Hugging Face is one of the biggest platforms that provides tools that enable users to build, train and deploy machine learning (ML) models based on open source (OS) code and technologies. It is also a community where data scientists, researchers, and ML engineers can meet and share ideas, get support and contribute to open source projects.
The developers of Hugging Face have recently added Saint George on a Bike’s DEArt: Dataset of European Art to its archives, allowing cultural heritage and deep learning researchers to use it to train or evaluate models for object-detection on historical document images. The link to DEArt can be found here.
About DEArt:
DEArt: Dataset of European Art, developed by the Saint George on a Bike project, is an object detection and pose classification dataset meant to be a reference for paintings between the 17th and 18th centuries. It contains more than 15000 images, about 80% non-iconic, aligned with manual annotations for the bounding boxes identifying all instances of 69 classes as well as 12 possible poses for boxes identifying human-like objects.
