Instructions to use PaddlePaddle/PP-OCRv3_server_det with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PP-OCRv3_server_det with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import TextDetection model = TextDetection(model_name="PP-OCRv3_server_det") output = model.predict(input="path/to/image.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json") - Notebooks
- Google Colab
- Kaggle
Download inference.yml from PaddlePaddle/PP-OCRv3_server_det: direct link, hf CLI and curl.
- Browser
- Download file 885 Bytes
-
https://huggingface.co/PaddlePaddle/PP-OCRv3_server_det/resolve/main/inference.yml
- Command line
-
hf download hf://PaddlePaddle/PP-OCRv3_server_det/inference.yml
-
curl -L -o inference.yml https://huggingface.co/PaddlePaddle/PP-OCRv3_server_det/resolve/main/inference.yml
885 Bytes
| Global: | |
| model_name: PP-OCRv3_server_det | |
| Hpi: | |
| backend_configs: | |
| paddle_infer: | |
| trt_dynamic_shapes: | |
| x: | |
| - - 1 | |
| - 3 | |
| - 32 | |
| - 32 | |
| - - 1 | |
| - 3 | |
| - 736 | |
| - 736 | |
| - - 1 | |
| - 3 | |
| - 4000 | |
| - 4000 | |
| tensorrt: | |
| dynamic_shapes: | |
| PreProcess: | |
| transform_ops: | |
| - DecodeImage: | |
| channel_first: false | |
| img_mode: BGR | |
| - DetLabelEncode: null | |
| - DetResizeForTest: null | |
| - NormalizeImage: | |
| mean: | |
| - 0.485 | |
| - 0.456 | |
| - 0.406 | |
| order: hwc | |
| scale: 1./255. | |
| std: | |
| - 0.229 | |
| - 0.224 | |
| - 0.225 | |
| - ToCHWImage: null | |
| - KeepKeys: | |
| keep_keys: | |
| - image | |
| - shape | |
| - polys | |
| - ignore_tags | |
| PostProcess: | |
| name: DBPostProcess | |
| thresh: 0.3 | |
| box_thresh: 0.6 | |
| max_candidates: 1000 | |
| unclip_ratio: 1.5 | |