text2knowledge/doctr-torch-lw-detr-s-open

import numpy as np
from doctr.models import layout_predictor
 
model = layout_predictor("lw_detr_s", pretrained=True)
dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
out = model([dummy_img])
# out[0] -> {"class_names": ["Title", "Text", ...], "boxes": array(...), "scores": array(...)}

from doctr.io import DocumentFile
from doctr.models import ocr_predictor
 
model = ocr_predictor(pretrained=True, detect_layout=True, layout_arch="lw_detr_s")
doc = DocumentFile.from_images("path/to/your/doc.jpg")
result = model(doc)
 
# Access the detected layout regions of the first page
for region in result.pages[0].layout:
    print(region.type, region.confidence, region.geometry)
# Title 0.97 ((0.13, 0.06), (0.87, 0.11))
# Text 0.95 ((0.11, 0.14), (0.89, 0.42))
# Table 0.93 ((0.12, 0.45), (0.88, 0.79))
 
# The layout is part of the exported representation
export = result.pages[0].export()
print(export["layout"])
 
# Overlay both text and layout regions (use display_layout=False to hide the regions)
result.pages[0].show()