In chapter 5 we used categorical cross-entropy as the loss function for a multiclass classifier. This is just another multiclass classifier and we can continue using categorical cross-entropy as our loss function, and accuracy as a metric. We've moved on to using images as input, but luckily our cost function and metrics remain unchanged.
Cost function and metrics
Get Deep Learning Quick Reference now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
