layout_detection
ingredient-detection-layout-dataset
Dataset Card for "ingredient-detection-layout-dataset"
More Information needed
nutrient-detection-layout
Nutrient extraction dataset
This dataset contains annotated images of nutrition tables. The goal of this dataset was to train a model to extract nutrient values from nutrition tables, as part of the Nutrisight project.
It contains ~3k samples in total (2.8k for training and 199 for testing). For more information about the project, please refer to the nutrisight directory in the openfoodfacts-ai GitHub repository.
The images were collected from the Open Food Facts database, and… See the full description on the dataset page: https://huggingface.co/datasets/openfoodfacts/nutrient-detection-layout.0004-pdf-layout-detection
Layout detection with PP-DocLayout-L
Bounding-box layout predictions for images from stephenmcconnachie/0004-pdf-pages-test, produced by
PaddleOCR's PP-DocLayout-L.
Processing details
Source: stephenmcconnachie/0004-pdf-pages-test
Model: PaddlePaddle/PP-DocLayout-L (~123M params (RT-DETR-L backbone))
Samples: 50
Processing time: 0.30 min
Processing date: 2026-06-20 09:31 UTC
Confidence threshold: 0.5
Layout NMS: on
Output column: layout (JSON-encoded list of… See the full description on the dataset page: https://huggingface.co/datasets/stephenmcconnachie/0004-pdf-layout-detection.raphael0202_ingredient-detection-layout-datasetCe répertoire est vide, il a été créé pour améliorer le référencement du jeu de données raphael0202/ingredient-detection-layout-dataset.