soft-nms icon indicating copy to clipboard operation
soft-nms copied to clipboard

Object Detection

Results 19 soft-nms issues
Sort by recently updated
recently updated
newest added

Can you please explain the calculation of the iou within lines **73 - 79**. To me all those _+1_ additions in the calculations of the box areas don't seem to...

Hi @bharatsingh430 , I wish to know if you have tested the performance of Softnms on dataset with non-overlap objects(considering that objects are not overlaped), can it still be better...

Wonderful work. My platform is Windows 10+caffe+py-R-FCN and it works well. In order to use soft-nms, I added the code in nms_wrapper.py, cpu_nms.py and config.py following your guide. Then compile...

I have read seriously README.md and i still don't know how to run it, anyone could list the runing steps, thanks.

I am trying to integrate this implementation with TF.NMS implementation but I have no idea how to do so since TF implementation use tensors ?

I found if i use the soft_nms, i should set the USE_GPU_NMS: false. If I did not set the variable, your soft_nms does not work. I find there is just...

The previous code will swap the current box with the last box if the confidence score of previous box falls below threshold. However, it does not check the confidence score...

I implement soft-nms in SSD(caffe), code link [modify detection_output.cu, bbox_util.hpp, bbox_util.cpp](https://github.com/ujsyehao/hardcaffe), I ensure the custom implementation version is the same as author-provided python version(I have tested it use fake input)...

@bharatsingh430 Hi, I struggle on the problem of the title and I just git clone the updated caffe posted by you. Could u please to help me?