feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management

D2: TrOCR ONNX export script (printed + handwritten, int8 quantization)
D3: PP-DocLayout ONNX export script (download or Docker-based conversion)
B3: Model Management admin page (PyTorch vs ONNX status, benchmarks, config)
A4: TrOCR ONNX service with runtime routing (auto/pytorch/onnx via TROCR_BACKEND)
A5: PP-DocLayout ONNX detection with OpenCV fallback (via GRAPHIC_DETECT_BACKEND)
B4: Structure Detection UI toggle (OpenCV vs PP-DocLayout) with class color coding
C3: TrOCR-ONNX.md documentation
C4: OCR-Pipeline.md ONNX section added
C5: mkdocs.yml nav updated, optimum added to requirements.txt

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-23 09:53:02 +01:00
parent c695b659fb
commit be7f5f1872
16 changed files with 3616 additions and 60 deletions

View File

@@ -70,6 +70,7 @@ nav:
- BYOEH Developer Guide: services/klausur-service/BYOEH-Developer-Guide.md
- NiBiS Pipeline: services/klausur-service/NiBiS-Ingestion-Pipeline.md
- OCR Pipeline: services/klausur-service/OCR-Pipeline.md
- TrOCR ONNX: services/klausur-service/TrOCR-ONNX.md
- OCR Labeling: services/klausur-service/OCR-Labeling-Spec.md
- OCR Vergleich: services/klausur-service/OCR-Compare.md
- RAG Admin: services/klausur-service/RAG-Admin-Spec.md