Live data from Hacker News

YOLO: Real-Time Object Detection

pjreddie.com

11–20 of 63 posts

Re: YOLO: Real-Time Object Detection

#12

Suprised to see this here since YOLO has been out for a while now. Shameless plug, I wrote an article on how to use use transfer learning on your custom dataset with the pretrained weights [1]. One of the downside of YOLO is that it uses his own deep learning library darknet. I find that the Tensorflow port dark flow easier to use but it haven't seen a v3 port yet. [1] https://www.powu3.com/ml/yolo/

Chainercv seems to: https://github.com/chainer/chainercv/blob/master/README.md

Re: YOLO: Real-Time Object Detection

#13
post #3

It still seems to be using only the single frame, without past/present context. E.g. a dog sometimes is recognized as teddy bear for a split second. Is there any "continuous" models for that? Sounds like a simple bayesian post-processing would do a great deal (e.g. recording the probability of dogs mutating to teddy bears as very low).

For each frame, it returns a list of candidate detections with confidence values if I remember correctly. Should be pretty straightforward to make it smooth using that.
Post reply on HN