Struct PPLCNetModel 

pub struct PPLCNetModel { /* private fields */ }

Pure PP-LCNet model implementation.

This model performs image classification using the PP-LCNet architecture.

Implementations

impl PPLCNetModel

pub fn new( inference: OrtInfer, normalizer: NormalizeImage, topk_processor: Topk, input_shape: (u32, u32), resize_filter: FilterType, resize_short: Option<u32>, ) -> PPLCNetModel

Creates a new PP-LCNet model.

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

Preprocesses images for classification.

Arguments

• images - Input images to preprocess

Returns

Preprocessed batch tensor

pub fn infer( &self, batch_tensor: &ArrayBase<OwnedRepr<f32>, Dim<[usize; 4]>>, ) -> Result<ArrayBase<OwnedRepr<f32>, Dim<[usize; 2]>>, OCRError>

Runs inference on the preprocessed batch.

Arguments

• batch_tensor - Preprocessed batch tensor

Returns

Model predictions as a 2D tensor (batch_size x num_classes)

pub fn postprocess( &self, predictions: &ArrayBase<OwnedRepr<f32>, Dim<[usize; 2]>>, config: &PPLCNetPostprocessConfig, ) -> Result<PPLCNetModelOutput, OCRError>

Postprocesses model predictions to class IDs and scores.

Arguments

• predictions - Model predictions (batch_size x num_classes)
• config - Postprocessing configuration

Returns

PPLCNetModelOutput containing class IDs, scores, and optional label names

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

Performs complete forward pass: preprocess -> infer -> postprocess.

Arguments

• images - Input images to classify
• config - Postprocessing configuration

Returns

PPLCNetModelOutput containing classification results

Trait Implementations

impl Debug for PPLCNetModel

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

Formats the value using the given formatter.