pyvino
pyvino copied to clipboard
This is the python implementation of openvino models.
Overview
This is the python implementation of OpenVINO models.
The OpenVINO™ toolkit is a comprehensive toolkit for quickly developing applications and solutions that emulate human vision. Based on Convolutional Neural Networks (CNNs), the toolkit extends CV workloads across Intel® hardware, maximizing performance.
Supported tasks
We support these tasks.
task | model |
---|---|
detect_face | face-detection-adas-0001 |
emotion_recognition | emotions-recognition-retail-0003 |
estimate_headpose | head-pose-estimation-adas-0001 |
detect_body | person-detection-retail-0013 |
estimate_humanpose | human-pose-estimation-0001 |
estimate_3d_humanpose | human-pose-estimation-3d |
detect_segmentation | instance-segmentation-seurity-0050 |
Computed results by models are as below.
Installation
Use docker
Click HERE for installation instructions using docker.
No use docker
Click HERE for installation instructions.
Notebook samples
Notebook samples are HERE.
Update
v0.0.1 (2019/08/24)
- Mac, Windows and Ubuntu are supported/
v0.0.2 (2019/01/04)
- 3d pose estimation, docker supported
v0.0.3 (2020/06/07)
- OpenVino 2020 R3 LTS version is based
License
This project is released under the Apache 2.0 license.