training stops due to NaN loss value
12 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
The training process stops due NaN loss... How to avoid this to complete the training ..and what is the possible issue that causses..
5 Commenti
Chunru
il 23 Ago 2022
try "dbstop error" and then run the program. Check if the network output is 0. There might be a problem if network output is 0 since entropy loss has term of T*log(Y) where T is target and Y is the network output.
Risposte (1)
Shoaib Ali
il 24 Ago 2022
2 Commenti
Chunru
il 25 Ago 2022
"dbstop error" can be used in command line before you train the network. Then it should stop when error occurs and then you check out what is wrong at which part of program.
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!