ContinualAI/avalanche
Auf GitHub ansehenUnbalanced Steps Sizes Option for Benchmarks Generators
Open
#331 geöffnet am 23. Feb. 2021
BenchmarksFeature - Low Prioritygood first issue
Repository-Metriken
- Stars
- (1.516 Stars)
- PR-Merge-Metriken
- (Keine gemergten PRs in 30 T)
Beschreibung
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.