Files
momentry_core/scripts/find_magnifying_glass.py
Warren 8f05a7c188 feat: update Python processors and add utility scripts
- Update ASR, face, OCR, pose processors
- Add release pre-flight check script
- Add synonym generation, chunk processing scripts
- Add face recognition, stamp search utilities
2026-04-30 15:07:49 +08:00

87 lines
2.7 KiB
Python

#!/opt/homebrew/bin/python3.11
"""
Search for magnifying glass in key stamp scenes using OWL-ViT
"""
import os
import cv2
import json
from PIL import Image
import torch
from transformers import OwlViTProcessor, OwlViTForObjectDetection
BASE_DIR = "output/384b0ff44aaaa1f1/magnifying_glass"
RESULTS_DIR = "output/384b0ff44aaaa1f1/magnifying_glass_results"
os.makedirs(RESULTS_DIR, exist_ok=True)
print("🔬 Loading OWL-ViT...")
processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32")
model.eval()
SEARCH_TERMS = [
"magnifying glass",
"magnifier",
"loupe",
"lens",
"looking glass",
"glass",
"round glass",
]
import glob
frames = sorted(glob.glob(os.path.join(BASE_DIR, "mag_*.jpg")))
print(f"🔍 Searching {len(frames)} frames for magnifying glass...")
found = False
for frame_path in frames:
frame_name = os.path.basename(frame_path)
sec = frame_name.replace("mag_", "").replace("s.jpg", "")
image = Image.open(frame_path).convert("RGB")
for term in SEARCH_TERMS:
inputs = processor(text=[[term]], images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
target_sizes = torch.Tensor([image.size[::-1]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_sizes, threshold=0.05
)
for score, label, box in zip(
results[0]["scores"], results[0]["labels"], results[0]["boxes"]
):
s = float(score)
if s > 0.05:
x1, y1, x2, y2 = map(int, box.tolist())
img = cv2.imread(frame_path)
crop = img[y1:y2, x1:x2]
if crop.size > 0:
crop_name = f"mag_{sec}s_{term.replace(' ', '_')}_{s:.2f}.jpg"
cv2.imwrite(os.path.join(RESULTS_DIR, crop_name), crop)
cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), 3)
cv2.putText(
img,
f"{term} {s:.2f}",
(x1, y1 - 10),
cv2.FONT_HERSHEY_SIMPLEX,
0.7,
(0, 255, 0),
2,
)
ann_name = f"annotated_mag_{sec}s.jpg"
cv2.imwrite(os.path.join(RESULTS_DIR, ann_name), img)
print(f" 📍 {sec}s | {term} | {s:.2f}")
found = True
if not found:
print("❌ No magnifying glass detected in these frames.")
else:
print(f"\n✅ Found magnifying glass detections. Check {RESULTS_DIR}")