Skip to content

Swin Transformer V2#

eqxvision.models.swin_v2_t(torch_weights: str = None, **kwargs: Any) -> SwinTransformer #

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

Arguments:

  • torch_weights: A Path or URL for the PyTorch weights. Defaults to None

eqxvision.models.swin_v2_s(torch_weights: str = None, **kwargs: Any) -> SwinTransformer #

Constructs a swin_v2_small architecture from Swin Transformer V2: Scaling Up Capacity and Resolution.

Arguments:

  • torch_weights: A Path or URL for the PyTorch weights. Defaults to None

eqxvision.models.swin_v2_b(torch_weights: str = None, **kwargs: Any) -> SwinTransformer #

Constructs a swin_v2_base architecture from Swin Transformer V2: Scaling Up Capacity and Resolution.

Arguments:

  • torch_weights: A Path or URL for the PyTorch weights. Defaults to None