Replies: 1 comment
-
Hi @vokcow ,
|
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.
-
Hello,
First of all, many thanks for Auto3dSeg, it is an amazing new feature of MONAI. I have some questions:
Say I would like to use the same (custom) loss function for all the algos, how do I specify that? Is it trhoguh set_training_params() method?
Therefore, I would assume we can specify the cross validation folds from this datalist file, as for each training sample a fold is specified. However, it seems that the number of splits is determined by AutoRunner() and set to a default of 5, and modificable via the method
What is the purpose of the "fold" fields in the datalist file then?
Many thanks in advance,
Victor
Beta Was this translation helpful? Give feedback.
All reactions