dtoro
fa9b21856f
Face detection/recognition: - Replace YuNet + SFace with InsightFace buffalo_l (RetinaFace + ArcFace) - 512-d ArcFace embeddings (was 128-d SFace), migration 0006 resizes column - Remove YOLO person-bbox workaround — RetinaFace is accurate enough - Detection threshold 0.65 cleanly separates real faces (0.72+) from false positives on dogs/paintings (0.56-0.61) Content-type classification: - CLIP zero-shot classifier using native PyTorch text encoder + ONNX image encoder for high-quality text-image similarity - Categories: photograph, screenshot, document, receipt, meme, artwork - Writes Tag(kind=content_type) per photo via photo_tags - Margin-based confidence: top-1 vs top-2 score difference - New ClassifierSettings in config (enabled, min_confidence) - Wired into vision_fanout pipeline Tested: 6 real faces from 4 photos (zero false positives), 11/13 photos classified (8 photograph, 2 artwork, 1 meme). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
86 lines
2.7 KiB
Python
86 lines
2.7 KiB
Python
"""
|
|
Download vision model weights on first worker boot.
|
|
|
|
Run as: python -m app.services.vision.bootstrap_models
|
|
|
|
Or called from the vision worker entrypoint before Celery starts.
|
|
Downloads are idempotent — existing files are skipped.
|
|
|
|
For models that require export (OpenCLIP, YOLOv8n), see export_models.py.
|
|
Those must be exported once on any machine with pip, then placed in
|
|
the models volume before the worker starts.
|
|
"""
|
|
import logging
|
|
import os
|
|
from pathlib import Path
|
|
from urllib.request import urlretrieve
|
|
|
|
from app.config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# (relative_path, url, description)
|
|
# Models with url=None must be pre-exported via export_models.py.
|
|
# InsightFace (RetinaFace + ArcFace) auto-downloads via the insightface
|
|
# package on first use — no manual download entries needed.
|
|
DOWNLOADS = []
|
|
|
|
# Models that need manual export via export_models.py
|
|
EXPORTS = [
|
|
("embed/visual.onnx", "OpenCLIP ViT-B/32 visual encoder"),
|
|
("embed/textual.onnx", "OpenCLIP ViT-B/32 textual encoder"),
|
|
("detect/yolov8n.onnx", "YOLOv8n object detector"),
|
|
]
|
|
|
|
|
|
def bootstrap(models_dir: str | None = None):
|
|
"""Ensure all model files are present. Download what we can, warn about
|
|
files that need manual export."""
|
|
base = Path(models_dir or settings.vision.models_dir)
|
|
base.mkdir(parents=True, exist_ok=True)
|
|
|
|
# Download auto-downloadable models
|
|
for rel_path, url, desc in DOWNLOADS:
|
|
dest = base / rel_path
|
|
dest.parent.mkdir(parents=True, exist_ok=True)
|
|
|
|
if dest.exists():
|
|
logger.debug("Already exists: %s (%s)", dest, desc)
|
|
continue
|
|
|
|
logger.info("Downloading %s → %s", desc, dest)
|
|
try:
|
|
urlretrieve(url, str(dest))
|
|
size_kb = dest.stat().st_size / 1024
|
|
logger.info("Downloaded %s (%.0f KB)", desc, size_kb)
|
|
except Exception as e:
|
|
logger.error("Failed to download %s: %s", desc, e)
|
|
if dest.exists():
|
|
dest.unlink()
|
|
|
|
# Check for manually-exported models
|
|
missing = []
|
|
for rel_path, desc in EXPORTS:
|
|
dest = base / rel_path
|
|
if not dest.exists():
|
|
missing.append((rel_path, desc))
|
|
|
|
if missing:
|
|
logger.warning(
|
|
"Missing %d model(s) that require manual export via export_models.py:",
|
|
len(missing),
|
|
)
|
|
for rel_path, desc in missing:
|
|
logger.warning(" %s — %s", base / rel_path, desc)
|
|
logger.warning(
|
|
"Run: python -m app.services.vision.export_models --models-dir %s",
|
|
base,
|
|
)
|
|
else:
|
|
logger.info("All model files present in %s", base)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
logging.basicConfig(level=logging.INFO)
|
|
bootstrap()
|