![]() In the StyleGAN paper, however, we used all 70,000 images for training. Multi-resolution data for StyleGAN and StyleGAN2Ĭontents of each folder as a ZIP archive.įor use cases that require separate training and validation sets, we have appointed the first 60,000 images to be used for training and the remaining 10,000 for validation. Metadata including copyright info, URLs, etc. You can use, redistribute, and adapt it for non-commercial purposes, as long as you (a) give appropriate credit by citing our paper, (b) indicate any changes that you've made, and (c) distribute any derivative works under the same license. The dataset itself (including JSON metadata, download script, and documentation) is made available under Creative Commons BY-NC-SA 4.0 license by NVIDIA Corporation. The license and original author of each image are indicated in the metadata. However, some of them require giving appropriate credit to the original author, as well as indicating any changes that were made to the images. All of these licenses allow free use, redistribution, and adaptation for non-commercial purposes. The individual images were published in Flickr by their respective authors under either Creative Commons BY 2.0, Creative Commons BY-NC 2.0, Public Domain Mark 1.0, Public Domain CC0 1.0, or U.S. For business inquiries, please visit our website and submit the form: NVIDIA Research Licensing Licenses Please note that this dataset is not intended for, and should not be used for, development or improvement of facial recognition technologies. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos. Only images under permissive licenses were collected. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. ![]() ![]() It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. ![]() The dataset consists of 70,000 high-quality PNG images at 1024×1024 resolution and contains considerable variation in terms of age, ethnicity and image background. Tero Karras (NVIDIA), Samuli Laine (NVIDIA), Timo Aila (NVIDIA) Flickr-Faces-HQ (FFHQ) is a high-quality image dataset of human faces, originally created as a benchmark for generative adversarial networks (GAN):Ī Style-Based Generator Architecture for Generative Adversarial Networks ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |