where were they from to views and locations? were they from f"{prefix}_images.npy"?
Closed this issue · 2 comments
eeric commented
(val_view, (views, locations)), labels = inputs
eeric commented
Adrien987k commented
Hi, the views are the transformed images, loaded from ImageNet, and the locations are the coordinates maps of the crops which are generated by the _location_to_NxN_grid
function from the crop parameters randomly sampled in the RandomResizedCropWithLocation
class.
The train_images.npy and val_images.npy are just ImageNet stored in numpy tensor files.