momo1986 opened a new issue #14672: Is it possible for mxnet to save the best 
model and early stopping
URL: https://github.com/apache/incubator-mxnet/issues/14672
 
 
   Hello, thanks for sharing the framework.
   
   I want to do some objection task based on the finetuned mxnet official SSD 
model.
   
   I observe that after several epochs, the cross-entropy loss and smooth L1 
loss will no longer be reduced. 
   
   How can I save the best epochs and stop early instead of saving the 
parameters when the setting epochs is over?
   
   Thanks & regards!

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to