Struct LayoutModel 

pub struct LayoutModel { /* private fields */ }

Implementations

impl LayoutModel

pub fn load() -> Result<Self, String>

Load the ONNX model from DOCLING_LAYOUT_ONNX. Without the override, prefers models/layout_heron_int8.onnx when present (the quantized default; DOCLING_RS_FP32=1 opts out), else models/layout_heron.onnx.

pub fn load_with(intra: usize) -> Result<Self, String>

Like load but with an explicit intra-op thread count. A parallel page-worker pool loads its helper models on a single thread each and gets its speed-up from running pages concurrently instead.

pub fn predict_fp32_fallback( &mut self, img: &RgbImage, page_w: f32, page_h: f32, ) -> Result<Option<Vec<Region>>, String>

Re-run one page through the fp32 graph — the escape hatch for a page whose int8 detections look implausible (see fp32_path). Ok(None) when there is nothing to escalate to: fp32 already loaded, an explicit model override, or no fp32 file on disk.

pub fn predict( &mut self, img: &RgbImage, page_w: f32, page_h: f32, ) -> Result<Vec<Region>, String>

Detect layout regions on a page image. page_w/page_h are the page size in points; returned boxes are in those coordinates.

pub fn predict_batch( &mut self, pages: &[(&RgbImage, f32, f32)], ) -> Result<Vec<Vec<Region>>, String>

Detect layout regions on several page images with one inference call (issue #73). The ONNX export has a dynamic batch dimension, so a worker can amortize the per-run framework overhead and keep its cores busier on multi-page documents. Results are per-image, index-aligned with pages, and identical to calling predict per page.