ContinualAI/avalanche
Voir sur GitHubUnbalanced Steps Sizes Option for Benchmarks Generators
Open
#331 ouverte le 23 févr. 2021
BenchmarksFeature - Low Prioritygood first issue
Métriques du dépôt
- Stars
- (1 516 stars)
- Métriques de merge PR
- (Aucune PR mergée en 30 j)
Description
I noticed it is quite tricky at the moment to generate a benchmark with an unbalanced number of examples for each step. It would be nice to have an option in ni_scenario, nc_scenario and similar to set the number of examples for each step.