search

bennetthardwick / darknet.js

A NodeJS wrapper of pjreddie's darknet / yolo.
65 stars 27 forks source link

Less accurate detection compare to darknet project #24

Closed MaDumont closed 5 years ago

MaDumont commented 5 years ago

Hi,

I trained some darknet weights to detect a specific object. When I use the darknet project with my camera the detection is really great.

./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights

But when I use those same weights and config within my nodejs project, I have difficulty detecting the same object. It work if the object is close to the camera, but when it's a little bit far it doesn't detect anything. I use the node opencv4nodejs to capture the picture from my camera. I tested with the example with opencv4nodejs.

Do you have an idea of what could cause that issue?

bennetthardwick commented 5 years ago

The detection options in the demo.c file are nms = 0.4, thres = 0, hier = 0.5.

Can you try darknet.detect(frame, { nms: 0.4, thresh: 0 }). I'm not really sure what the options do (other than thresh), but it'll make it a lot more sensitive at least.

Other stuff that the demo.c file seems to do is remember the state of the previous frame before doing the next detection.

MaDumont commented 5 years ago

Decreasing the threshold help detecting better, but it also bring the problem of false detection.

But I'm not sure to know why I need a really low threshold. I use the same setup and with demo.c I get 80% detection and with this I get between 5% and 2%.

bennetthardwick commented 5 years ago

I'm a bit stumped on this. I think it's got something to do with the avg_detections method inside the demo.c file, but I don't have much capacity to look into it at the moment.

I am curious however, is it just your own weights that you have the problem with? Or does it happen with the example ones as well?

MaDumont commented 5 years ago

I just tested with my own weights. I will test it with the example weights and give you feed back.

MaDumont commented 5 years ago

I tested with yolov3-tiny weights and cfg because that's with those file I trained my own weights. I couldn't test with the normal yolov3 because of some issues with my computer. I didn't saw that much difference of accuracy of detection. So I feel it's related to my weights. I'm gonna try to figure it out what it could be.

bennetthardwick commented 5 years ago

I feel like there might be a small difference between the opencv that darknet uses and opencv4nodejs, which means the images aren't 100% identical. Maybe you can try retraining your weights and add random noise to the images?

MaDumont commented 5 years ago

Hummmm ok yeah I'm gonna try that.