|
Download README.md from WaveMatrix/Yolo26-Depth: direct link, hf CLI and curl.
- Browser
- Download file 3.27 kB
-
https://huggingface.co/WaveMatrix/Yolo26-Depth/resolve/main/README.md
- Command line
-
hf download hf://WaveMatrix/Yolo26-Depth/README.md
-
curl -L -o README.md https://huggingface.co/WaveMatrix/Yolo26-Depth/resolve/main/README.md
3.27 kB
| license: bsd-3-clause | |
| language: | |
| - en | |
| base_model: | |
| - YOLO26 | |
| pipeline_tag: depth-estimation | |
| tags: | |
| - WaveMatrix | |
| - NPU | |
| - yolo26-depth | |
| # YOLO26-Depth | |
| This repository provides an WaveMatrix NPU inference deployment example for the Ultralytics YOLO26-Depth depth-estimation model, including model conversion and WM9955 Python inference examples. | |
| This version of YOLO26-Depth has been converted to run on the WaveMatrix NPU using mixed U8/U16 quantization for improved performance. | |
| ## Convert tools links: | |
| For those who are interested in model conversion, you can try to export axmodel through | |
| - [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) | |
| ## Support Platform | |
| - WM9955 | |
| - M.2 Accelerator card | |
| - WM8845 | |
| - Demo board | |
| ### Performance Statistics | |
| WM9955 (NPU3 mode) | |
| | 樑ε | εθΎ¨η | θζΆ(ms) | FPS | CMM(MiB) | | |
| |---|---:|---:|---:|---:| | |
| | yolo26n-depth | 768x768 | 5.83 | 171.53 | 7.97 | | |
| | yolo26s-depth | 768x768 | 8.33 | 120.05 | 14.90 | | |
| | yolo26m-depth | 768x768 | 16.37 | 61.09 | 36.36 | | |
| | yolo26l-depth | 768x768 | 20.74 | 48.22 | 41.12 | | |
| | yolo26x-depth | 768x768 | 39.19 | 25.52 | 93.37 | | |
| WM8845 (NPU2 mode) | |
| | 樑ε | εθΎ¨η | θζΆ(ms) | FPS | CMM(MiB) | | |
| |---|---:|---:|---:|---:| | |
| | yolo26n-depth | 768x768 | 27.67 | 36.14 | 15.65 | | |
| | yolo26s-depth | 768x768 | 41.68 | 23.99 | 22.75 | | |
| | yolo26m-depth | 768x768 | 74.02 | 13.51 | 47.10 | | |
| | yolo26l-depth | 768x768 | 94.04 | 10.63 | 44.77 | | |
| | yolo26x-depth | 768x768 | 169.09 | 5.91 | 84.50 | | |
| ## How to use | |
| Download all files from this repository to the device | |
| ```shell | |
| root@wm9955~/root/yolo26-depth# tree -L 2 | |
| . | |
| βββ asserts | |
| βΒ Β βββ bus.jpg | |
| βΒ Β βββ ssd_car_depth_heatmap_ax.png | |
| βΒ Β βββ ssd_car_depth_heatmap_onnx.png | |
| βΒ Β βββ ssd_car.jpg | |
| βββ wm8845 | |
| βΒ Β βββ config.json | |
| βΒ Β βββ yolo26l-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26m-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26n-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26s-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26x-depth_w8a8_mix.axmodel | |
| βββ wm9955 | |
| βΒ Β βββ config.json | |
| βΒ Β βββ yolo26l-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26m-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26n-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26s-depth_w8a8_mix.axmodel | |
| βΒ Β βββ yolo26x-depth_w8a8_mix.axmodel | |
| βββ axengine-0.1.3-py3-none-any.whl | |
| βββ calib_data.zip | |
| βββ fold_depth_log.py | |
| βββ infer_depth.py | |
| βββ onnx | |
| βΒ Β βββ yolo26l-depth.onnx | |
| βΒ Β βββ yolo26m-depth.onnx | |
| βΒ Β βββ yolo26n-depth.onnx | |
| βΒ Β βββ yolo26s-depth.onnx | |
| βΒ Β βββ yolo26x-depth.onnx | |
| βββ README.md | |
| βββ requirements.txt | |
| ``` | |
| Inference with WM9955 Host, such as demo board | |
| ```shell | |
| cd /root/yolo26-depth | |
| pip3 install -r requirements.txt | |
| pip3 install axengine-0.1.3-py3-none-any.whl | |
| # wavematrix npu infer | |
| python3 infer_depth.py --model ./wm9955/yolo26n-depth_w8a8_mix.axmodel --source ./asserts/ssd_car.jpg | |
| # onnxtuntime cpu infer | |
| python3 infer_depth.py --model ./onnx/yolo26n-depth.onnx --source ./asserts/ssd_car.jpg | |
| ``` | |
| wavematrix npu output: | |
|  |