dtoro
9282a5c734
Introduce the app/services/vision/ module with ABC interfaces, ONNX Runtime backend, model registry, and per-task implementations: - OpenCLIP ViT-B/32 embedder (image + text, 512-d) - RapidOCR engine (PP-OCRv4 via ONNX, no PaddlePaddle) - YOLOv8n object detector (raw ONNX, no ultralytics runtime) - YuNet + SFace face processor (Apache 2.0, opencv_zoo, 128-d) - DBSCAN face clustering helper Add VisionSettings to config (mulita.yml + Pydantic), bootstrap_models.py for first-boot weight downloads, models_data Docker volume, and ROCm backend stub for future GPU acceleration. No Celery tasks wired yet — models load but nothing invokes them. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
"""
|
|
OCR engine using rapidocr-onnxruntime (PP-OCRv4 weights).
|
|
|
|
No PaddlePaddle dependency — pure ONNX Runtime. Language packs are
|
|
downloaded automatically by rapidocr on first use.
|
|
"""
|
|
import logging
|
|
|
|
import numpy as np
|
|
|
|
from app.config import VisionSettings
|
|
from app.services.vision.base import OCREngine, OCRResult
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class RapidOCREngine(OCREngine):
|
|
def __init__(self, settings: VisionSettings):
|
|
from rapidocr_onnxruntime import RapidOCR
|
|
|
|
self._min_confidence = settings.ocr.min_confidence
|
|
self._engine = RapidOCR()
|
|
logger.info("RapidOCR engine initialized")
|
|
|
|
def run(self, image: np.ndarray) -> list[OCRResult]:
|
|
result, _ = self._engine(image)
|
|
if not result:
|
|
return []
|
|
|
|
out = []
|
|
for box, text, score in result:
|
|
if score < self._min_confidence:
|
|
continue
|
|
# box is [[x1,y1],[x2,y2],[x3,y3],[x4,y4]] — take bounding rect
|
|
xs = [p[0] for p in box]
|
|
ys = [p[1] for p in box]
|
|
h, w = image.shape[:2]
|
|
bbox = [
|
|
min(xs) / w,
|
|
min(ys) / h,
|
|
max(xs) / w,
|
|
max(ys) / h,
|
|
]
|
|
out.append(OCRResult(text=text, confidence=float(score), bbox=bbox))
|
|
return out
|