QRCode_det

This version of QRCode detetion model 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: 4.2

Convert tools links:

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

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

• Pulsar2 Link, How to Convert ONNX to axmodel

• The repo of AXera Platform,which you can compile the c++ demo

Support Platform

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

Chips	model	cost
	yolov5n	0.73 ms
	yolov8n	1.31 ms
	yolov9t	1.89 ms
AX650	yolov10n	1.44 ms
	yolo11n	1.39 ms
	yolo12n	2.49 ms
	DEIMv2_femto(u16)	1.79 ms

|AX630C|yolov5n|2.57 ms| |AX630C|yolov8n|5.89 ms|

How to use

Download all files from this repository to the device

root@ax650:~/QRCode_det# tree
.
|-- CPP
|   |-- ax_deimv2_qrcode_batch
|   |-- ax_yolov5_qrcode_batch
|   `-- ax_yolov8_qrcode_batch
|-- README.md
|-- images
|   |-- qrcode_01.jpg
|   |-- qrcode_02.jpg
|   |-- qrcode_03.jpg
|   ....
|   `-- qrcode_55.jpg
|-- model
|   |-- AX620E
|   |   |-- yolov5n_npu1.axmodel
|   |   |-- yolov5n_npu2.axmodel
|   |   |-- yolov8n_npu1.axmodel
|   |   `-- yolov8n_npu2.axmodel
|   |-- AX637
|   |   |-- deimv2_hgnetv2_femto_coco_npu1.axmodel
|   |   |-- yolov5n_npu1.axmodel
|   |   `-- yolov8n_npu1.axmodel
|   |-- AX650
|   |   |-- deimv2_hgnetv2_femto_coco_npu3.axmodel
|   |   |-- yolov5n_npu3.axmodel
|   |   `-- yolov8n_npu3.axmodel
|   `-- CPP
|       |-- deimv2_hgnetv2_femto_coco_cpp_npu3.axmodel
|       |-- yolov5n_cpp_npu3.axmodel
|       `-- yolov8n_cpp_npu3.axmodel
|-- python
|   |-- QRCode_axmodel_infer_DEIMv2.py
|   |-- QRCode_axmodel_infer_v5.py
|   |-- QRCode_axmodel_infer_v8.py
|   |-- QRCode_onnx_infer_DEIMv2.py
|   |-- QRCode_onnx_infer_v5.py
|   |-- QRCode_onnx_infer_v8.py
|   `-- requirements.txt
`-- result.png

Inference

Input Data:

|-- images
|   `-- qrcode_01.jpg
|   `-- qrcode_02.jpg
|   `-- qrcode_03.jpg
|   `-- qrcode_04.jpg...

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

Python

run with python3 QRCode_axmodel_infer_xxx.py

root@ax650:~/QRCode# python3 QRCode_axmodel_infer_DEIMv2.py
[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: 4.2 b98901c3
识别成功！
图片 ./qrcode_test/qrcode_01.jpg 处理耗时: 0.2165 秒
识别成功！
图片 ./qrcode_test/qrcode_02.jpg 处理耗时: 0.1540 秒
识别成功！
图片 ./qrcode_test/qrcode_03.jpg 处理耗时: 0.1456 秒
识别成功！
图片 ./qrcode_test/qrcode_05.jpg 处理耗时: 0.1449 秒

Output:

C++

./ax_xxx_qrcode_batch -m xxx_cpp_npu3.axmodel -i images/ -o res/

Output: