Closed SmartPorridge closed 5 years ago
Following the shell script run_visda17_trainval_resnet152_minaug.sh
:
The learning rate is 1e-5. Layers from the pre-trained model are trained using an LR of 1e-5 * 0.1 = 1e-6.
@Britefury
Yeah, you are right, it's 1e-6, and it keeps 1e-6 till the end?
I modefied your code to video action recognition task, but I got a terrible result. Could you give some advice on which parameters I need to change in the shell script for video action recognition task?
Thank you for your great work. Best Regards!
The learning rate is held constant throughout training, yes.
I don't know how to best modify it for video recognition! It may be not at all well suited to this task.
Best of luck.
Hi, If I have a pretrained model, the lr should be 1e-4*0.1 = 1e-5, and then the lr keeps 1e-5 till the end of the training?
Thank you.