README.md

---
license: bsd-3-clause
language:
- en
base_model:
- depth-anything/Depth-Anything-V2-Small
pipeline_tag: depth-estimation
tags:
- Depth-Anything-V2
---

# Depth-Anything-V2 

This version of Depth-Anything-V2  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 

- [The repo of original](https://depth-anything-v2.github.io/)

- [The repo of AXera Platform](https://github.com/AXERA-TECH/DepthAnythingV2.axera), which you can get the detial of guide

- [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)
  - [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
- AX630C
  - [爱芯派2](https://axera-pi-2-docs-cn.readthedocs.io/zh-cn/latest/index.html)
  - [Module-LLM](https://docs.m5stack.com/zh_CN/module/Module-LLM)
  - [LLM630 Compute Kit](https://docs.m5stack.com/zh_CN/core/LLM630%20Compute%20Kit)
 
|Chips|Time|
|--|--|
|AX650| 33 ms |
|AX630C| 310 ms |

## How to use

Download all files from this repository to the device

```
root@ax650:~/AXERA-TECH/Depth-Anything-V2# tree
.
|-- README.md
|-- calib-cocotest2017.tar
|-- config.json
|-- depth_anything_v2_vits.onnx
|-- depth_anything_v2_vits_ax620e.axmodel
|-- depth_anything_v2_vits_ax650.axmodel
|-- examples
|   |-- demo01.jpg
....
|   `-- demo20.jpg
|-- output-ax.png
`-- python
    |-- infer.py
    |-- infer_onnx.py
    |-- output.png
    `-- requirements.txt

2 directories, 31 files
root@ax650:~/AXERA-TECH/Depth-Anything-V2#
```

### python env requirement

#### pyaxengine

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

```
wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc1/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(爱芯派Pro)

Input image:

![](examples/demo01.jpg)

```
root@ax650:~/AXERA-TECH/Depth-Anything-V2# python3 python/infer.py --model depth_anything_v2_vits_ax650.axmodel --img examples/demo01.jpg
[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: 3.3 ae03a08f
root@ax650:~/AXERA-TECH/Depth-Anything-V2# ls
```

Output image:

![](output-ax.png)

#### Inference with M.2 Accelerator card
Input image:

![](examples/demo01.jpg)

```
(base) axera@raspberrypi:~/lhj/Depth-Anything-V2 $ ./axcl_aarch64/axcl_depth_anything -m depth_anything_v2_vits_ax650.axmodel -i examples/demo01.jpg -g 518,518
--------------------------------------
model file : depth_anything_v2_vits_ax650.axmodel
image file : examples/demo01.jpg
img_h, img_w : 518 518
--------------------------------------
axclrtEngineCreateContextt is done. 
axclrtEngineGetIOInfo is done. 

grpid: 0

input size: 1
    name:    input 
        1 x 518 x 518 x 3


output size: 1
    name:   output 
        1 x 1 x 518 x 518

==================================================

Engine push input is done. 
--------------------------------------
post process cost time:7.07 ms 
--------------------------------------
Repeat 1 times, avg time 33.25 ms, max_time 33.25 ms, min_time 33.25 ms
```

Output image:

![](depth_anything_out.png)