[package] authors = ["nathanielsimard "] categories = ["science"] description = "Library with simple dataset APIs for creating ML data pipelines" documentation = "https://docs.rs/burn-dataset" edition.workspace = true keywords = ["deep-learning", "machine-learning", "data"] license.workspace = true name = "burn-dataset" readme.workspace = true repository = "https://github.com/tracel-ai/burn/tree/main/crates/burn-dataset" version.workspace = true [lints] workspace = true [features] default = ["sqlite-bundled"] doc = ["default"] tracing = [ "burn-std/tracing", ] audio = ["hound"] builtin-sources = ["vision", "dep:tar", "nlp"] fake = ["dep:fake"] network = ["dep:burn-std"] sqlite = ["__sqlite-shared", "dep:rusqlite"] sqlite-bundled = ["__sqlite-shared", "rusqlite/bundled"] vision = ["dep:flate2", "dep:globwalk", "dep:image", "network"] nlp = ["dep:zip", "dep:encoding_rs"] # internal __sqlite-shared = [ "dep:r2d2", "dep:r2d2_sqlite", "dep:serde_rusqlite", "dep:image", "dep:gix-tempfile", ] dataframe = ["dep:polars", "dep:planus"] [dependencies] burn-std = { path = "../burn-std", version = "=0.21.0-pre.2", optional = true, features = [ "network", ] } csv = { workspace = true } derive-new = { workspace = true } dirs = { workspace = true } fake = { workspace = true, optional = true } flate2 = { workspace = true, optional = true } gix-tempfile = { workspace = true, optional = true } globwalk = { workspace = true, optional = true } hound = { workspace = true, optional = true } image = { workspace = true, optional = true } planus = { workspace = true, optional = true } encoding_rs = { workspace = true, optional = true } polars = { workspace = true, optional = true } r2d2 = { workspace = true, optional = true } r2d2_sqlite = { workspace = true, optional = true } rand = { workspace = true, features = ["std", "sys_rng"] } zip = { workspace = true, optional = true } rmp-serde = { workspace = true } rusqlite = { workspace = true, optional = true } sanitize-filename = { workspace = true } serde = { workspace = true, features = ["std", "derive"] } serde_json = { workspace = true, features = ["std"] } serde_rusqlite = { workspace = true, optional = true } strum = { workspace = true } tar = { workspace = true, optional = true } tempfile = { workspace = true } thiserror = { workspace = true } [dev-dependencies] fake = { workspace = true } rayon = { workspace = true } rstest = { workspace = true } [package.metadata.cargo-udeps.ignore] normal = ["strum", "strum_macros"] [package.metadata.docs.rs] features = ["doc"] rustdoc-args = ["--cfg", "docsrs"]