object-detection Inference on FLIR video

Hi @enesozi,

I was wondering if you have tried running inference on the frames of FLIR thermal video. I tried doing that using my trained weights and also yours, and for some reason, none of the weights are able to detect anything. Wanted to know if someone had a success with your trained weights. Thanks!

Apr 29 '20 06:04 Pari-singh

Hi, No, I didn't try that, yet, I'd expect the model to detect objects since it has already seen some of the frames during training.

Apr 29 '20 09:04 enesozi

@Pari-singh I encountered the same situation, the variable "detections" returned from "darknet.detect_image()" seems to always be a empty array (Not None) with zero length.

May 01 '20 12:05 supercrazysam

Hi,

I am facing same kind of problem. I tried to predict the objects on single images from both the train and testing dataset of FLIR. But unfortunately, prediction image is not showing any detection. I checked the number of detection boxes, it shows a large number 2750(!), but no boxes are drawn on the predicted image. If anyone can help, that will be really great.

Apr 27 '22 07:04 nkhan076