search

foolwood / DCFNet

DCFNet: Discriminant Correlation Filters Network for Visual Tracking
MIT License
215 stars 66 forks source link

training process question #15

Closed 522545707 closed 6 years ago

522545707 commented 6 years ago

Hello,when I run the train_DCFNet.m,the display content in command window is like this:

train: epoch 08: 226/572: 84.8 (84.8) HZ objective: 44.632 train: epoch 08: 227/572: 84.8 (84.8) HZ objective: 44.628 train: epoch 08: 228/572: 84.8 (84.8) HZ objective: 44.549 train: epoch 08: 229/572: 84.8 (84.8) HZ objective: 44.570 ......

the last value are always between 44 and 46,no obvious increase or decrease,I am not sure is it normal? I use a subset of VID,the first 100 files in the first folder.

Thanks for your attention.

foolwood commented 6 years ago

Sorry for such a late reply. Maybe the subset is too small. The objectives should below 10. You can use the whole training set with less RAM via the PyTorch implementation. https://github.com/foolwood/DCFNet_pytorch