I am trying to overfit the Yolov2 for specific items (50 in total). I have had some amount of success by training for an extended time, but is there any parameters that I can tune to make it overfit even better? Thanks.
smallesan
All 4 comments
increase the learning rate, use smaller dataset
VanitarNordic
on 16 Aug 2017
Also please tell us why do you want to overfit the YOLO. Overfitting is a nightmare in deep learning models. is there any reason?
VanitarNordic
on 19 Aug 2017
👍1
Yup, there is. Overfitting small portion of your dataset is a sanity check before you start 'heavy' training. If you are not able to overfit 10 examples something is probably wrong.
gizmoy
on 3 Dec 2017
👍3
does anybody know how to overfit the yolov2 from scratch just to prove sanity checks are really helpful? Any links, posts are appreciated.
bit-scientist
on 17 May 2018
Was this page helpful?
0 / 5 - 0 ratings
Related issues
jasleen137
路
3Comments
Mididou
路
3Comments
zihaozhang9
路
3Comments
PROGRAMMINGENGINEER-NIKI
路
3Comments
Greta-A
路
3Comments
Most helpful comment
Yup, there is. Overfitting small portion of your dataset is a sanity check before you start 'heavy' training. If you are not able to overfit 10 examples something is probably wrong.