The weights can be loaded normally as follows:
py
from torchvision.models import *
model1 = vit_h_14(weights="IMAGENET1K_SWAG_E2E_V1")
model2 = vit_h_14(weights="IMAGENET1K_SWAG_LINEAR_V1")
The SWAG weights are released under the [_Attribution-NonCommercial 4.0 International_](https://github.com/facebookresearch/SWAG/blob/main/LICENSE) license. We would like to thank [_Laura Gustafson_](https://github.com/lauragustafson), [_Mannat Singh_](https://github.com/mannatsingh) and [_Aaron Adcock_](https://github.com/aadcock) for their work and support in making the weights available to TorchVision.
Model Refresh
The release of the Multi-weight support API enabled us to refresh the most popular models and offer more accurate weights. We improved on average each model by ~3 points. The new recipe used was learned on top of ResNet50 and its details were covered on a [_previous blogpost_](https://pytorch.org/blog/how-to-train-state-of-the-art-models-using-torchvision-latest-primitives/).
Model | Old weights | New weights
-- | -- | --