Skip to content
ModelListedExternal
Download

Pp Doclayout v3 Trt

onnx/inference.onnx paddlex/inference.json paddlex/inference.yml engines/sm89-trt10.15-cuda12.6-fp16-b18/ppdoclayoutv3.engine engines/sm89-trt10.15-cuda12.6-fp16-b18/enginemanifest.json artifactmanifest.json...

Sourcehuggingface.co/bndos/pp-doclayout-v3-trt/tree/3c0d3e1f20ce58e1b4ca8a60767e7262b1db622c
KindOtherVersionRevision 3c0d3e1

Model source

Kind
Other
File size
124 MB
Version
vRevision 3c0d3e1
Updated
Sep 16, 2026
Downloads
0
Tasks
Object detection
Source
Hugging Face

Source description

PP-DocLayoutV3 TensorRT

Contents

onnx/inference.onnx
paddlex/inference.json
paddlex/inference.yml
engines/sm89-trt10.15-cuda12.6-fp16-b1_8/pp_doclayout_v3.engine
engines/sm89-trt10.15-cuda12.6-fp16-b1_8/engine_manifest.json
artifact_manifest.json
scripts/build_engine.sh

Engine

GPU: RTX 4090 / sm89
TensorRT: 10.15.1.29
CUDA: 12.6
Precision: FP16
Profile: batch 1-8, image 3x800x800

TensorRT engines are runtime-specific. Rebuild from onnx/inference.onnx if the engine is not compatible with the deployment GPU or TensorRT version.

Rebuild

bash scripts/build_engine.sh

Sources

1 source
Hugging FacePrimaryVersion 3c0d3e1f20ce58e1b4ca8a60767e7262b1db622c
huggingface.co/bndos/pp-doclayout-v3-trt/tree/3c0d3e1f20ce58e1b4ca8a60767e7262b1db622c

Verified Sep 16

Model artifacts

1 artifact

onnx/inference.onnx

onnx · 124 MB · SHA-256 45bf71750b00…28ba · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 16huggingface.co/bndos/pp-doclayout-v3-trt

--- license: apache-2.0 tags: - pp-doclayoutv3 - tensorrt - onnx - document-layout-analysis pipeline_tag: object-detection library_name: paddlex --- # PP-DocLayoutV3 TensorRT ## Contents ```text onnx/inference.onnx paddlex/inference.json paddlex/inference.yml engines/sm89-trt10.15-cuda12.6-fp16-b1_8/pp_doclayout_v3.engine engines/sm89-trt10.15-cuda12.6-fp16-b1_8/engine_manifest.json artifact_manifest.json scripts/build_engine.sh ``` ## Engine ```text GPU: RTX 4090 / sm89 TensorRT: 10.15.1.29 CUDA: 12.6 Precision: FP16 Profile: batch 1-8, image 3x800x800 ``` TensorRT engines are runtime-specific. Rebuild from `onnx/inference.onnx` if the engine is not compatible with the deployment GPU or TensorRT version. ## Rebuild ```bash bash scripts/build_engine.sh ```

NoteSep 16huggingface.co/bndos/pp-doclayout-v3-trt

Source context: 0 downloads · 0 likes · Pipeline object-detection · Library paddlex · Repo bndos/pp-doclayout-v3-trt