Configure CL Dataset

The continual learning dataset is a sequence of datasets corresponding to continual learning tasks, each of which has their own training and test data. If you are not familiar with continual learning datasets, feel free to get some knowledge from my CL beginner’s guide about CL dataset.

Configure CL Dataset

To configure the continual learning dataset for your experiment, link the /cl_dataset field in the experiment index config to a YAML file in cl_dataset/ subfolder of your configs. That YAML file should use _target_ field to link to a CL dataset class (as shown in source code: clarena/cl_datasets/) and specify its arguments in the following field. Here is an example:

./clarena/example_configs
├── __init__.py
├── entrance.yaml
├── experiment
│   ├── example.yaml
│   └── ...
├── cl_dataset
│   └── permuted_mnist.yaml
...

example_configs/experiment/example.yaml

defaults:
  ...
    - /cl_dataset: permuted_mnist.yaml
  ...

example_configs/cl_dataset/permuted_mnist.yaml

_target_: clarena.cl_datasets.PermutedMNIST
root: data/MNIST
num_tasks: 10
validation_percentage: 0.1
batch_size: 128
permutation_mode: first_channel_only

Supported CL Dataset List

In this package we implemented many CL dataset classes in clarena.cl_datasets module that you can use for your experiment. Below is the full list. Please refer to the API reference of each class to learn its required arguments.

API Reference (CL Datasets) Source Code

CL Dataset	Description
Permuted MNIST	A MNIST variant for CL by random permutation of the input pixels to form different tasks.
Split CIFAR100	A CIFAR-100 variant for CL by splitting by class.