使用准备
1、windows需要下载安装tesseract。下载地址:Home · UB-Mannheim/tesseract Wiki
2、把tesseract添加到Path环境变量。
3、安装pip包:
pip install pytesseract
图片问答
模型下载1:impira/layoutlm-document-qa · Hugging Face
模型下载2:impira/layoutlm-document-qa · HF Mirror
from transformers import pipeline
vqa = pipeline(model="impira/layoutlm-document-qa")
output = vqa(
image="https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png",
question="What is the invoice number?",
)
output[0]["score"] = round(output[0]["score"], 3)
print(output)
输出:
[{'score': 1.0, 'answer': 'us-001', 'start': 15, 'end': 15}]