Bei0001/PP-DocLayoutV3-ONNX

PP-DocLayoutV3 — ONNX export

ONNX export of PaddlePaddle/PP-DocLayoutV3_safetensors, the layout-detection model used in the PaddleOCR-VL-1.5 pipeline.

This export preserves all four model heads: classification logits, bounding boxes, instance-segmentation masks, and reading-order logits. The original PaddlePaddle release outputs polygon points and reading order via a postprocessor that consumes these four tensors.

Files

Inputs / outputs

Input (single tensor):

Outputs (four tensors):

Postprocessing

The official postprocessor lives in transformers.models.pp_doclayout_v3.image_processing_pp_doclayout_v3.PPDocLayoutV3ImageProcessor.post_process_object_detection. It takes the four output tensors plus a target_sizes tensor and returns:

{
  "scores":         (N,)      float32
  "labels":         (N,)      int64
  "boxes":          (N, 4)    float32 — axis-aligned (x1, y1, x2, y2) in target coords
  "polygon_points": list[N]   each (P, 2) int polygon vertices in target coords
  "order_seq":      (N,)      int64   — reading-order index
}

You can use that postprocessor directly (transformers >= 5.4, requires torch and cv2) or port it to numpy + cv2 for a torch-free runtime.

Loading

import onnxruntime as ort
import numpy as np

sess = ort.InferenceSession("PP-DocLayoutV3.onnx", providers=["CPUExecutionProvider"])
# preprocess to 800x800 RGB float32, normalize per preprocessor_config.json
pixel_values = ...  # shape (1, 3, 800, 800), float32
logits, pred_boxes, out_masks, order_logits = sess.run(
    ["logits", "pred_boxes", "out_masks", "order_logits"],
    {"pixel_values": pixel_values},
)

The .onnx.data sidecar is loaded automatically by onnxruntime via the relative location reference embedded in the graph. Both files must sit in the same directory.

How this was exported

1. 1.pip install transformers==5.6.2 torch==2.11 onnx==1.21 onnxscript
2. 2.model = AutoModelForObjectDetection.from_pretrained("PaddlePaddle/PP-DocLayoutV3_safetensors").eval()
3. 3.Wrap the model so forward(pixel_values) returns (logits, pred_boxes, out_masks, order_logits).
4. 4.torch.onnx.export(wrapped, (pixel_values,), "PP-DocLayoutV3.onnx", opset_version=18, dynamo=True, dynamic_axes={"pixel_values": {0: "batch"}})
5. 5.Re-save with onnx.save(..., save_as_external_data=True, location="PP-DocLayoutV3.onnx.data") to standardize the sidecar filename.

Numerical parity vs torch (random (1, 3, 800, 800) input):

The order_logits deviation reflects accumulated floating-point drift in the decoder's attention; argmax-based reading order is unaffected on the test images we checked.

Inference speed

CPU (Apple M-series, single page, 800×800 input): ~480 ms/page with CPUExecutionProvider.

Source

• —Original weights: PaddlePaddle/PP-DocLayoutV3_safetensors
• —Original PaddlePaddle release: PaddlePaddle/PP-DocLayoutV3
• —Paper: PaddleOCR-VL-1.5 (arXiv:2601.21957)

License

Apache-2.0 (inherited from PaddlePaddle/PP-DocLayoutV3_safetensors).