我正在通過它的 API 使用 MS 認知服務(wù)來分析圖像，并注意到當圖像處于橫向模式（“面部未垂直對齊”）時，它返回一個空結(jié)果。我很困惑，想知道是我做錯了什么，還是 MS 服務(wù)的工作方式。這是一個重現(xiàn)問題的簡單示例。您應(yīng)該擁有 MS Face 訂閱密鑰才能使用該服務(wù)！import requests# If you are using a Jupyter notebook, uncomment the following line.#%matplotlib inlineimport matplotlib.pyplot as pltfrom PIL import Imagefrom matplotlib import patchesfrom io import BytesIO# send request to MS, use YOUR subscription keysubscription_key = "982374kwhXXXxxxx"assert subscription_keyface_api_url ='https://westus.api.cognitive.microsoft.com/face/v1.0/detect'header = {'Ocp-Apim-Subscription-Key': face_api_url }headers  = {'Ocp-Apim-Subscription-Key': subscription_key, "Content-Type": "application/octet-stream" }params = {    'returnFaceId': 'true',    'returnFaceLandmarks': 'false',    'returnFaceAttributes': 'age,gender,headPose,smile,facialHair,glasses,' +    'emotion,hair,makeup,occlusion,accessories,blur,exposure,noise'}# get a random image and convert to numpy arrayimage_url = 'https://how-old.net/Images/faces2/main007.jpg'image = Image.open(BytesIO(requests.get(image_url).content))image_np = np.array(image)這是圖像：