You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm training a network with CTC. The loss improves over time but the network only predicts blank characters (greedy decoding). Currently, the input sequence is 4 to 5 times as long as the target sequence.
Do you have any suggestions on how to fix this?
The text was updated successfully, but these errors were encountered:
I'm training a network with CTC. The loss improves over time but the network only predicts blank characters (greedy decoding). Currently, the input sequence is 4 to 5 times as long as the target sequence.
Do you have any suggestions on how to fix this?
The text was updated successfully, but these errors were encountered: