Closed wdon021 closed 3 years ago
We experimented with CTC-Loss, but in the end I think we only used Softmax loss. You could set the code to use ctc metrics as loss and everyhting will be trained using CTC Loss (this file)
thank you @Bartzi for your reply,
I was trying to use that CTC Loss file, but run into
x need to be in a Variable List problem
The current input seems to be just a Variable type. is there a quick method to adopt this CTC loss? Or it will require some amount of work?
thank you again
My guess is that it should not be that difficult. But I did not use this code in 3 years.
I think you will need to adapt the number of labels. In this line the code produces a prediction for each character. If you want to use CTC you'll have to do this 2 * self.num_labels + 1
times for ctc loss.
You should not pay any attention to the comment in the file, I guess this is legacy :sweat_smile:.
@Bartzi Thank you, got it working again with some minor changes.
Hi @Bartzi, I see the repository has a
ctc_metrics.py
, and in the Recognition map there is a commentHowever, in
train_fsns.py
I don't get to see ctc loss gets to apply anywhere in the metric. Can you please help me with the question?thank you very much.