faster_rcnn_pytorch

faster_rcnn_pytorch copied to clipboard

ROI pooling layer only supports the case that batch size equals to 1?

5

From the source code(roi_pooling_cuda.c) and my naive experiments, it seems that the RoI pooling layer only support batch size equals to one. Does anyone know why?

zfchenUnique

debug so lowlly

2

hi, @longcw , i am so appreciated with your great job. and i can run train.py and demo.py correctly. but when i remote debug the code, at first it is...

tengshaofeng

the problem with running demo.py

2

~/faster_rcnn_pytorch$ python demo.py Traceback (most recent call last): File "demo.py", line 3, in import torch File "/home/user/faster_rcnn_pytorch/lfaster_rcnn/network.py", line 1, in import torch File "/home/user/anaconda2/lib/python2.7/site-packages/torch/__init__.py", line 53, in from torch._C import...

pranerd

I have four different prior boxes (anchors) with width and length dimension a1 = (w1, l1) a2 = (w2, l2) a3 = (w3, l3) a4 = (w4, l4) how to...

YogeshShitole

ImportError: No module named gpu_nms

1

When I checked the log of ./make.sh, I found that, g++: error: unrecognized option ‘-R, how could I solve it? running build_ext cythoning utils/bbox.pyx to utils/bbox.c building 'utils.cython_bbox' extension creating...

yinst2012

Question about the reslute mAP.

7

Does anyone get the comparable mAP on VOC07 in the origin paper?

ayumiymk

ruoqianguo

I can see your SmoothL1Loss is different with the original papers. How does this compare?

anhlt

rpn_loss_box = F.smooth_l1_loss(rpn_bbox_pred, rpn_bbox_targets, size_average=False) / (fg_cnt + 1e-4) loss_box = F.smooth_l1_loss(bbox_pred, bbox_targets, size_average=False) / (fg_cnt + 1e-4) I can see regression loss divided by fg_cnt why regression loss divide...

rimchang

I'am trying to run pascal_voc.py,and I got this Error: from .imdb import imdb ValueError: Attempted relative import in non-package Then I go to imdb file and I got another Error:...

zjtgit