search

AntreasAntoniou / HowToTrainYourMAMLPytorch

The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
https://arxiv.org/abs/1810.09502
Other
773 stars 137 forks source link

One question about Line 314 in meta_neural_network_architectures.py #22

Open haichaoyu opened 5 years ago

haichaoyu commented 5 years ago

Hi Antreas,

Thanks for your excellent work and code. Here is a question about Line 314 in meta_neural_network_architectures.py. Why is self.weight always used even if params is not None?

AntreasAntoniou commented 5 years ago

Good catch. That block is legacy code prior to my mechanism for explicit selection of what parameters should be optimized in the inner loop. It should really be identical to how MetaBatchNorm works.