DevMesh

[CPU only 40 FPS++] Tensorflow based Fast Pose estimation. OpenVINO, Tensorflow Lite, NCS, NCS2 + Python

Katsuya Hyodo

Katsuya Hyodo

Nagoya, Aichi

6 0
  • 0 Collaborators

This repository has its own implementation, impressed by ildoonet's achievements. Thank you, ildoonet. https://github.com/ildoonet/tf-pose-estimation.git I will make his implementation even faster with CPU only. ...learn more

Project status: Under Development

Internet of Things, Artificial Intelligence

Groups
Internet of Things, DeepLearning, Movidius™ Neural Compute Group

Intel Technologies
OpenVINO, Intel Opt ML/DL Framework, Movidius NCS

Code Samples [1]Links [3]

Overview / Usage

$ git clone https://github.com/PINTO0309/MobileNetV2-PoseEstimation.git
$ cd MobileNetV2-PoseEstimation

CPU - Sync + Boost Mode
$ python3 openvino-usbcamera-cpu-ncs2-sync.py -d CPU -b True

Methodology / Approach

  • Ubuntu 16.04 x86_64 Core i7/Core m3
  • OpenVINO 2019 R1.0.1
  • Tensorflow v1.12.0 + Tensorflow Lite
  • USB Camera
  • Python 3.5

Technologies Used

OpenVINO 2019 R1.01 + Intel's CPU only inference
OpenVINO 2019 R1.01 + Intel's NCS2 inference
OpenVINO 2019 R1.01 + Intel's GPU inference

Repository

https://github.com/PINTO0309/MobileNetV2-PoseEstimation

Comments (0)