我正在尝试使用谷歌云视觉API来生成图像的标题。
我尝试使用以下代码来注释图像:
from google.cloud import vision
from google.cloud.vision_v1 import types
client = vision.ImageAnnotatorClient.from_service_account_json('service_account_key.json')
file_name = 'Images/man.jpg'
with open(file_name, 'rb') as image_file:
content = image_file.read()
image = types.Image(content=content)
response = client.annotate_image({
'image': image,
'features': [{'type': vision.enums.Feature.Type.LABEL_DETECTION}]
})
captions = []
for annotation in response.label_annotations:
captions.append(annotation.description)
print("Generated captions for the image:")
for caption in captions:
print(caption)
我收到的错误是 '功能':[{'类型':vision.enums.Feature.Type.LABEL_DETECTION}] AttributeError:模块“google.cloud.vision”没有属性“enums”
vision 是一个枚举,要访问 LABEL_DETECTION 值,可以直接使用`vision.Feature.Type.LABEL_DETECTION。