-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
how to specify the traing param lr and lr_step #50
Comments
Hi,
|
@xingyizhou thank you. |
@xingyizhou The learning rate 5e-4 is set for batchsize 128 on 8 GPUs (batchsize 16 on each GPU). If I use 2 GPUs and batchsize is 40, should I set |
Anybody knows why? |
I can see the loss with this cmd: |
i modify the code to train my data on detection. 280 classes, 80,000 images, and run the cmd below.
but the param lr and lr_step, i can not find a good value.
when the program run for 7 days (k80, slow),
the program runs using nohup, and i can not see the loss and progress.
only when load the the model best, i can find the model best is on the 75th epoch.
it does not update for two days, and it can not go further about 50 epoches.
The text was updated successfully, but these errors were encountered: