he010103

Results 4 issues of he010103

Hi, @bertinetto Undefined function or variable 'dist'. Error in create_logisticloss_label (line 11) dist_from_origin = dist([i j], 'label_origin');

代码中有一步是对 global_feat 和 排序的part_feat concat,然后进行200类的分类。但是不同图片的part_feat是按照得分来排序的,不是按照身体部位来排序的,所以存在特征不对齐的问题。有可能图a是: 头,腿,胸,身体,图b是胸,头,腿,身体。我这里尝试把concat换成add会训练更稳定一点,性能有小的提升!

@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], ^...

@jwyang 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], ^...