Domi31tls
8d683bc6d8
OnnxTR exécute les MÊMES modèles que docTR (db_resnet50 + crnn_vgg16_bn) sur ONNX Runtime, sans PyTorch. Corrige le crash torch/oneDNN « could not create a primitive » sur CPU contraint (VM 2 cœurs collaborateur : OCR scan impossible → quarantaine). Qualité identique validée empiriquement (CER 0,10-0,23 % vs docTR, 2 validations indépendantes Claude+Qwen), OCR ~2-3× plus rapide CPU. - core : import OnnxTR, _get_ocr_model(), _OCR_AVAILABLE, boucle OCR inchangée (API miroir) ; ONNXTR_CACHE_DIR pour le frozen ; bandeau de logs ENV au démarrage (OS, CPU+AVX, cœurs, RAM, versions, providers) pour retours terrain auto-suffisants. - 3 .spec : embarquent les poids ONNX OnnxTR (fail-closed) + hiddenimports onnxtr. - requirements : onnxtr[cpu] (python-doctr conservé transitoirement). - inclut le correctif quarantaine-visible du runner (GO Qwen). Tests : test_ocr_onnxtr.py (RED→GREEN), 95 unit passed, e2e scan client OK (OCR 5/5, PDF produit, plus de crash). Retrait torch du frozen + rebuild Windows = étapes suivantes (gates Dom). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
156 lines
3.6 KiB
Python
156 lines
3.6 KiB
Python
import os
|
|
from pathlib import Path
|
|
|
|
|
|
block_cipher = None
|
|
|
|
project_dir = Path(globals().get("SPECPATH", os.getcwd())).resolve()
|
|
|
|
|
|
def _data_entry(relative_path: str, target_dir: str | None = None):
|
|
src = project_dir / relative_path
|
|
if not src.exists():
|
|
return None
|
|
return (str(src), target_dir or relative_path)
|
|
|
|
|
|
datas = []
|
|
for relative_path, target_dir in [
|
|
("config", "config"),
|
|
("data/bdpm", "data/bdpm"),
|
|
("data/finess", "data/finess"),
|
|
("data/insee", "data/insee"),
|
|
("models/camembert-bio-deid/onnx", "models/camembert-bio-deid/onnx"),
|
|
("detectors", "detectors"),
|
|
("scripts", "scripts"),
|
|
("assets", "assets"),
|
|
]:
|
|
entry = _data_entry(relative_path, target_dir)
|
|
if entry is not None:
|
|
datas.append(entry)
|
|
|
|
# Fichiers directs sous data/ requis par le core.
|
|
for relative_path in [
|
|
"data/stopwords_manuels.txt",
|
|
"data/villes_blacklist.txt",
|
|
"data/dpi_labels_blacklist.txt",
|
|
"data/companion_blacklist.txt",
|
|
]:
|
|
entry = _data_entry(relative_path, "data")
|
|
if entry is not None:
|
|
datas.append(entry)
|
|
|
|
onnxtr_cache_dir = Path(os.environ.get("ONNXTR_CACHE_DIR", Path.home() / ".cache" / "onnxtr"))
|
|
required_onnxtr_weights = [
|
|
"db_resnet50-69ba0015.onnx",
|
|
"crnn_vgg16_bn-743599aa.onnx",
|
|
]
|
|
missing_onnxtr_weights = []
|
|
for filename in required_onnxtr_weights:
|
|
src = onnxtr_cache_dir / "models" / filename
|
|
if src.exists():
|
|
datas.append((str(src), "models/onnxtr/models"))
|
|
else:
|
|
missing_onnxtr_weights.append(str(src))
|
|
if missing_onnxtr_weights:
|
|
raise FileNotFoundError(
|
|
"Poids OCR OnnxTR manquants pour le build frozen : "
|
|
+ ", ".join(missing_onnxtr_weights)
|
|
+ ". Précharger OnnxTR (lancer une OCR une fois) ou définir ONNXTR_CACHE_DIR avant PyInstaller."
|
|
)
|
|
|
|
|
|
hiddenimports = [
|
|
"Pseudonymisation_Gui_V5",
|
|
"anonymizer_core_refactored_onnx",
|
|
"admin_rules",
|
|
"config_defaults",
|
|
"profile_defaults",
|
|
"gui_batch_paths",
|
|
"manual_masking",
|
|
"pdf_mask_designer",
|
|
"format_converter",
|
|
"ner_manager_onnx",
|
|
"camembert_ner_manager",
|
|
"eds_pseudo_manager",
|
|
"gliner_manager",
|
|
"vlm_manager",
|
|
"build_info",
|
|
"doctr",
|
|
"doctr.io",
|
|
"doctr.models",
|
|
"doctr.models.detection",
|
|
"doctr.models.recognition",
|
|
# OCR OnnxTR (remplace docTR — ONNX Runtime, sans torch)
|
|
"onnxtr",
|
|
"onnxtr.io",
|
|
"onnxtr.models",
|
|
"onnxtr.models.detection",
|
|
"onnxtr.models.recognition",
|
|
"onnxtr.utils",
|
|
"onnxtr.utils.data",
|
|
"cv2",
|
|
"torchvision",
|
|
"edsnlp",
|
|
"edsnlp.pipes",
|
|
"edsnlp.pipes.ner",
|
|
"edsnlp.pipes.ner.pseudo",
|
|
"spacy",
|
|
"spacy.lang.fr",
|
|
"gliner",
|
|
"onnxruntime",
|
|
"transformers",
|
|
"tokenizers",
|
|
"torch",
|
|
"pdfplumber",
|
|
"fitz",
|
|
"PIL",
|
|
"yaml",
|
|
"loguru",
|
|
"regex",
|
|
"optimum",
|
|
"optimum.onnxruntime",
|
|
"optimum.pipelines",
|
|
"optimum.modeling_base",
|
|
"optimum.exporters.onnx",
|
|
]
|
|
|
|
|
|
a = Analysis(
|
|
[str(project_dir / "launcher.py")],
|
|
pathex=[str(project_dir)],
|
|
datas=datas,
|
|
hiddenimports=hiddenimports,
|
|
cipher=block_cipher,
|
|
noarchive=False,
|
|
)
|
|
pyz = PYZ(a.pure, a.zipped_data, cipher=block_cipher)
|
|
|
|
splash = Splash(
|
|
str(project_dir / "assets" / "splash.png"),
|
|
binaries=a.binaries,
|
|
datas=a.datas,
|
|
text_pos=(60, 195),
|
|
text_size=10,
|
|
text_color="white",
|
|
minify_script=True,
|
|
always_on_top=False,
|
|
)
|
|
|
|
exe = EXE(
|
|
pyz,
|
|
a.scripts,
|
|
splash,
|
|
splash.binaries,
|
|
a.binaries,
|
|
a.zipfiles,
|
|
a.datas,
|
|
[],
|
|
name="Anonymisation",
|
|
debug=False,
|
|
strip=False,
|
|
upx=False,
|
|
console=False,
|
|
icon=str(project_dir / "assets" / "icons" / "app.ico"),
|
|
)
|