ONNX Model Zoo

AXERA-TECH/MixFormerV2

By AXERA-TECH · ↓ 6 · ♥ 2 · Updated 2025-06-22

What's in this repo

This page lists the files in AXERA-TECH/MixFormerV2, including mixformer_v2_sim.onnx.

  • 1 ONNX models (.onnx files)
  • 9 files, including 2 .axmodel, 2 .py, 1 .md, 1 .avi, 1 .json, 1 .onnx
  • Last updated 2025-06-22

ONNX files

File Size Download
onnx/mixformer_v2_sim.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

MixFormerV2

This version of MixFormerV2 has been converted to run on the Axera NPU using w8a16 quantization.

This model has been optimized with the following LoRA:

Compatible with Pulsar2 version: 3.4

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through

Support Platform

Chips npu1
AX650 11 ms
AX630C 33 ms

How to use

Download all files from this repository to the device

root@ax650:/mnt/qtang/MixFormerV2# tree -L 1
.
├── ax650
├── car.avi
├── config.json
├── onnx
├── README.md
├── run_mixformer2_axmodel.py
└── run_mixformer2_onnx.py

python env requirement

pyaxengine

https://github.com/AXERA-TECH/pyaxengine

wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.1rc0/axengine-0.1.1-py3-none-any.whl
pip install axengine-0.1.1-py3-none-any.whl
others
pip install argparse numpy opencv-python glob2
Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)
root@ax650:/mnt/qtang/ax650_mixformer2_demo# python3 run_mixformer2_axmodel.py --model-path ax650/mixformer_v2.axmodel --frame-path car.avi -r 10
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.7.2a
[INFO] Model type: 0 (single core)
[INFO] Compiler version: 3.4-dirty 4ff37520-dirty
====================type================= [1079, 482] <class 'list'> <class 'list'>
第一帧初始化完毕!
Video: tracking     246.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Video: tracking     4.0fps
Reached the maximum number of frames (10). Exiting loop.
video: average finale average tracking fps 31.8 fps
root@ax650:/mnt/qtang/ax650_mixformer2_demo#
Inference with M.2 Accelerator card

What is M.2 Accelerator card?, Show this DEMO based on Raspberry PI 5.

(axcl) axera@raspberrypi:~/samples/MixFormerV2 $ python3 run_mixformer2_axmodel.py --model-path ax650/mixformer_v2.axmodel --frame-path car.avi -r 10
[INFO] Available providers:  ['AXCLRTExecutionProvider']
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 3.4-dirty 4ff37520-dirty
====================type================= [1079, 482] <class 'list'> <class 'list'>
第一帧初始化完毕!
Video: tracking     925.0fps
Video: tracking     12.0fps
Video: tracking     12.0fps
Video: tracking     11.0fps
Video: tracking     11.0fps
Video: tracking     11.0fps
Video: tracking     11.0fps
Video: tracking     11.0fps
Video: tracking     10.0fps
Video: tracking     10.0fps
Video: tracking     10.0fps
Reached the maximum number of frames (10). Exiting loop.
video: average finale average tracking fps 114.9 fps
(axcl) axera@raspberrypi:~/samples/MixFormerV2 $

Model info

onnx Transformer Tracking ONNX en license:mit region:us
↓ 6 ♥ 2

Created: 2025-04-03

Updated: 2025-06-22

View on Hugging Face

Files (9)

.gitattributes
README.md
ax630c/mixformer_v2.axmodel
ax650/mixformer_v2.axmodel
car.avi
config.json
onnx/mixformer_v2_sim.onnx ONNX
run_mixformer2_axmodel.py
run_mixformer2_onnx.py

Related models