Gradient checkpointing technique for Model Agnostic Meta Learning
Project description
PyTorch implementation of Model Agnostic Meta Learning with gradient checkpointing. Allows you to perform way (~10-100x) more MAML steps with the same GPU memory budget.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torch_maml-1.0.tar.gz
(9.7 kB
view hashes)