Why 20000 tasks are set, but only one batch task is used

cbfinn / maml

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

MIT License

2.56k stars 606 forks source link

Why 20000 tasks are set, but only one batch task is used #81

Open asker-github opened 4 years ago

asker-github commented 4 years ago

Hello, I saw this paper and code recently. There are many puzzles in it. I hope someone can give me some advice. The first question is:In data_ generator.py, why 20000 tasks are set, but only one batch task is used.

KDD24-ID169 commented 3 years ago

Have you figured out the reason?