cerebras.modelzoo.data.vision.classification.data.dmlab.Dmlab

class cerebras.modelzoo.data.vision.classification.data.dmlab.Dmlab

Bases: torchvision.datasets.vision.VisionDataset

The Dmlab dataset contains frames observed by the agent acting in the DMLab environment, which are annotated by the distance between the agent and various objects present in the environment. The goal is to is to evaluate the ability of a visual model to reason about distances from the visual input in 3D environments.

The Dmlab dataset consists of 360x480 color images in 6 classes. The classes are {close, far, very far} x {positive reward, negative reward} respectively.

Methods

__init__(root, transform=None, target_transform=None, split='train')

__call__(*args: Any, **kwargs: Any) → Any

Call self as a function.

static __new__(cls, *args: Any, **kwargs: Any) → Any

previous

cerebras.modelzoo.data.vision.classification.data.dmlab

next

cerebras.modelzoo.data.vision.classification.data.dmlab.DmlabProcessor