HelloRicky123 / Siamese-RPN

Full reimplementation of siamese rpn, has 0.24 eao on vot2017.
MIT License
223 stars 44 forks source link

About the loss #14

Closed feiaxyt closed 5 years ago

feiaxyt commented 5 years ago

You did a good work. I also implemented the training code, but I always get a higher loss in the validation set compared to the training set. The performance on the OTB dataset is not good. Do you have this problem? Whats the values of your loss of the regression and classification branch, respectively?