Downloads · 30 days
0
pp-doclayout-v3-trt
bndos/pp-doclayout-v3-trt
pp-doclayout-v3-trt is a object detection model from bndos. Use it when you need objects located in an image. It is set up for paddlex. The card lists the license as apache-2.0.
TensorRT engines are runtime-specific. Rebuild from onnx/inference.onnx if the engine is not compatible with the deployment GPU or TensorRT version.
Access
Public
Updated May 29, 2026
Repo size
203 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx131 MB · 64%
At a glance
- Task
- Object Detection
- Library
- paddlex
- License
- apache-2.0
- Access
- Public
- Created
- May 28, 2026
- Updated
- May 29, 2026
- SHA
- 3c0d3e1f
Model card
From the Hugging Face model README
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
- Task
- Object Detection
- Library
- paddlex
- License
- apache-2.0
- Created
- May 28, 2026
- Updated
- May 29, 2026