search

xiaochus / YOLOv3

Keras implementation of yolo v3 object detection.
MIT License
605 stars 264 forks source link

Detection accuracy is not equal to darknet #8

Open surajitkundu29 opened 6 years ago

surajitkundu29 commented 6 years ago

I have used my own weights and configuration file. But while I am testing with new images the darknet can detect 4 objects where keras can detect only 2. Do you know the reason behind this ?

SagiShaashua commented 6 years ago

I'm having the similar issue - I am using the same weights and the same cfg as the Darknet one... and i can't get the same results. For one example while Darknet detected a car with 99% the this one had only 26%... what is the difference between the two?

Did you find a solution?

Thanks