A dataset containing 30,000 high-quality celebrity faces, resampled to 256px. This dataset was used by NVIDIA in the research paper Progressive Growing of ...

Dataset: No description available. Usability info: 3.75. License: Unknown. Expected update frequency: Not specified. Tags: Music.

CelebA-HQ 256x256 is frequently used for evaluating unconditional generation ability of generative models (such as GANs and denoising diffusion/score-based ...

See what others are saying about this dataset · What have you used this dataset for? · How would you describe this dataset?

Celeba Dataset with masked image , its mask and overlay.

CelebAMask-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA dataset by following CelebA-HQ. Each ...

Kaggle is the world's largest data science community with powerful tools and resources to help you achieve your data science goals.

Multi-Modal-CelebA-HQ (MM-CelebA-HQ) is a dataset containing 30,000 high-resolution face images selected from CelebA, following CelebA-HQ. Each image in the ...

The CelebA-HQ dataset is a high-quality version of CelebA that consists of 30000 images at 1024×1024 resolution.

This dataset is great for training and testing models for face detection, particularly for recognising facial attributes such as finding people with brown hair, ... Discussion (10) · Data Card · Code (546)