VisionTransformer¶

模型建構器¶

以下模型建構器可用於實例化 VisionTransformer 模型，無論有無預訓練權重。所有模型建構器內部都依賴 torchvision.models.vision_transformer.VisionTransformer 基底類別。有關此類別的更多詳細資訊，請參閱原始碼。

`vit_b_16`(*[, weights, progress])	從 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 建構 vit_b_16 架構。
`vit_b_32`(*[, weights, progress])	從 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 建構 vit_b_32 架構。
`vit_l_16`(*[, weights, progress])	從 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 建構 vit_l_16 架構。
`vit_l_32`(*[, weights, progress])	從 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 建構 vit_l_32 架構。
`vit_h_14`(*[, weights, progress])	從 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 建構 vit_h_14 架構。