/65 Could you take a look at this issue ?

@acgtyrant going by https://github.com/longcw/faster_rcnn_pytorch/blob/master/faster_rcnn/network.py#L109 as far as I understood if the totalnorm becomes very large, then the norm gets really small and underflow occurs? Is that correct?