def insert_batch(data_path: pathlib.Path, model_name: str,
model_version: str) -> int:
timestamp = datetime.datetime.utcnow()
logger.info("Loading seen set...")
seen_set = get_seen_set()
logger.info("Seen set loaded")
inserted = 0
for item in tqdm.tqdm(jsonl_iter(data_path)):
barcode = item["barcode"]
source_image = generate_image_path(barcode=barcode,
image_id=item["image_id"])
key = (model_name, source_image)
if key in seen_set:
continue
image_instance = ImageModel.get_or_none(source_image=source_image)
if image_instance is None:
logger.warning("Unknown image in DB: {}".format(source_image))
continue
results = [r for r in item["result"] if r["score"] > 0.1]
data = {"objects": results}
max_confidence = max([r["score"] for r in results], default=None)
inserted += 1
image_prediction = ImagePrediction.create(
type=TYPE,
image=image_instance,
timestamp=timestamp,
model_name=model_name,
model_version=model_version,
data=data,
max_confidence=max_confidence,
)
for i, item in enumerate(results):
if item["score"] >= 0.5:
LogoAnnotation.create(
image_prediction=image_prediction,
index=i,
score=item["score"],
bounding_box=item["bounding_box"],
)
seen_set.add(key)
return inserted
def run_object_detection(barcode: str, image_url: str, server_domain: str):
source_image = get_source_from_image_url(image_url)
image_instance = ImageModel.get_or_none(source_image=source_image)
if image_instance is None:
logger.warning("Missing image in DB for image {}".format(image_url))
return
timestamp = datetime.datetime.utcnow()
results = predict_objects(barcode, image_url, server_domain)
logos = []
for model_name, result in results.items():
data = result.to_json(threshold=0.1)
max_confidence = max([item["score"] for item in data], default=None)
image_prediction = ImagePrediction.create(
image=image_instance,
type="object_detection",
model_name=model_name,
model_version=settings.OBJECT_DETECTION_MODEL_VERSION[model_name],
data={"objects": data},
timestamp=timestamp,
max_confidence=max_confidence,
)
for i, item in enumerate(data):
if item["score"] >= 0.5:
logo = LogoAnnotation.create(
image_prediction=image_prediction,
index=i,
score=item["score"],
bounding_box=item["bounding_box"],
)
logos.append(logo)
if logos:
add_logos_to_ann(image_instance, logos)
save_nearest_neighbors(logos)
thresholds = LOGO_CONFIDENCE_THRESHOLDS.get()
import_logo_insights(logos,
thresholds=thresholds,
server_domain=server_domain)
def run_object_detection(
barcode: str, image: Image.Image, source_image: str, server_domain: str
):
"""Detect logos using the universal logo detector model and generate
logo-related insights.
:param barcode: Product barcode
:param image: Pillow Image to run the object detection on
:param image_url: URL of the image to use
:param server_domain: The server domain associated with the image
"""
logger.info(
f"Running object detection for product {barcode} ({server_domain}), "
f"image {source_image}"
)
image_instance = ImageModel.get_or_none(source_image=source_image)
if image_instance is None:
logger.warning("Missing image in DB for image %s", source_image)
return
timestamp = datetime.datetime.utcnow()
model_name = "universal-logo-detector"
results = ObjectDetectionModelRegistry.get(model_name).detect_from_image(
image, output_image=False
)
data = results.to_json(threshold=0.1)
max_confidence = max([item["score"] for item in data], default=None)
image_prediction = ImagePrediction.create(
image=image_instance,
type="object_detection",
model_name=model_name,
model_version=settings.OBJECT_DETECTION_MODEL_VERSION[model_name],
data={"objects": data},
timestamp=timestamp,
max_confidence=max_confidence,
)
logos = []
for i, item in enumerate(data):
if item["score"] >= 0.5:
logo = LogoAnnotation.create(
image_prediction=image_prediction,
index=i,
score=item["score"],
bounding_box=item["bounding_box"],
)
logos.append(logo)
logger.info(f"{len(logos)} logos found for image {source_image}")
if logos:
add_logos_to_ann(image_instance, logos)
try:
save_nearest_neighbors(logos)
except requests.exceptions.HTTPError as e:
resp = e.response
logger.warning(
f"Could not save nearest neighbors in ANN: {resp.status_code}: %s",
resp.text,
)
thresholds = LOGO_CONFIDENCE_THRESHOLDS.get()
import_logo_insights(logos, thresholds=thresholds, server_domain=server_domain)