DarkRoom/core/dr-face/src/lib.rs

//! Faces and identity (S14, docs/faces.md).
//!
//! Two models, run over the native render, producing per face a box, five
//! landmarks, a confidence and a 512-d embedding (FR-CULL-8) — and then the
//! arithmetic that turns embeddings into people (FR-CULL-9, FR-CULL-10). Two
//! more, optional, read each face's eyes and whether sunglasses hide them
//! (FR-CULL-8a, [`classify`] and [`eyes`]).
//!
//! Like `dr-segment`, this crate is **device-free**: no GPU adapter, no
//! Slint, nothing that needs a display. Unlike `dr-segment`, it carries **no
//! weights at all**, and the absence is deliberate — see [`the licence
//! note`](#the-weights-are-not-in-this-repository) below.
//!
//! # The weights are not in this repository
//!
//! The models this crate is built for — SCRFD-500MF and ArcFace/MobileFaceNet
//! — are InsightFace's, and their pretrained weights carry a **non-commercial
//! research-only** grant. That is incompatible with GPL-3.0-or-later and with
//! every channel DarkRoom ships through, so the weights cannot be committed
//! here the way `dr-segment`'s can, and there is no `embedded-model` feature
//! for a packaging script to switch on. The application obtains a model at
//! runtime; this crate takes bytes and never fetches anything.
//!
//! docs/faces.md §2 is the full reading, including what would have to change
//! for that to stop being true. The eye-state models are the exception: MIT,
//! weights and all, and shipped in `models/face/` (docs/faces.md §17).
//!
//! # Why the runtime is split behind a feature
//!
//! [`calibrate`], [`cluster`] and [`assign`] are where this subsystem's accuracy
//! actually lives, and all three are pure arithmetic over embeddings with no
//! model in them.
//! They build and test without `inference`, on synthetic embeddings, on a
//! machine with no weights on it — which is what lets CI cover the part most
//! likely to be subtly wrong.

pub mod align;
pub mod assign;
pub mod calibrate;
#[cfg(feature = "inference")]
pub mod classify;
pub mod cluster;
#[cfg(feature = "inference")]
pub mod detect;
#[cfg(feature = "inference")]
pub mod embed;
pub mod embedding;
pub mod eyes;
#[cfg(feature = "inference")]
pub mod landmarks;
pub mod naming;
pub mod neighbours;
pub mod references;

/// Smallest long edge a face crop may be sampled from.
///
/// **A floor on the crop source, not on the detector input.** The distinction
/// is the whole of FR-CULL-8 and `docs/faces.md` §7: detection letterboxes
/// every buffer into 640×640, so its input resolution decides nothing, while
/// [`warp`] samples the 112×112 the embedder sees and so converts source
/// resolution directly into embedding quality. FR-CULL-8 requires that crop to
/// come from the native render; this is the guard that catches a caller
/// sampling from a proxy instead.
///
/// 1025 rather than 1024 because 1024 is exactly `dr_thumbs::ThumbSize::Large`,
/// the stored proxy tier a caller is most likely to reach for by mistake, so
/// the floor has to exclude it rather than admit it. Written as a minimum so
/// the test is `edge < MIN_CROP_EDGE` with no boundary to get wrong.
///
/// It is a coarse guard and deliberately so: whether any *individual* crop was
/// upsampled is answered exactly by `faces.crop_px` against [`ALIGNED_EDGE`],
/// and that is the number §7b measures. This only stops a whole pass reading
/// from the wrong tier.
pub const MIN_CROP_EDGE: u32 = 1025;

pub use align::{
    crop_box, eye_box, eye_patch, head_views, warp, warp_pixels, Aligned112, EyePatch, HeadViews,
    Pixels, Similarity, ALIGNED_EDGE, ARCFACE_TEMPLATE,
};
pub use assign::{identity_shares, RIVAL_FLOOR, TOP_MATCHES};
pub use calibrate::{Calibration, Pairs, ReliabilityBand};
#[cfg(feature = "inference")]
pub use classify::{EyeClassifier, EyeModels, SunglassesClassifier};
pub use cluster::{
    cluster, cluster_scored, split, Candidate, Cluster, Grouping, DEFAULT_MERGE_PROBABILITY,
};
#[cfg(feature = "inference")]
pub use detect::{DetectOptions, Detection, Detector};
#[cfg(feature = "inference")]
pub use embed::{Embedded, Embedder};
pub use embedding::{
    in_gallery, read_f16_bytes, Embedding, ModelId, EMBEDDING_DIM, MIN_GALLERY_QUALITY,
};
pub use eyes::{
    Eye, EyeReading, EyeState, EYES_OPEN_THRESHOLD, HIDDEN_EYE_RATIO, MIN_EYE_PX,
    MIN_EYE_SHARPNESS, SUNGLASSES_THRESHOLD,
};
#[cfg(feature = "inference")]
pub use landmarks::{Landmarker, Landmarks};
pub use naming::{name_for_instance, name_instances, NamedFace};

/// What can go wrong between an image and a face.
#[derive(Debug, thiserror::Error)]
pub enum FaceError {
    #[error("could not read model file: {0}")]
    ModelRead(#[source] std::io::Error),

    #[cfg(feature = "inference")]
    #[error("inference failed: {0}")]
    Inference(#[source] ort::Error),

    /// The graph is not the one this decoder was written for.
    ///
    /// Worth a distinct variant rather than a generic failure: the models in
    /// this space have interchangeable *shapes* and incompatible *layouts*
    /// (a YuNet export also has twelve outputs), so the failure this catches
    /// is not a crash but a page of plausible numbers.
    #[error("model does not look like {expected}: {detail}")]
    WrongModel {
        expected: &'static str,
        detail: String,
    },

    #[error("image buffer is {got} floats, expected {expected} (RGB, three per pixel)")]
    ImageShape { expected: usize, got: usize },
}

#[cfg(feature = "inference")]
impl From<dr_inference_engine::Error> for FaceError {
    fn from(e: dr_inference_engine::Error) -> Self {
        match e {
            dr_inference_engine::Error::Inference(e) => FaceError::Inference(e),
            dr_inference_engine::Error::Io(e) => FaceError::ModelRead(e),
        }
    }
}

/// Make sure `ort` has a backend, for the M1 probe example, which drives
/// `ort` directly rather than through [`detect::Detector`] so it can report
/// the raw error. Every other path goes through `dr-inference-engine`.
#[cfg(feature = "inference")]
#[doc(hidden)]
pub fn install_backend_for_probe() {
    dr_inference_engine::ensure_runtime();
}