We are excited to release LayoutParser v0.3.0, with a lot of exciting updates and functional improvements.

New Features

• The biggest change in this version is that LayoutParser now supports multiple deep learning backends: Detectron2, effdet, and paddledetection. This allows for more flexible usage of thelayoutparser library, and makes it easier for implementing customized layout models in the future.#54#67
• Additionally, the newly addedAutoModel and improved model configuration parsing makes it easier load and use the layout detection models.#69
  • e.g,model = lp.AutoLayoutModel("lp://efficientdet/PubLayNet").
• To support this multi-backend framework, we implement the dynamic importing mechanism as well as better ways for installinglayoutparser and the needed dependencies (seeinstructions).#65#68
• And nowlayoutparser supports directly loading PDF files into aslayout objects:#71

  importlayoutparseraslppdf_layout,pdf_images=lp.load_pdf("path/to/pdf",load_images=True)lp.draw_box(pdf_images[0],pdf_layout[0])

• To support more flexible processing of the layout objects, a set of new toolkits are available:#72

  importlayoutparseraslppage_layout=lp.load_pdf("tests/fixtures/io/example.pdf")[0]pdf_lines=lp.simple_line_detection(page_layout)

New Models

• Add MFD model that can detect (display) equation regions within scientific documents#59