Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CIFAR10-100 Split #131

Closed
vlomonaco opened this issue Oct 14, 2020 · 2 comments
Closed

CIFAR10-100 Split #131

vlomonaco opened this issue Oct 14, 2020 · 2 comments
Labels
Benchmarks Related to the Benchmarks module Feature - High Priority New feature or request, high priority good first issue Good for newcomers

Comments

@vlomonaco
Copy link
Member

vlomonaco commented Oct 14, 2020

We should add the classic benchmark Cifar10-100 split described in the paper: Continual Learning Through Synaptic Intelligence.

This should be added in avalanche/benchmarks/classic as it is very used. It can be easily implemented using the method NCScenario that allows to create a sequence of tasks given multiple datasets to concatenate.

@vlomonaco vlomonaco added good first issue Good for newcomers Feature - High Priority New feature or request, high priority Benchmarks Related to the Benchmarks module labels Oct 14, 2020
@vlomonaco
Copy link
Member Author

Ops it's been already implemented here: create_cifar100_with_cifar10_pretrain_benchmark, but we should change the name of the method :)

@vlomonaco
Copy link
Member Author

Fixed by vlomonaco@d46c811

vlomonaco pushed a commit that referenced this issue Dec 20, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Benchmarks Related to the Benchmarks module Feature - High Priority New feature or request, high priority good first issue Good for newcomers
Projects
None yet
Development

No branches or pull requests

1 participant