Add new `.. betastatus::` directive and document Beta APIs (#6115)

* Add new .. betastatus:: directive to document Beta APIs

* Also add it for the fine-grained video API

* Add directive for all builders and pages of Detection module

* Also segmentation and video models

torchvision/models/detection/mask_rcnn.py

@@ -412,6 +412,8 @@ def maskrcnn_resnet50_fpn(
     """Mask R-CNN model with a ResNet-50-FPN backbone from the `Mask R-CNN
     <https://arxiv.org/abs/1703.06870>`_ paper.
 
+    .. betastatus:: detection module
+
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
     image, and should be in ``0-1`` range. Different images can have different sizes.
 
@@ -513,6 +515,8 @@ def maskrcnn_resnet50_fpn_v2(
     """Improved Mask R-CNN model with a ResNet-50-FPN backbone from the `Benchmarking Detection Transfer
     Learning with Vision Transformers <https://arxiv.org/abs/2111.11429>`_ paper.
 
+    .. betastatus:: detection module
+
     :func:`~torchvision.models.detection.maskrcnn_resnet50_fpn` for more details.
 
     Args:

torchvision/models/detection/retinanet.py

@@ -733,6 +733,8 @@ def retinanet_resnet50_fpn(
     """
     Constructs a RetinaNet model with a ResNet-50-FPN backbone.
 
+    .. betastatus:: detection module
+
     Reference: `Focal Loss for Dense Object Detection <https://arxiv.org/abs/1708.02002>`_.
 
     The input to the model is expected to be a list of tensors, each of shape ``[C, H, W]``, one for each
@@ -829,6 +831,8 @@ def retinanet_resnet50_fpn_v2(
     """
     Constructs an improved RetinaNet model with a ResNet-50-FPN backbone.
 
+    .. betastatus:: detection module
+
     Reference: `Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
     <https://arxiv.org/abs/1912.02424>`_.
 

torchvision/models/detection/ssd.py

@@ -584,6 +584,8 @@ def ssd300_vgg16(
     """The SSD300 model is based on the `SSD: Single Shot MultiBox Detector
     <https://arxiv.org/abs/1512.02325>`_ paper.
 
+    .. betastatus:: detection module
+
     The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each
     image, and should be in 0-1 range. Different images can have different sizes but they will be resized
     to a fixed size before passing it to the backbone.

torchvision/models/detection/ssdlite.py

@@ -222,6 +222,8 @@ def ssdlite320_mobilenet_v3_large(
     described at `Searching for MobileNetV3 <https://arxiv.org/abs/1905.02244>`__ and
     `MobileNetV2: Inverted Residuals and Linear Bottlenecks <https://arxiv.org/abs/1801.04381>`__.
 
+    .. betastatus:: detection module
+
     See :func:`~torchvision.models.detection.ssd300_vgg16` for more details.
 
     Example:

torchvision/models/segmentation/deeplabv3.py

@@ -233,6 +233,8 @@ def deeplabv3_resnet50(
 ) -> DeepLabV3:
     """Constructs a DeepLabV3 model with a ResNet-50 backbone.
 
+    .. betastatus:: segmentation module
+
     Reference: `Rethinking Atrous Convolution for Semantic Image Segmentation <https://arxiv.org/abs/1706.05587>`__.
 
     Args:
@@ -286,6 +288,8 @@ def deeplabv3_resnet101(
 ) -> DeepLabV3:
     """Constructs a DeepLabV3 model with a ResNet-101 backbone.
 
+    .. betastatus:: segmentation module
+
     Reference: `Rethinking Atrous Convolution for Semantic Image Segmentation <https://arxiv.org/abs/1706.05587>`__.
 
     Args:

torchvision/models/segmentation/fcn.py

@@ -126,6 +126,8 @@ def fcn_resnet50(
     """Fully-Convolutional Network model with a ResNet-50 backbone from the `Fully Convolutional
     Networks for Semantic Segmentation <https://arxiv.org/abs/1411.4038>`_ paper.
 
+    .. betastatus:: segmentation module
+
     Args:
         weights (:class:`~torchvision.models.segmentation.FCN_ResNet50_Weights`, optional): The
             pretrained weights to use. See
@@ -182,6 +184,8 @@ def fcn_resnet101(
     """Fully-Convolutional Network model with a ResNet-101 backbone from the `Fully Convolutional
     Networks for Semantic Segmentation <https://arxiv.org/abs/1411.4038>`_ paper.
 
+    .. betastatus:: segmentation module
+
     Args:
         weights (:class:`~torchvision.models.segmentation.FCN_ResNet101_Weights`, optional): The
             pretrained weights to use. See

torchvision/models/segmentation/lraspp.py

@@ -132,6 +132,8 @@ def lraspp_mobilenet_v3_large(
     """Constructs a Lite R-ASPP Network model with a MobileNetV3-Large backbone from
     `Searching for MobileNetV3 <https://arxiv.org/abs/1905.02244>`_ paper.
 
+    .. betastatus:: segmentation module
+
     Args:
         weights (:class:`~torchvision.models.segmentation.LRASPP_MobileNet_V3_Large_Weights`, optional): The
             pretrained weights to use. See

torchvision/models/video/resnet.py

@@ -374,6 +374,8 @@ class R2Plus1D_18_Weights(WeightsEnum):
 def r3d_18(*, weights: Optional[R3D_18_Weights] = None, progress: bool = True, **kwargs: Any) -> VideoResNet:
     """Construct 18 layer Resnet3D model.
 
+    .. betastatus:: video module
+
     Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.
 
     Args:
@@ -408,6 +410,8 @@ def r3d_18(*, weights: Optional[R3D_18_Weights] = None, progress: bool = True, *
 def mc3_18(*, weights: Optional[MC3_18_Weights] = None, progress: bool = True, **kwargs: Any) -> VideoResNet:
     """Construct 18 layer Mixed Convolution network as in
 
+    .. betastatus:: video module
+
     Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.
 
     Args:
@@ -442,6 +446,8 @@ def mc3_18(*, weights: Optional[MC3_18_Weights] = None, progress: bool = True, *
 def r2plus1d_18(*, weights: Optional[R2Plus1D_18_Weights] = None, progress: bool = True, **kwargs: Any) -> VideoResNet:
     """Construct 18 layer deep R(2+1)D network as in
 
+    .. betastatus:: video module
+
     Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.
 
     Args: