Downloads · 30 days
17
4% of all-time downloads
aoiandroid/PP-DocLayoutV3-safetensors-CoreML
PP-DocLayoutV3-safetensors-CoreML is a machine learning model from aoiandroid. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for coreml. The card lists the license as apache-2.0.
Private distribution of the Core ML export for PaddlePaddle/PP-DocLayoutV3safetensors, built for TranslateBlue on-device layout detection.
Downloads · 30 days
17
4% of all-time downloads
All-time downloads
393
Public
Repo size
131 MB
Likes
0
Public
Click a slice to open those files.
.bin131 MB · 100%
From the Hugging Face model README
Private distribution of the Core ML export for PaddlePaddle/PP-DocLayoutV3_safetensors, built for TranslateBlue on-device layout detection.
Source weights: PaddlePaddle/PP-DocLayoutV3 / PP-DocLayoutV3_safetensors.
| File | Description |
|---|---|
PP-DocLayoutV3-safetensors.mlpackage/ | Core ML mlprogram (iOS 18+, float32) |
preprocessor_config.json | HF image processor contract (800×800) |
conversion-status.json | Export metadata |
parity-report.json | PyTorch vs Core ML tensor diff (smoke image) |
| Tensor | Shape | Dtype |
|---|---|---|
pixel_values (in) | [1, 3, 800, 800] | float32 |
logits (out) | [1, 300, 25] | float32 |
pred_boxes (out) | [1, 300, 4] | float32 (normalized cxcywh) |
order_logits (out) | [1, 300, 300] | float32 |
Match PPDocLayoutV3ImageProcessor:
antialias=False in Transformers export)pixel / 255[0,0,0], std [1,1,1]See preprocessor_config.json.
Apply the same logic as PPDocLayoutV3ImageProcessor.post_process_object_detection in Python or Swift:
logitsorder_logitsScripts/export_pp_doclayout_v3_safetensors_coreml/numpy<2.4 required for coremltools convert (coremltools#2633)compute_precision=float32 (fp16 MIL cast diverges)On bus.jpg (TranslateBlue smoke):
| Tensor | max abs diff vs export wrapper |
|---|---|
| logits | 7.2e-5 |
| pred_boxes | 9.7e-6 |
| order_logits | 0.04 |
Apache 2.0 (same family as PaddlePaddle/PP-DocLayoutV3).