rankit 0.1.0

Learning to Rank: differentiable ranking, LTR losses (RankNet, LambdaRank, ApproxNDCG, ListNet, ListMLE), trainers, and IR evaluation metrics

rankit

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 5 feature flags, 2 of them enabled by default.

default

eval (default)

losses (default)

This feature flag does not enable additional features.

gumbel

parallel

serde