a-PyTorch-Tutorial-to-Image-Captioning icon indicating copy to clipboard operation
a-PyTorch-Tutorial-to-Image-Captioning copied to clipboard

Published 20 hours ago • verified publisher icon sgrvinod

Query

Open malikfahadsarwar opened this issue 11 months ago • 0 comments

can you explain that do we use the teacher forcing in the validation phase EVEN with no parmater update in order to compute the cross entropy loss like we do in training to measure model performance in terms of overfitting,underfitting,generalization not used the autoregressive technique in the validation set? autoregressive is ONLY used in test phase not in validation? THANKS

malikfahadsarwar avatar Nov 21 '24 04:11 malikfahadsarwar