Adding classifications on Video models (#6572)

Author: datumbox

torchvision/models/video/mvit.py

@@ -667,6 +667,8 @@ def mvit_v1_b(*, weights: Optional[MViT_V1_B_Weights] = None, progress: bool = T
     Constructs a base MViTV1 architecture from
     `Multiscale Vision Transformers <https://arxiv.org/abs/2104.11227>`__.
 
+    .. betastatus:: video module
+
     Args:
         weights (:class:`~torchvision.models.video.MViT_V1_B_Weights`, optional): The
             pretrained weights to use. See
@@ -763,6 +765,8 @@ def mvit_v2_s(*, weights: Optional[MViT_V2_S_Weights] = None, progress: bool = T
     Constructs a small MViTV2 architecture from
     `Multiscale Vision Transformers <https://arxiv.org/abs/2104.11227>`__.
 
+    .. betastatus:: video module
+
     Args:
         weights (:class:`~torchvision.models.video.MViT_V2_S_Weights`, optional): The
             pretrained weights to use. See

torchvision/models/video/s3d.py

@@ -187,6 +187,8 @@ def s3d(*, weights: Optional[S3D_Weights] = None, progress: bool = True, **kwarg
 
     Reference: `Rethinking Spatiotemporal Feature Learning <https://arxiv.org/abs/1712.04851>`__.
 
+    .. betastatus:: video module
+
     Args:
         weights (:class:`~torchvision.models.video.S3D_Weights`, optional): The
             pretrained weights to use. See