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

• The repo of AXera Platform, which you can get the detial of guide

• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

• AX650
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card
• AX630C
  • 爱芯派2
  • Module-LLM
  • LLM630 Compute Kit

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:

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: