如何致电Google Vision Legacy模型？

发布于 2025-01-25 03:41:20 字数 885 浏览 2 评论 0 原文

我想使用旧版 text_detection 和 document_text_detection 模型。（请参阅：）我使用功能以这种方式尝试：

import io
from google.cloud import vision

vision_client = vision.ImageAnnotatorClient()


with io.open("/mnt/d/snap.png", 'rb') as image_file:
    content = image_file.read()

image = vision.Image(content=content)


response = vision_client.document_text_detection(image=image)
# print(response) --> uses stable models, works fine



feature = vision.Feature(model="builtin/legacy")

response = vision_client.document_text_detection(image=image, features=feature)
# print(response) --> throws error show below

我会收到以下错误：

TypeError: dict() got multiple values for keyword argument 'features'

我在做什么错？

原文

I want to use the legacy text_detection and document_text_detection model. (refer: https://cloud.google.com/vision/docs/service-announcements)
Im trying it this way using features:

import io
from google.cloud import vision

vision_client = vision.ImageAnnotatorClient()


with io.open("/mnt/d/snap.png", 'rb') as image_file:
    content = image_file.read()

image = vision.Image(content=content)


response = vision_client.document_text_detection(image=image)
# print(response) --> uses stable models, works fine



feature = vision.Feature(model="builtin/legacy")

response = vision_client.document_text_detection(image=image, features=feature)
# print(response) --> throws error show below

I'm getting the following error:

TypeError: dict() got multiple values for keyword argument 'features'

What am I doing wrong?

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

孤君无依 2025-02-01 03:41:20

尝试以下操作：

import io from google.cloud import vision

vision_client = vision.ImageAnnotatorClient()

with io.open("/mnt/d/snap.png", 'rb') as image_file:
    content = image_file.read()

#image = vision.Image(content=content)

response = vision_client.annotate_image({'image': {'content': content},'features': [{'type_': vision.Feature.Type.DOCUMENT_TEXT_DETECTION,'model': "builtin/legacy"}]})

Try this:

import io from google.cloud import vision

vision_client = vision.ImageAnnotatorClient()

with io.open("/mnt/d/snap.png", 'rb') as image_file:
    content = image_file.read()

#image = vision.Image(content=content)

response = vision_client.annotate_image({'image': {'content': content},'features': [{'type_': vision.Feature.Type.DOCUMENT_TEXT_DETECTION,'model': "builtin/legacy"}]})

回复收藏 0 原文

~没有更多了~