search

cbfinn / maml

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
MIT License
2.55k stars 604 forks source link

why add accuraciesa with accuraciesb in eval? #48

Open MarStarck opened 5 years ago

MarStarck commented 5 years ago

in my opinion, the part a is used for update initial weight and the part b is used for inner learning. So in eval, part a can be used to evaluation because the meta-learning is not trainning. But part b is used for the model training, so the accuracy should not include part b accuracy.

WHQ1111 commented 5 years ago

I think the part a is used for inner learning and the part b is used for outer learning.