-
Notifications
You must be signed in to change notification settings - Fork 206
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
error stop_factor_lr #1
Comments
hello,do you rebuild the face mxnet branch and Python interface? stop_factor_lr used when we use factor lr, because factor lr will let lr be smaller and smaller, so stop_factor_lr is the min lr in the whole training. |
I just test last night using the newly build mxnet, i.e., 0.7.0 and found that the stop_factor_lr introduces the error. Maybe I should read the doc for more details. |
hello @csgcmai , the latest mxnet has support stop_factor_lr, so do can you post your error here? |
I will run this command later and then post the err msg here. Currently I simply delete that param. |
Thx your share when I run this model and I found "lr_scheduler = mx.lr_scheduler.FactorScheduler(step=5*max(int(epoch_size * 1), 1), factor=0.8, stop_factor_lr=5e-5),"
error"TypeError: init() got an unexpected keyword argument 'stop_factor_lr'" what does it mean?
and I use your mxnet version
The text was updated successfully, but these errors were encountered: