AXERA-TECH / RTMPose

huggingface.co
Total runs: 26
24-hour runs: 0
7-day runs: 2
30-day runs: 15
Model's Last Updated: May 20 2026
image-classification

Introduction of RTMPose

Model Details of RTMPose

RTMPose-M

This version of RTMPose-M (256x192) has been converted to run on the Axera NPU using mixed w16/fp32 quantization. It is optimized for real-time human pose estimation with 17 COCO keypoints using the SimCC decoding approach.

Compatible with Pulsar2 version: 6.0.

Model Info
Item Value
Architecture RTMPose-M (CSPNeXt + SimCC Head)
Parameters 13.58M
Input 1x256x192x3 (NHWC, uint8, BGR)
Output simcc_x (1,17,384), simcc_y (1,17,512)
Keypoints 17 (COCO format)
Source OpenMMLab MMPose
Convert tools links:

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

Support Platform
Performance Statistics
AX650N
Model Latency(ms) npu3
rtmpose_m 2.881
Conversion Pipeline
  1. Export ONNX — Download official RTMPose-M from OpenMMLab and fix batch dim:
python export_onnx.py
  1. Replace HardSigmoid — Replace HardSigmoid ops with Mul+Add+Clip for better NPU quantization:
python replace_hardsigmoid.py
  1. Compile axmodel — Use Pulsar2 with the provided config.json to quantize and compile:
pulsar2 build --target_hardware AX650 --config config.json --input rtmpose_m_256x192_no_hs.onnx --output_dir AX650
How to use

Download all files from this repository to the device.

python env requirement
pyaxengine

https://github.com/AXERA-TECH/pyaxengine

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

Input image:

run

python3 ax_infer.py -m rtmpose_m_npu3.axmodel -i test.jpg
root@ax650:~/data# python3 ax_infer.py -m rtmpose_m_npu3.axmodel -i test.jpg
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.10.1s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 6.0 93b95f7f
Model input: name=input, shape=[1, 256, 192, 3], dtype=uint8
Forward: 3.38 ms (avg of 10 runs)
simcc_x: shape=(1, 17, 384), range=[-0.58, 0.88]
simcc_y: shape=(1, 17, 512), range=[-0.49, 0.88]
kpts above 0.3: 17/17
  kp00: ( 359.6,   83.3)  score=0.6773
  kp01: ( 370.0,   79.2)  score=0.6950
  kp02: ( 359.6,   77.1)  score=0.6878
  kp03: ( 384.6,   79.2)  score=0.7398
  kp04: ( 359.6,   79.2)  score=0.6385
  kp05: ( 403.3,  106.3)  score=0.7596
  kp06: ( 367.9,  116.7)  score=0.7683
  kp07: ( 432.5,  152.1)  score=0.4699
  kp08: ( 342.9,  158.3)  score=0.6831
  kp09: ( 445.0,  177.1)  score=0.3021
  kp10: ( 305.4,  179.2)  score=0.5798
  kp11: ( 432.5,  212.5)  score=0.7872
  kp12: ( 399.2,  218.7)  score=0.8110
  kp13: ( 432.5,  289.6)  score=0.7358
  kp14: ( 372.1,  279.2)  score=0.8252
  kp15: ( 470.0,  356.2)  score=0.6704
  kp16: ( 399.2,  345.8)  score=0.8183
Saved: ax_result.jpg

Output image:

Runs of AXERA-TECH RTMPose on huggingface.co

26
Total runs
0
24-hour runs
1
3-day runs
2
7-day runs
15
30-day runs

More Information About RTMPose huggingface.co Model

More RTMPose license Visit here:

https://choosealicense.com/licenses/apache-2.0

RTMPose huggingface.co

RTMPose huggingface.co is an AI model on huggingface.co that provides RTMPose's model effect (), which can be used instantly with this AXERA-TECH RTMPose model. huggingface.co supports a free trial of the RTMPose model, and also provides paid use of the RTMPose. Support call RTMPose model through api, including Node.js, Python, http.

AXERA-TECH RTMPose online free

RTMPose huggingface.co is an online trial and call api platform, which integrates RTMPose's modeling effects, including api services, and provides a free online trial of RTMPose, you can try RTMPose online for free by clicking the link below.

AXERA-TECH RTMPose online free url in huggingface.co:

https://huggingface.co/AXERA-TECH/RTMPose

RTMPose install

RTMPose is an open source model from GitHub that offers a free installation service, and any user can find RTMPose on GitHub to install. At the same time, huggingface.co provides the effect of RTMPose install, users can directly use RTMPose installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

RTMPose install url in huggingface.co:

https://huggingface.co/AXERA-TECH/RTMPose

Url of RTMPose

Provider of RTMPose huggingface.co

AXERA-TECH
ORGANIZATIONS

Other API from AXERA-TECH

huggingface.co

Total runs: 824
Run Growth: 824
Growth Rate: 100.00%
Updated:September 24 2026
huggingface.co

Total runs: 116
Run Growth: 55
Growth Rate: 47.41%
Updated:September 02 2026
huggingface.co

Total runs: 61
Run Growth: 34
Growth Rate: 55.74%
Updated:November 25 2025
huggingface.co

Total runs: 53
Run Growth: 42
Growth Rate: 79.25%
Updated:January 08 2026
huggingface.co

Total runs: 49
Run Growth: 26
Growth Rate: 53.06%
Updated:July 31 2026
huggingface.co

Total runs: 48
Run Growth: 22
Growth Rate: 45.83%
Updated:July 15 2026
huggingface.co

Total runs: 46
Run Growth: 7
Growth Rate: 15.22%
Updated:September 08 2026
huggingface.co

Total runs: 30
Run Growth: -87
Growth Rate: -290.00%
Updated:August 14 2026
huggingface.co

Total runs: 29
Run Growth: 6
Growth Rate: 20.69%
Updated:May 07 2026
huggingface.co

Total runs: 27
Run Growth: 13
Growth Rate: 48.15%
Updated:November 02 2025
huggingface.co

Total runs: 27
Run Growth: 12
Growth Rate: 44.44%
Updated:July 31 2026
huggingface.co

Total runs: 26
Run Growth: 1
Growth Rate: 3.85%
Updated:November 25 2025
huggingface.co

Total runs: 25
Run Growth: -6
Growth Rate: -24.00%
Updated:January 15 2026