Edward

Reference ed.criticisms ed.inferences ed.models ed.util observations

observations.celeba

celeba(path)

Load the Large-scale CelebFaces Attributes (CelebA) data set (Liu, Luo, Wang, & Tang, 2015). It consists of ~200,000 178x218 RGB images, each with 40 annotated attributes, and with a total of ~10,000 identities. Here we load only the images.

Args:

path: str. Path to directory which either stores file or otherwise file will be downloaded and extracted there. Filename is img_align_celeba/.

Returns:

str. It is a message advising to load data manually.

Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. In Proceedings of international conference on computer vision (iccv).