cerebras.modelzoo.data.vision.classification.data.patch_camelyon.PatchCamelyon#

class cerebras.modelzoo.data.vision.classification.data.patch_camelyon.PatchCamelyon(*args, **kwargs)[source]#

Bases: torchvision.datasets.vision.VisionDataset

The PatchCamelyon benchmark is a new and challenging image classification dataset. It consists of 327.680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annoted with a binary label indicating presence of metastatic tissue. PCam provides a new benchmark for machine learning models: bigger than CIFAR10, smaller than Imagenet, trainable on a single GPU.

Methods