Video SwinTransformer¶
The Video SwinTransformer model is based on the Video Swin Transformer paper.
Warning
The video module is in Beta stage, and backward compatibility is not guaranteed.
Model builders¶
The following model builders can be used to instantiate a VideoResNet model, with or
without pre-trained weights. All the model builders internally rely on the
torchvision.models.video.swin_transformer.SwinTransformer3d
base class. Please refer to the source
code for
more details about this class.
|
Constructs a swin_tiny architecture from Video Swin Transformer. |
|
Constructs a swin_small architecture from Video Swin Transformer. |
|
Constructs a swin_base architecture from Video Swin Transformer. |