I'm training a keras model that takes item embeddings as pairs and outputs a binary classification (close to word2vec). I need to find the mAP of the model for the recommender system after each epoch in order to be able to compare. I couldn't really find a way to do it other than calculating each time from scratch with the new embeddings. I would appreciate some help if anybody has a way.
Asked
Active
Viewed 1,618 times
