Instructions to use deepdoctection/tatr_tab_struct_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepdoctection/tatr_tab_struct_v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="deepdoctection/tatr_tab_struct_v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("deepdoctection/tatr_tab_struct_v2") model = AutoModelForObjectDetection.from_pretrained("deepdoctection/tatr_tab_struct_v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from deepdoctection/tatr_tab_struct_v2: direct link, hf CLI and curl.
- Browser
- Download file 274 Bytes
-
https://huggingface.co/deepdoctection/tatr_tab_struct_v2/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://deepdoctection/tatr_tab_struct_v2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/deepdoctection/tatr_tab_struct_v2/resolve/main/preprocessor_config.json
274 Bytes
| { | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "feature_extractor_type": "DetrFeatureExtractor", | |
| "format": "coco_detection", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "max_size": 1000, | |
| "size": 800 | |
| } | |