Vision Models
Collection
Common computer vision class models, such as the YOLO family
โข
22 items
โข
Updated
โข
2
This version of SuperResolution has been converted to run on the Axera NPU using w8a8 quantization.
This model has been optimized with the following LoRA:
Compatible with Pulsar2 version: 4.2
For those who are interested in model conversion, you can try to export axmodel through
| Chips | model | cost |
|---|---|---|
| AX650 | EDSR | 800 ms |
| ESPCN | 22 ms |
Download all files from this repository to the device
root@ax650:~/SuperResolution# tree -L 1
.
โโโ assert
โโโ config.json
โโโ experiment
โโโ model_convert
โโโ python
โโโ README.md
โโโ video
6 directories, 2 files
pip install -r python/requirements.txt
pyaxengine ๆฏ npu ็ python api๏ผ่ฏฆ็ปๅฎ่ฃ ่ฏทๅ่: https://github.com/AXERA-TECH/pyaxengine
Input Data:
โโโ video
โโโ test_1920x1080.mp4
root@ax650 ~/SuperResolution # python python/run_axmodel.py --model model_convert/axmodel/edsr_baseline_x2_1.axmodel --scale 2 --dir_demo video/test_1920x1080.mp4
[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 6bff2f67
100%|โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ| 267/267 [10:06<00:00, 2.27s/it]
Total time: 99.582 seconds for 267 frames
Average time: 0.373 seconds for each frame
The output file in experiment/test_1920x1080_x2.avi

Output Data:
โโโ experiment
โ โโโ test_1920x1080_x2.avi
$ cd python
$ python gradio_demo.py
[INFO] Available providers: ['AXCLRTExecutionProvider']
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 4.2 6bff2f67
[INFO] Using provider: AXCLRTExecutionProvider
[INFO] SOC Name: AX650N
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Compiler version: 4.2 6bff2f67
* Running on local URL: http://0.0.0.0:7860
* To create a public link, set `share=True` in `launch()`.
Then use the M.2 Accelerator card IP instead of the 0.0.0.0, and use chrome open the URL: http://[your ip]:7860