Shortcuts

Image

class torchvision.tv_tensors.Image(data: Any, *, dtype: Optional[dtype] = None, device: Optional[Union[device, str, int]] = None, requires_grad: Optional[bool] = None)[source]

[BETA] torch.Tensor subclass for images.

Note

In the transforms, Image instances are largely interchangeable with pure torch.Tensor. See this note for more details.

Parameters:
  • data (tensor-like, PIL.Image.Image) – Any data that can be turned into a tensor with torch.as_tensor() as well as PIL images.

  • dtype (torch.dpython:type, optional) – Desired data type. If omitted, will be inferred from data.

  • device (torch.device, optional) – Desired device. If omitted and data is a torch.Tensor, the device is taken from it. Otherwise, the image is constructed on the CPU.

  • requires_grad (bool, optional) – Whether autograd should record operations. If omitted and data is a torch.Tensor, the value is taken from it. Otherwise, defaults to False.

Examples using Image:

Getting started with transforms v2

Getting started with transforms v2

Transforms v2: End-to-end object detection/segmentation example

Transforms v2: End-to-end object detection/segmentation example

TVTensors FAQ

TVTensors FAQ

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources