CodeFormer

This version of CoderFormer 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: 5.0-patch1

Convert tools links:

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

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

• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

• AX650
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card

Chips	model	cost
AX650	coderformer	408 ms

How to use

Download all files from this repository to the device

root@ax650:~/coderformer# tree
.
|-- model
|   `-- coderformer.axmodel
|-- python
|`-- run_axmodel.py
|`-- requirements.txt

Inference

Input Data:

|-- images
|   `-- 00_00.png
|   `-- 00_01.png
|   `-- 00_02.png

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

root@ax650 ~/realesrgan #python3 run_axmodel.py --inputs_path ./images --model_path ./coderformer.axmodel

[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: 5.0-patch1 681a0b38
SR image save to `00_00.png`
SR image save to `01_00.png`
SR image save to `02_00.png`

Output: