部署并调用端点

import os
import time
from collections import Counter

import httpx

URL = "https://YOUR_DEPLOYMENT_URL.run.app/predict"
HEADERS = {"Authorization": f"Bearer {os.environ['ULTRALYTICS_API_KEY']}"}  # the deployment's bound key, server-side only

def predict(client, path, conf=0.25, attempts=4):
    """POST one image; retry timeouts, 429, and 5xx with backoff; fail fast on other errors."""
    for attempt in range(attempts):
        try:
            with open(path, "rb") as f:
                r = client.post(URL, headers=HEADERS, data={"conf": conf}, files={"file": f}, timeout=90)
            if r.status_code < 400:
                return r.json()
            if r.status_code != 429 and r.status_code < 500:
                r.raise_for_status()  # 401 wrong key, 413 too large: retrying won't help
            wait, reason = float(r.headers.get("Retry-After", 2**attempt)), r.status_code
        except httpx.TimeoutException:  # a scaled-to-zero endpoint can take up to a minute to wake
            wait, reason = 2**attempt, "timeout"
        print(f"attempt {attempt + 1}: {reason}, retrying in {wait:.0f} s")
        time.sleep(wait)
    raise RuntimeError(f"endpoint still unavailable after {attempts} attempts")

with httpx.Client() as client:
    response = predict(client, "bus.jpg")
for image in response["images"]:
    counts = Counter(d["name"] for d in image["results"])
    print(f"{sum(counts.values())} objects {dict(counts)} in {image['speed']['inference']:.1f} ms")

attempt 1: 429, retrying in 2 s
5 objects {'bus': 1, 'person': 4} in 34.9 ms

curl -X POST "https://YOUR_DEPLOYMENT_URL.run.app/predict" \
  -H "Authorization: Bearer $ULTRALYTICS_API_KEY" \
  -F "file=@bus.jpg" -F "conf=0.25" -F "iou=0.7" -F "imgsz=640"