Instructions to use Mit1208/UDOP-finetuned-DocLayNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mit1208/UDOP-finetuned-DocLayNet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Mit1208/UDOP-finetuned-DocLayNet")# Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("Mit1208/UDOP-finetuned-DocLayNet") model = AutoModelForTokenClassification.from_pretrained("Mit1208/UDOP-finetuned-DocLayNet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_valid_processor_keys": [ | |
| "images", | |
| "do_resize", | |
| "size", | |
| "resample", | |
| "do_rescale", | |
| "rescale_factor", | |
| "do_normalize", | |
| "image_mean", | |
| "image_std", | |
| "apply_ocr", | |
| "ocr_lang", | |
| "tesseract_config", | |
| "return_tensors", | |
| "data_format", | |
| "input_data_format" | |
| ], | |
| "apply_ocr": false, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "LayoutLMv3ImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "ocr_lang": null, | |
| "processor_class": "UdopProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| }, | |
| "tesseract_config": "" | |
| } | |