louyanyang
louyanyang
@eric612 hi,, recently, gaussian yolov3 has a considerable gain, do you have a plan of caffe version?
hi, @eric612 , i'm reading region_loss_layer.cpp、yolov3_layer.cpp in your implementation and comparing region_layer.c 、yolo_layer.c in darknet. i find a difference about "logistic_gradient": yolov2,in your implementation and darknet, the way using logistic_gradient...
hi, @eric612 i'm very glad to find this repo suppports giou loss and ae layer. when the performance report can be provided and how much the gain in contrast to...
@cdcseacave hi, it's success when building static lib and exe, but is error when building shared one. Is there any advice you'd like to give me? my env: -- Boost...
Hi, i have implemented this paper from mxnet to caffe and it has 7% gain at [email protected] when num_deformable_group = 1, channel = 18. But, it has poor performance when...
hi @Tramac , thanks for your job. i have reproduced the miou(54.3%) and pa(92.1%) at cropsize=768 . but i want to know whether you reproduce the paper's result(68.0%) or not.