Struct SLANetModel 

pub struct SLANetModel { /* private fields */ }

Pure SLANet model implementation.

Implementations

impl SLANetModel

pub fn new( inference: OrtInfer, normalizer: NormalizeImage, input_shape: InputShape, ) -> SLANetModel

Creates a new SLANet model.

pub fn input_shape(&self) -> &InputShape

Returns the input shape of this model.

pub fn preprocess( &self, images: Vec<ImageBuffer<Rgb<u8>, Vec<u8>>>, ) -> Result<(ArrayBase<OwnedRepr<f32>, Dim<[usize; 4]>>, Vec<[f32; 6]>), OCRError>

Preprocesses images for table structure recognition.

Preprocessing follows PaddleX TablePredictor order:

• ResizeByLong
• Normalize
• PaddingTableImage (for fixed-shape models)

Important: padding happens after normalization and uses zero fill in normalized tensor space. This matches PaddleX behavior and avoids introducing large negative values from normalizing black pixels in padded regions.

pub fn infer( &self, batch_tensor: &ArrayBase<OwnedRepr<f32>, Dim<[usize; 4]>>, ) -> Result<(ArrayBase<OwnedRepr<f32>, Dim<[usize; 3]>>, ArrayBase<OwnedRepr<f32>, Dim<[usize; 3]>>), OCRError>

Runs inference on the preprocessed tensor.

Returns dual outputs matching ONNX model order: (bbox predictions, structure logits).

pub fn forward( &self, images: Vec<ImageBuffer<Rgb<u8>, Vec<u8>>>, ) -> Result<SLANetModelOutput, OCRError>

Runs the complete forward pass: preprocess -> infer.

Postprocessing is handled separately by TableStructureDecode.

Model Output Order

The ONNX model outputs are in this order:

• fetch_name_0: bbox predictions [batch, seq, 8]
• fetch_name_1: structure logits [batch, seq, vocab_size]

Trait Implementations

impl Debug for SLANetModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.