Closed srp-31 closed 5 years ago
Hi @srp-31 ,
There is a paper I reference in the blog post where researchers have done a speed/accuracy comparison of ssd and yolo on a dataset for the object detection task. I believe their insights will be useful for your questions.
http://arxiv.org/abs/1611.10012
[1] J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer, Z. Wojna, Y. Song, S. Guadarrama, and K. Murphy, “Speed/accuracy trade-offs for modern convolutional object detectors,” in IEEE CVPR, 2017, pp. 1–21.
Hi Victor
Thank you for the speedy reply. I was looking for it all over and somehow missed it.
I closed it thinking it might have a comparison with yolo. But unfortunately this paper does not deal with yolo. There is however already some work in thsi regards:-
http://cs231n.stanford.edu/reports/2017/posters/225.pdf
I am going to try and get in touch with them. I will update on the issue about my progress.
thanks a lot.
shreeraman
Hi srp-31, I am also training a yolo model by using this dataset. Have you got success in it ?
Hi ghffarpk,
I suspended training yolo since the resutls form victor's code meets my requirement. I will update you if I train yolo for the dataset.
goodluck.
Hi Victor and others,
Has anyone trained the recent yolo(v1 v2 or v3) on the ego hands dataset and can probile provide a absic comparison in terms of speed and accuracy?
thanks in advanace shreeraman