cascade-rcnn_Pytorch

cascade-rcnn_Pytorch copied to clipboard

https://github.com/guoruoqian/cascade-rcnn_Pytorch/blob/947ebe93b9431c1dd654a54024c902d4386f030e/lib/model/rpn/anchor_target_layer_fpn.py#L120

SunAnLan

@guoruoqian HI 在**proposal_target_layer.py**中，在选择负样本时，用的函数是： ``` rand_num = np.floor(np.random.rand(bg_rois_per_this_image) * bg_num_rois) 　 rand_num = torch.from_numpy(rand_num).type_as(gt_boxes).long() bg_inds = bg_inds[rand_num] ``` 其中， `rand_num = np.floor(np.random.rand(bg_rois_per_this_image) * bg_num_rois) 　` 其结果会有重复数字，即导致重复采样．**为什么要设置成重复采样呢？？** 在py-faster-rcnn中，采样时 `npr.choice(bg_inds, size=bg_rois_per_this_image, replace=False)` 通过`replace=False`的设置来刻意避免重复采样． many...

foralliance

sh make.sh error

2

@guoruoqian I use python2.7(anaconda) and CUDA9.0 and sm_52(TITAN Xp) when I run sh make.sh, error occurs: ``` /mnt/lustre/hezhiqun/experiments/detection/cascade-rcnn_Pytorch/lib/model/nms/src/nms_cuda.c: In function ‘nms_cuda’: /mnt/lustre/hezhiqun/experiments/detection/cascade-rcnn_Pytorch/lib/model/nms/src/nms_cuda.c:14:22: error: dereferencing pointer to incomplete type boxes_host->size[0], ^...

he010103

@guoruoqian HI 在对偏移量对normalization时， 1. 在caffe源码中，3个stage用了3组不同的参数． 2. 在您的代码中，3个stage共用1组参数 共用1组参数的目的是什么呢？

foralliance

i can run test_net.py，but when i changed the code about faster_rcnn to fpn in demo.py, there someting wrong

lymoon3129