I'm curious how the pre-built neural network has been trained in
ocropus 0.3. The reason is that I get misidentification on noiseless
input, and wondering whether it's due to insufficient training, or to
overall design of NN and features.

For instance the cost of outputting 6 is lower than cost of outputting
0 on the following image (6.28 vs 6.12)
http://yaroslavvb.com/upload/run-run/zero-fail.png

--~--~---------~--~----~------------~-------~--~----~
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