---
title: IGEV-plusplus
canonical_url: "https://www.modelscope.cn/models/AXERA-TECH/IGEV-plusplus"
md_url: "https://www.modelscope.cn/models/AXERA-TECH/IGEV-plusplus.md"
repository: AXERA-TECH/IGEV-plusplus
last_updated: 2026-07-19
license: bsd-3-clause
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 56
stars: 0
tags:
  - IGEV++
---

# IGEV-plusplus

> IGEV-plusplus - AXERA-TECH 在 ModelScope 开源的模型。This version of RT IGEV has been converted to run on the Axera NPU using w8a16 quantization.

AXERA-TECH/IGEV-plusplus 是 ModelScope 魔搭社区上的机器学习模型，采用 bsd-3-clause 许可。

- **Repository**: AXERA-TECH/IGEV-plusplus
- **License**: bsd-3-clause
- **Tags**: IGEV++
- **Downloads**: 56
- **Stars**: 0
- **Last updated**: 2026-07-19

Source: https://www.modelscope.cn/models/AXERA-TECH/IGEV-plusplus

---

# IGEV++   

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

Compatible with Pulsar2 version: 5.0-patch1

## Convert tools links:

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

- [The repo of original](https://github.com/gangweiX/IGEV-plusplus)

- [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) 


## Support Platform

- AX650
  - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
- AX8850
  - [M.2 Accelerator card](https://docs.m5stack.com/en/ai_hardware/LLM-8850_Card)
 
|Chips|Models |Time|
|--|--|--|
|AX650|AX650_RTIGEV| 139.803 ms |
|AX637|AX637_RTIGEV| 385.72 ms |


## How to use

Download all files from this repository to the device


### python env requirement

#### pyaxengine

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

```
wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc2/axengine-0.1.3-py3-none-any.whl
pip install axengine-0.1.3-py3-none-any.whl
```

#### others

Maybe None.

#### Inference with AX650 Host (such as M4N-Dock, a.k.a. 爱芯派 Pro) or AX637 Host

Input image (take 1 pair of images as examples):

![Left image](./demo-imgs/Adirondack/im0.png)
![Right image](./demo-imgs/Adirondack/im1.png)

run:

```sh
# the default target_chip is AX650, the default input is all images in `demo-img` folder
python3 infer.py 
```

Output image:  

AXmodel result (take 2 images as examples):
![AX650 output image example](./output-imgs/AX650/AXModel_Disparity_Map-rt-Adirondack.png)
![AX637 output image example](./output-imgs/AX637/AXModel_Disparity_Map-rt-2.png)