- torchvision.models.maxvit_t(*, weights: Optional[MaxVit_T_Weights] = None, progress: bool = True, **kwargs: Any) MaxVit ¶
Constructs a maxvit_t architecture from MaxViT: Multi-Axis Vision Transformer.
progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.
**kwargs – parameters passed to the
torchvision.models.maxvit.MaxVitbase class. Please refer to the source code for more details about this class.
- class torchvision.models.MaxVit_T_Weights(value)¶
The model builder above accepts the following values as the
MaxVit_T_Weights.DEFAULTis equivalent to
MaxVit_T_Weights.IMAGENET1K_V1. You can also use strings, e.g.
These weights reproduce closely the results of the paper using a similar training recipe. Also available as
acc@1 (on ImageNet-1K)
acc@5 (on ImageNet-1K)
tench, goldfish, great white shark, … (997 omitted)
The inference transforms are available at
MaxVit_T_Weights.IMAGENET1K_V1.transformsand perform the following preprocessing operations: Accepts
(B, C, H, W)and single
(C, H, W)image
torch.Tensorobjects. The images are resized to
interpolation=InterpolationMode.BICUBIC, followed by a central crop of
crop_size=. Finally the values are first rescaled to
[0.0, 1.0]and then normalized using
mean=[0.485, 0.456, 0.406]and
std=[0.229, 0.224, 0.225].