Compatible with Pulsar2 version: 5.1.
For those who are interested in model conversion, you can try to export axmodel through:
wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc2/axengine-0.1.3-py3-none-any.whl
pip install axengine-0.1.3-py3-none-any.whl
Maybe None.
1(ax_env) root@ax650:~/ax650# python ax_infer.py --model-path yolo26l-pose_npu3.axmodel --test-img bus.jpg
2[INFO] Available providers: ['AxEngineExecutionProvider']
3[INFO] Using provider: AxEngineExecutionProvider
4[INFO] Chip type: ChipType.MC50
5[INFO] VNPU type: VNPUType.DISABLED
6[INFO] Engine version: 2.12.0s
7[INFO] Model type: 2 (triple core)
8[INFO] Compiler version: 5.1-patch1-dirty 9164b433-dirty
9[YOLO26-Pose] [16:47:23.013] [DEBUG] Load model time = 838.91 ms
10[YOLO26-Pose] [16:47:23.070] [DEBUG] Pre-process time = 16.87 ms
11[YOLO26-Pose] [16:47:23.109] [DEBUG] Forward time = 39.14 ms
12[YOLO26-Pose] [16:47:23.113] [DEBUG] Post-process time = 2.97 ms
13[YOLO26-Pose] [16:47:23.117] [INFO] Draw Results (4 persons):
14[YOLO26-Pose] [16:47:23.117] [INFO] (221, 406, 345, 859) -> person: 0.92
15[YOLO26-Pose] [16:47:23.120] [INFO] (668, 391, 807, 880) -> person: 0.92
16[YOLO26-Pose] [16:47:23.122] [INFO] (47, 397, 243, 901) -> person: 0.90
17[YOLO26-Pose] [16:47:23.123] [INFO] (0, 439, 78, 949) -> person: 0.69
18[YOLO26-Pose] [16:47:23.151] [INFO] Saved to result_yolo26_pose.jpg
19
