Task-Informed Meta-Learning applied to the Omniglot dataset. This dataset must be downloaded into the omniglot folder.
Anaconda running python 3.6 is used as the package manager. To get set up with an environment, install Anaconda from the link above, and (from this directory) run
conda env create -f environment.yml
This will create an environment named timl-omniglot
with all the necessary packages to run the code. To
activate this environment, run
conda activate timl-omniglot
The main script to train the models is then run.py
, with the model configurations controlled by the config
.