search

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.73k stars 7.96k forks source link

Where to find the .cfgs of the compared networks? #2233

Open May-forever opened 5 years ago

May-forever commented 5 years ago

Dear AlexeyAB, @AlexeyAB Sorry to bother you, but I really need your help.

1. In Figure 5(a) of paper 'You only look once: unified, real-time object detection', you compared YOLO with DPM，Poselets and RCNN. However, I did not find the .cfgs and weights of DPM，Poselets and RCNN in darknet-master, could please tell me where to download them?

2. The second question is what's the meaning of 'Best F1' ? Please see Figure 5(b).

3. How do you get the 11 points of the PR value? By changing a special threshold 11 times ?

I am looking forward to hearing from you, thank you very much in advance.

With best regards

AlexeyAB commented 5 years ago

@hjm1990818 Hi,

  1. All mAP and speed are taken from referenced artices (authors of DPM, RCNN, ...)

    • DPM isn't a neural network
    • RCNN is based on Caffe framework and very very slow

  2. https://en.wikipedia.org/wiki/F1_score that you see as F1-score when run ./darknet detector map ...

  3. I sort all detections by Confidence-score, then go through all objects and take into account only 1 detection, then 2 detections, 3 detections.... to build Precision-Recall curve, then take 11 points on it. https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173

You can look at this code: https://github.com/AlexeyAB/darknet/blob/5343aa423563c107e0071b1427ad5defc27b56d2/src/detector.c#L638-L1000