[PR] Support face-parsing semantic segmentation model - Githubissues

tucan9389 / SemanticSegmentation-CoreML

The example project of inferencing Semantic Segementation using Core ML

https://github.com/motlabs/awesome-ml-demos-with-ios

MIT License

320 stars 32 forks source link

[PR] Support face-parsing semantic segmentation model #14

Closed tucan9389 closed 3 years ago

tucan9389 commented 3 years ago

face-parsing model

video source: https://www.youtube.com/watch?v=D571qZzLfX4

PR Points

Support the face-parsing semantic segmentation model
Support to visualize multi-class semantic segmentation output
- Add MultitargetSegmentationTextureGenerater.swift
- Add new multitarget_segmentation_render_target shader function in Shaders.metal

Model Info

original model repo: https://github.com/zllrunning/face-parsing.PyTorch

Related Issues

How to run the FaceParsing model?

Download the mlmodel from here
Import the FaceParsing.mlmodel into SemanticSegmentation-CoreML>mlmodel folder of the project
Change the minimum iOS version to 14.0+
Change the model class from DeepLabV3() to FaceParsing() in LiveImageViewController.swift or LiveMetalCameraViewController.swift
Build & run the project on the real device

tucan9389 commented 3 years ago

@jsharp83 Could you review my pull request for Metal codes?