# OpenPoseForMobile

**Repository Path**: pn_code/OpenPoseForMobile

## Basic Information

- **Project Name**: OpenPoseForMobile
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-11-28
- **Last Updated**: 2021-08-23

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

This is an Andriod APP for OpenPose at mobilephones, app_release.apk is the runable release. The lightweight network was trained in MSCOCO and got over 0.27 AP, and works with 60 ms per frame at Qualcomm SnapDragon 855 SoC's GPU.

This APP was modified from the Android demo in https://github.com/edvardHua/PoseEstimationForMobile, written in Kotlin and Java, thanks a lot for this awesome framework. The post-processing of PAF and HeatMap was added for Multi-Person Pose Estimation.




# TF Lite Android App

## Building from Source with Bazel

1. Follow the [Bazel steps for the TF Demo App](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#bazel):

  1. [Install Bazel and Android Prerequisites](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#install-bazel-and-android-prerequisites).
     It's easiest with Android Studio.

      - You'll need at least SDK version 23.
      - Make sure to install the latest version of Bazel. Some distributions
        ship with Bazel 0.5.4, which is too old.
      - Bazel requires Android Build Tools `26.0.1` or higher.
      - **Bazel is incompatible with NDK revisions 15 and above,** with revision
        16 being a compile-breaking change. [Download an older version manually
        instead of using the SDK Manager.](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#install-bazel-and-android-prerequisites)
      - You also need to install the Android Support Repository, available
        through Android Studio under `Android SDK Manager -> SDK Tools ->
        Android Support Repository`.

  2. [Edit your `WORKSPACE`](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#edit-workspace)
     to add SDK and NDK targets.

     NOTE: As long as you have the SDK and NDK installed, the `./configure`
     script will create these rules for you. Answer "Yes" when the script asks
     to automatically configure the `./WORKSPACE`.

      - Make sure the `api_level` in `WORKSPACE` is set to an SDK version that
        you have installed.
      - By default, Android Studio will install the SDK to `~/Android/Sdk` and
        the NDK to `~/Android/Sdk/ndk-bundle` (but the NDK should be a manual
        download until Bazel supports NDK 16. See bullet points under (1)).

2. Build the app with Bazel. The demo needs C++11:

  ```shell
  bazel build -c opt --cxxopt='--std=c++11' \
    //tensorflow/contrib/lite/java/demo/app/src/main:TfLiteCameraDemo
  ```

3. Install the demo on a
   [debug-enabled device](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/android#install):

  ```shell
  adb install bazel-bin/tensorflow/contrib/lite/java/demo/app/src/main/TfLiteCameraDemo.apk
  ```