multigeom.datasets#
Data: TinyImageNet and the canonical image transform of the pipeline (images 64 x 64, one channel, in [-1, 1]), the functions that download the datasets (TinyImageNet, TVSD, THINGS images), and synthetic neural data with a known ground truth.
Modules
Download the datasets of the paper, from a notebook or a script: download_tinyimagenet, download_tvsd and download_things_images. |
|
Synthetic neural data with a known ground truth, to learn the tools on and to test them. |
|
TinyImageNet, the diffusion-training and test images. |
|
The image transform of the pipeline: images 64 x 64, single-channel, in [-1, 1]. |