AXERA-TECH/centerpoint
By AXERA-TECH · ↓ 7 · ♥ 0 · Updated 2026-01-28
What's in this repo
This page lists the files in AXERA-TECH/centerpoint, including pointpillars.onnx.
- 1 ONNX models (.onnx files)
- 112 files, including 53 .json, 50 .bin, 2 .py, 2 .gz, 1 .md, 1 .axmodel
- Last updated 2026-01-28
ONNX files
| File | Size | Download |
|---|---|---|
| pointpillars.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
CenterPoint on Axera NPU
This repository contains the CenterPoint model converted for high-performance inference on the Axera NPU. CenterPoint is a center-based framework for 3D object detection and tracking that represents objects as points, significantly simplifying the detection pipeline on LiDAR point clouds.
This version is optimized with w8a16 quantization and is compatible with Pulsar2 version 4.2.
Convert Tools Links
For model conversion and deployment guidance:
- AXera Platform GitHub Repo: Sample code and optimization guides for Axera NPU.
- Pulsar2 Documentation: Guide for converting ONNX models to
.axmodel.
Support Platforms
| Chips | Model Variant | NPU3 Latency (ms) |
|---|---|---|
| AX650 | CenterPoint-Pillar | 88.334 |
How to Use
Download the repository and ensure the directory structure is organized as follows:
.
├── centerpoint.axmodel # The compiled Axera model
├── inference_axmodel.py # Main inference script
└── extracted_data/ # Input directory
├── config.json # Configuration files (e.g., inference_config.json)
├── sample_index.json
├── gt_annotations/
└── points/
Prerequisites
-
Environment: Ensure you have the required Python environment activated with the following core packages installed:
- NPU Runtime:
axengine(PyAXEngine) - Core Libraries:
numba,opencv-pythonandtqdm.
- NPU Runtime:
-
Model/Data: Ensure the compiled
.axmodel,inference_config.json, and input data (inference_data/) are available on the host.
Inference Command
Run the inference script by providing the compiled model, configuration, and data directory.
python inference_axmodel.py ./centerpoint.axmodel ./extracted_data/config.json ./extracted_data --output-dir ./inference_results --visualize --num-samples 50 --score-thr 0.5
Inference with AX650 Host
Results
The model generates a 3D detection map with bounding boxes oriented in 3D space. Results are saved as images and videos which visualize the ego-vehicle, point cloud data, and detected objects.
(ax_env) root@ax650:~/data# python inference_axmodel.py ./centerpoint.axmodel ./extracted_data/config.json ./extracted_data --output-dir ./inference_results --visualize --num-samples 50 --score-thr 0.5
[INFO] Available providers: ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 5.1-patch1 ed388aa0
Processing 50 samples...
Inference: 100%|████████████████████████████████████████████████████████████████████████| 50/50 [00:47<00:00, 1.06it/s]
Creating video: 100%|███████████████████████████████████████████████████████████████████| 50/50 [00:02<00:00, 23.32it/s]
Done! 50 frames, 12836 detections, saved to ./inference_results
Example Visualization

Model info
Created: 2026-01-28
Updated: 2026-01-28
View on Hugging Face