The dataset contains 9882 facial images in which 5913 facial images are fat label and 3969 facial images are under thin folder. The image id is the unique file name.
We generate 10,000 images using StyleGAN and discard some failed generated images. Then, we aligned the images based on facial part and all images were cropped to 200*200. Finally, we manually labelled to two facial weight classes.
Kindly cite the following paper if you use the dataset: Transforming Facial Weight of Real Images by Editing Latent Space of StyleGAN
Last updated on 18 Jan 2021 .