https://github.com/nikhilroxtomar/human-face-segmentation-in-tensorflow

This repository contains the code for Multiclass Segmentation on the human faces using Landmark Guided Face Parsing (LaPa) dataset in TensorFlow.
https://github.com/nikhilroxtomar/human-face-segmentation-in-tensorflow

multiclass-segmentation tensorflow tensorflow-segmentation

Last synced: about 1 month ago
JSON representation

This repository contains the code for Multiclass Segmentation on the human faces using Landmark Guided Face Parsing (LaPa) dataset in TensorFlow.

• Host: GitHub
• URL: https://github.com/nikhilroxtomar/human-face-segmentation-in-tensorflow
• Owner: nikhilroxtomar
• Created: 2022-11-18T12:12:06.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-12-01T05:08:38.000Z (over 2 years ago)
• Last Synced: 2025-03-28T08:11:30.624Z (about 2 months ago)
• Topics: multiclass-segmentation, tensorflow, tensorflow-segmentation
• Language: Python
• Homepage:
• Size: 1.26 MB
• Stars: 11
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Human Face Segmentation in TensorFlow

This repository contains the code for `Multiclass Segmentation` on the human faces using `Landmark Guided Face Parsing` (LaPa) dataset.





**YouTube Tutorial:** [Human Face Segmentation using UNET in TensorFlow](https://youtu.be/yUOlLd-8jng)

# Dataset

The LaPa dataset contains the training, validation and testing dataset. Each dataset have images, segmentation mask and the 106 human facial key points. 



Download the dataset: [Landmark Guided Face Parsing (LaPa)](https://github.com/JDAI-CV/lapa-dataset)


Dataset paper: [A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing](https://aaai.org/ojs/index.php/AAAI/article/view/6832/6686)

Original Image             |  Grayscale Mask           | RGB Mask

:-------------------------:|:-------------------------:|:-------------------------:

![](img/image.jpg)  |  ![](img/grayscale_mask.png)  |  ![](img/rgb_mask.png)

The following models are used:

- [UNET](https://arxiv.org/abs/1505.04597)

## Contact:

For more follow me on:

-  YouTube 

-  Facebook 

-  Twitter 

-  Instagram 

-  Telegram