show-attend-and-tell
show-attend-and-tell copied to clipboard
no validation loss
I'm pretty confused because there's no loss calculated in validation phase. Normally there should be some validation loss/accuracy/perplexity, especially for CV tasks. However there's only some NLP metrics for captions generated in validation phase.
Do we really need to calculate validation loss for the generated captions?
Hi... have implemented and computed validation loss??? Does it work?