Shouldn't it always decrease?

Epoch: 5        LR: 0.200000
539000/539999
Train cls error:    72.2433%    Train error: 453062.6250
Test cls error:     72.7121%    Test error:  50700.2773 Best test cls
error: 72.7121% Best test error: 50700.2773

Epoch: 6        LR: 0.200000
539000/539999
Train cls error:    72.4259%    Train error: 453240.4062
Test cls error:     72.8555%    Test error:  50749.9102 Best test cls
error: 72.7121% Best test error: 50700.2773


Unrelated question -- has ocropus ever been trained on dataset the
size of NIST? I have 4 GB and ocropus crashes with out of memory error
on a dataset with 16k examples (during feature extraction phase)
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"ocropus" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/ocropus?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to