Replies: 1 comment
-
In Chapter 2, it’s just finding (classifying) the regional boundary of blobs. So, we don’t need to use higher learning rates (0.01, 0.001, etc.) as model and dataset aren't complex. Setting a lower learning rate helps the model converge faster, while higher learning rates make the model converge slower. Setting the learning rate depends on the usage of data and the complexity of the model. In your case, you can use 0.1 with fewer epochs to see results, or set 0.01 with more epochs. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
The learning rate in classification in Chapter 2 is set to 0.1
I try to use 0.01, seems it does not work.
Any explanation why it needs to set to 0.1?
Beta Was this translation helpful? Give feedback.
All reactions