Skip to main contentModule ocr
Source - capabilities
- Backend capability checks for OCR graphs.
- cli
- config
- OCR configuration — detection thresholds, alphabet, decode method.
- ctc
- CTC decoding (greedy + beam search).
- detection
- engine
- High-level OCR engine — detect, layout, recognize.
- geom
- Geometry helpers for line polygons and edge extraction.
- layout
- Layout analysis — group detected words into reading-order lines (upstream
ocrs algorithm). - model
- Native RLX graphs for ocrs detection (U-Net) and recognition (CRNN + GRU).
- preprocess
- Greyscale image preprocessing for OCR models.
- recognition
- Recognition module — line batching helpers and full CRNN/GRU inference.
- rlx
- Compiled RLX inference for ocrs detection and recognition.
- runner
- High-level OCR runner with image loading.
- text
- Recognized text items with character-level bounding boxes.
- weights
- Weight paths, safetensors load, and optional
.rten export.
- CtcHypothesis
- Decoded label sequence with log score.
- CtcStep
- Item in a decoded sequence.
- DetectionGraphConfig
- DetectionParams
- Post-processing parameters for the text detection segmentation mask.
- ImageSource
- Input image for
crate::OcrEngine::prepare_input. - OcrConfig
- Shared OCR settings.
- OcrEngine
- End-to-end OCR pipeline (ocrs-compatible API).
- OcrEngineParams
- Parameters for constructing an
OcrEngine. - OcrInput
- Preprocessed greyscale input image
[1, H, W]. - OcrOutput
- Structured OCR output.
- OcrRunner
- OCR session wrapping a fully loaded
OcrEngine. - OcrRunnerBuilder
- Builder for
OcrRunner (mirrors whisper / dinov2 runners). - RecognitionGraphConfig
- RlxTextDetector
- Text detector using a compiled native RLX U-Net graph.
- RlxTextRecognizer
- Recognition backend using compiled native RLX CRNN + GRU graphs (per padded width).
- RotatedRect
- An oriented rectangle.
- SafetensorsFile
- Mmap-backed safetensors file; reuse across per-width graph builds.
- TextChar
- A single recognized character with its axis-aligned bounding box.
- TextLine
- A line of text composed of words.
- TextWord
- A word composed of one or more characters.
- DecodeMethod
- Method used to decode CRNN sequence outputs.
- DimOrder
- Pixel layout for image tensors.
- ImageSourceError
- Errors when constructing an
ImageSource. - TextItem
- Any recognized text item (line, word, or character).
- BLACK_VALUE
- Normalized greyscale background value used by ocrs models (matches
ocrs 0.12.x). - DEFAULT_ALPHABET
- Default character alphabet matching ocrs pretrained recognition models.
- HF_DETECTION_RTEN
- Production detection checkpoint (legacy RTen graph).
- HF_DETECTION_ST
- Safetensors export of detection weights (short name).
- HF_DETECTION_ST_FULL
- Full detection export (includes int32 BN scalars from RTen).
- HF_RECOGNITION_RTEN
- Production recognition checkpoint (legacy RTen CRNN + GRU graph).
- HF_RECOGNITION_ST
- Safetensors export of recognition weights.
- HF_RECOGNITION_ST_FULL
- STANDARD_DEVICES
- Backends every model crate is expected to support when the matching
rlx-runtime feature is enabled at build time. - STANDARD_DEVICE_NAMES
- CLI / help string for
--device.
- decode
- Decode a
[seq, classes] log-probability matrix. - input_image
- is_rten_checkpoint
- True when
path is an ocrs .rten checkpoint. - load_rlx_weights
- Alias for
load_safetensors_weights. - load_safetensors
- Load a
.safetensors file via mmap-backed read into f32 WeightMap tensors. - load_safetensors_weights
- Load weights for RLX graph build (safetensors only).
- ocr_rgb_bytes
- prepare_image
- Convert an image to a normalized greyscale CHW tensor
[1, H, W]. - resolve_model_dir
- Resolve detection + recognition weight paths under
dir (safetensors for native RLX). - validate_device
- Validate that
device is in the workspace standard backend set.