MNN/demo/exec
Zhang 91b5ade49a
Sync. Fix OpenGL related building issues. Build the whole suite on Android CI (#580)
* Sync code with latest internal version

* Update CMake

* Fix logging issues

* Fix OpenGL Building

* Bump CMakeLists version. Update Podspec

* Update MetalLib Lookup logic

* Fix Windows Build
2020-01-16 16:55:46 +08:00
..
CMakeLists.txt Update 2019-12-27 22:16:57 +08:00
PoseNames.hpp beta 0.2.0.3 2019-07-11 13:56:52 +08:00
README.md beta 0.2.0.3 2019-07-11 13:56:52 +08:00
expressDemo.cpp Sync. Fix OpenGL related building issues. Build the whole suite on Android CI (#580) 2020-01-16 16:55:46 +08:00
multiPose.cpp Update 2019-12-27 22:16:57 +08:00
pictureRecognition.cpp Update 2019-12-27 22:16:57 +08:00
pictureRotate.cpp Update 2019-12-27 22:16:57 +08:00
segment.cpp Sync. Fix OpenGL related building issues. Build the whole suite on Android CI (#580) 2020-01-16 16:55:46 +08:00

README.md

[TOC]

Build this Demo on Linux or Mac

Use Top CMakeLists.txt to construct demo like this:

cd path/to/MNN
mkdir build && cd build
cmake -DMNN_BUILD_DEMO=ON ..
make -j8

Build this Demo on Windows

Use Top CMakeLists.txt to construct demo like this:

cd path/to/MNN
mkdir build
cd build
cmake -G "NMake Makefiles" -DCMAKE_BUILD_TYPE=Release -DMNN_BUILD_DEMO=ON ..
nmake

MultiPose

  1. Download pose model
  2. Convert tensorflow model to MNN model
  3. run multipose like this:
./multiPose.out model.mnn input.jpg pose.png

Segment

Using deeplabv3 segment model downloaded from: https://storage.googleapis.com/download.tensorflow.org/models/tflite/gpu/deeplabv3_257_mv_gpu.tflite

./segment.out model.mnn input.jpg result.png