Skip to content

Latest commit

 

History

History
40 lines (32 loc) · 1.68 KB

README.md

File metadata and controls

40 lines (32 loc) · 1.68 KB

Multiclass-Image-Segmentation-using-UNETR-in-TensorFlow

This GitHub repository demonstrates the utilization of UNETR for multiclass image segmentation on the Landmark Guided Face Parsing dataset (LaPa) dataset. .

Architecture

The block diagram of the Original UNETR model.
The block diagram of the Original UNETR model.

Dataset

LaPa stands for Landmark guided face Parsing dataset (LaPa). It is a large-scale dataset for human face parsing. It consists of more than 22,000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with a 11-category pixel-level label map and 106-point landmarks.

Download the dataset: Landmark guided face Parsing dataset (LaPa)

For more: LaPa-Dataset for face parsing

Results

The sequence in the images below is Input Image, Ground Truth and Prediction.

How to improve

  • Train on more epochs.
  • Increase the input image resolution.
  • Apply data augmentation.

Contact

For more follow me on: