cerebras.modelzoo.data.vision.classification.data.caltech101.Caltech101#
- class cerebras.modelzoo.data.vision.classification.data.caltech101.Caltech101(*args, **kwargs)[source]#
Bases:
torchvision.datasets.vision.VisionDataset
Caltech-101 consists of pictures of objects belonging to 101 classes, plus one background clutter class. Each image is labelled with a single object. Each class contains roughly 40 to 800 images, totalling around 9k images. Images are of variable sizes, with typical edge lengths of 200-300 pixels. This version contains image-level labels only. The original dataset also contains bounding boxes.
This version also adds the option to split Caltech-101 into trainval set and test set.The trainval set is classed balanced with <class_balance_count> random samples for each of the 101 classes. The remainder are added to the test set.
Methods