You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
And while this allows for great flexibility and control over details it might be to complicated for our users. We should look into replacing our current setup e.g. with the Adam optimizer only setting the initial learning rate and the weight decay.
We can then set these two values to reasonable defaults and users can get started without thinking too much about parameters and without having to run multiple experiments just to get basic parameters figured out.
Tasks
Implement Adam optimizer with learning rate and weight decay
Benchmark and check results; if it looks reasonable go for it
Remove sgd parameters from config; use learning rate and weight decay only
The text was updated successfully, but these errors were encountered:
At the moment we are using stochastic gradient descent and a multi-step weight decay policy.
In this setup the user has to set
robosat/robosat/tools/train.py
Lines 83 to 85 in 2067cb7
And while this allows for great flexibility and control over details it might be to complicated for our users. We should look into replacing our current setup e.g. with the Adam optimizer only setting the initial learning rate and the weight decay.
We can then set these two values to reasonable defaults and users can get started without thinking too much about parameters and without having to run multiple experiments just to get basic parameters figured out.
Tasks
The text was updated successfully, but these errors were encountered: