资源算法MobileNetV2-PoseEstimation

MobileNetV2-PoseEstimation

2020-02-27 | |  98 |   0 |   0

MobileNetV2-PoseEstimation

[Caution] The behavior of RraspberryPi+NCS2 is very unstable.
[Caution] The behavior of Tensorflow Lite+CPU is unstable.
[Caution] May 06, 2019, The Google Edge TPU program and model are under construction.

Introduction

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.

Environment

Environment construction and training procedure

Learn "Openpose" from scratch with MobileNetv2 + MS-COCO and deploy it to OpenVINO/TensorflowLite Part.1

Learn "Openpose" from scratch with MobileNetv2 + MS-COCO and deploy it to OpenVINO/TensorflowLite (Inference by OpenVINO/NCS2) Part.2

Core i7 only + OpenVINO + Openpose Large model + Sync mode (disabled GPU)

NCS2 x1 + OpenVINO + Openpose Large model + Async + Normal mode

02.gif

Usage

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

CPU - Sync Mode

$ python3 openvino-usbcamera-cpu-ncs2-sync.py -d CPU

CPU - Sync + Boost Mode

$ python3 openvino-usbcamera-cpu-ncs2-sync.py -d CPU -b True

NCS2 - Sync Mode

$ python3 openvino-usbcamera-cpu-ncs2-sync.py -d MYRIAD

CPU - Async Mode

$ python3 openvino-usbcamera-cpu-ncs2-async.py -d CPU

NCS2 - Async - Single Stick Mode

$ python3 openvino-usbcamera-cpu-ncs2-async.py -d MYRIAD

NCS2 - Async - Multi Stick Mode

$ python3 openvino-usbcamera-cpu-ncs2-async.py -d MYRIAD -numncs 2

NCS2 - Async - Single Stick + Boost Mode

$ python3 openvino-usbcamera-cpu-ncs2-async.py -d MYRIAD -b True

GPU (Intel HD series only) - Async - Boost Mode

$ python3 openvino-usbcamera-cpu-ncs2-async.py -d GPU -b True

Reference articles, Very Thanks!!

https://github.com/ildoonet/tf-pose-estimation.git
https://www.tensorflow.org/api_docs/python/tf/image/resize_area
Python OpenCVの基礎 resieで画像サイズを変えてみる - Pythonの学習の過程とか - ピーハイ
Blurring and Smoothing - OpenCV with Python for Image and Video Analysis 8
https://www.learnopencv.com/deep-learning-based-human-pose-estimation-using-opencv-cpp-python/
https://teratail.com/questions/169393


上一篇:Caffe-MobileNetV2-ReLU6

下一篇: tensorflow_mobilenet_android_example

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...