swin_v2_t

torchvision.models.swin_v2_t(*, weights: Optional[Swin_V2_T_Weights] = None, progress: bool = True, **kwargs: Any) → SwinTransformer

Constructs a swin_v2_tiny architecture from Swin Transformer V2: Scaling Up Capacity and Resolution.

Parameters:

• weights (Swin_V2_T_Weights, optional) – The pretrained weights to use. See Swin_V2_T_Weights below for more details, and possible values. By default, no pre-trained weights are used.

• progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.

• **kwargs – parameters passed to the torchvision.models.swin_transformer.SwinTransformer base class. Please refer to the source code for more details about this class.

class torchvision.models.Swin_V2_T_Weights(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)