<p align="center"> <img src="https://github.com/felixdittrich92/OnnxTR/raw/main/docs/images/logo.jpg" width="40%"> </p>

由 Onnxruntime 驱动的光学字符识别，让任何人都能无缝使用

任务：检测

https://github.com/felixdittrich92/OnnxTR

使用示例：

>>> from onnxtr.io import DocumentFile
>>> from onnxtr.models import ocr_predictor, from_hub

>>> img = DocumentFile.from_images(['<image_path>'])
>>> # Load your model from the hub
>>> # 从 Hub 加载您的模型
>>> model = from_hub('onnxtr/my-model')

>>> # Pass it to the predictor
>>> # 将其传递给预测器
>>> # If your model is a recognition model:
>>> # 如果您的模型是识别模型：
>>> predictor = ocr_predictor(det_arch='db_mobilenet_v3_large',
>>>                           reco_arch=model)

>>> # If your model is a detection model:
>>> # 如果您的模型是检测模型：
>>> predictor = ocr_predictor(det_arch=model,
>>>                           reco_arch='crnn_mobilenet_v3_small')

>>> # Get your predictions
>>> # 获取您的预测结果
>>> res = predictor(img)