You can deploy this model and start earning money today!

welcomyou/
doclayout-yolo-onnx-dynamic

Name: doclayout-yolo-onnx-dynamic
Availability: InStock

document-layout-analysis

dynamic-axes

juliozhao/DocLayout-YOLO-DocStructBench

quantized

agpl-3.0

Views

No views yet

DocLayout-YOLO — ONNX with dynamic axes

Re-export of juliozhao/DocLayout-YOLO-DocStructBench and the DocLayNet-pretrained variant to ONNX with dynamic batch + spatial dimensions, which the upstream releases do not provide.

Why dynamic axes?

The official DocLayout-YOLO ONNX exports use fixed input shapes (e.g. 1024×1024). Dynamic axes let downstream tools batch arbitrary page sizes without re-exporting per resolution — convenient for desktop OCR pipelines that hit pages of mixed DPI.

Variants

Subdir	Source	Use case
`doclayout_yolo_onnx_dynamic/`	DocStructBench (academic + business mix)	Primary — used by ScanIndex `layout_analyzer`
`doclayout_yolo_doclaynet_onnx_dynamic/`	DocLayNet (annotated diverse docs)	Auxiliary for non-table region routing

Each subdir contains the .onnx + .onnx.data (external weights) + a .names.json for class id → label mapping.

Loading

python

import onnxruntime as ort
from huggingface_hub import snapshot_download
local = snapshot_download("welcomyou/doclayout-yolo-onnx-dynamic", local_dir="models")
sess = ort.InferenceSession(f"{local}/doclayout_yolo_onnx_dynamic/doclayout_yolo_docstructbench_imgsz1024_dynamic.onnx")
# input "images": (N, 3, H, W) where H, W must be multiples of 32

Re-export reproduction

See train-convert/doclayoutyolo/convert/export_doclayout_yolo_to_onnx.py.

License

AGPL-3.0, inherited from upstream DocLayout-YOLO. Commercial use requires complying with AGPL terms or obtaining an alternative license from the authors.