Yolov8m Table Extraction is an object detection model hosted on Hugging Face that identifies bordered and borderless tables within document images. It addresses the need to locate tables as a step in document understanding and data extraction pipelines.
The model is a medium-size YOLOv8 variant fine-tuned for the specific labels 'bordered' and 'borderless'. It is built on the Ultralytics framework and supplied with example inference code that loads the model from the repository and runs prediction on an image source, with an option to save the output. Two usage paths are documented: direct loading via the ultralytics library and an alternative that installs the ultralyticsplus package at a pinned version and employs a helper function to render results.
It is delivered as a downloadable model card on the Hugging Face platform, with support for integration through Python code, Google Colab notebooks, and Kaggle. The repository includes training metrics, TensorBoard logging, and files for the PyTorch implementation. The license is AGPL-3.0.
Yolov8m Table Extraction is an Other AI product. Automatically locating and classifying tables within scanned or digital documents. It is built as an open-source project for developers. Yolov8m Table Extraction is open source under the GPL-3.0 license. It runs on the web, the command line, and API.
Behind Yolov8m Table Extraction is keremberke, and the product first shipped in 2023. The GitHub repository has been archived.
Latest indexed changes and source events
keremberke/yolov8m-table-extraction verified by the PulseGate indexer
⚠ Archived
Other apps tracked under the same category.
