add v0.19.1 release

docs/source/models/efficientnetv2.rst

+EfficientNetV2
+==============
+
+.. currentmodule:: torchvision.models
+
+The EfficientNetV2 model is based on the `EfficientNetV2: Smaller Models and Faster Training <https://arxiv.org/abs/2104.00298>`__
+paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate an EfficientNetV2 model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.efficientnet.EfficientNet`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    efficientnet_v2_s
+    efficientnet_v2_m
+    efficientnet_v2_l

docs/source/models/faster_rcnn.rst

+Faster R-CNN
+============
+
+.. currentmodule:: torchvision.models.detection
+
+
+The Faster R-CNN model is based on the `Faster R-CNN: Towards Real-Time Object Detection 
+with Region Proposal Networks <https://arxiv.org/abs/1506.01497>`__
+paper.
+
+.. betastatus:: detection module
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a Faster R-CNN model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.detection.faster_rcnn.FasterRCNN`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/detection/faster_rcnn.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    fasterrcnn_resnet50_fpn
+    fasterrcnn_resnet50_fpn_v2
+    fasterrcnn_mobilenet_v3_large_fpn
+    fasterrcnn_mobilenet_v3_large_320_fpn
+    

docs/source/models/fcn.rst

+FCN
+===
+
+.. currentmodule:: torchvision.models.segmentation
+
+The FCN model is based on the `Fully Convolutional Networks for Semantic
+Segmentation <https://arxiv.org/abs/1411.4038>`__
+paper.
+
+.. betastatus:: segmentation module
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a FCN model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.segmentation.FCN`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/fcn.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    fcn_resnet50
+    fcn_resnet101

docs/source/models/fcos.rst

+FCOS
+=========
+
+.. currentmodule:: torchvision.models.detection
+
+The FCOS model is based on the `FCOS: Fully Convolutional One-Stage Object Detection
+<https://arxiv.org/abs/1904.01355>`__ paper.
+
+.. betastatus:: detection module
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a FCOS model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.detection.fcos.FCOS`` base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/detection/fcos.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    fcos_resnet50_fpn

docs/source/models/googlenet.rst

+GoogLeNet
+=========
+
+.. currentmodule:: torchvision.models
+
+The GoogleNet model is based on the `Going Deeper with Convolutions <https://arxiv.org/abs/1409.4842>`__
+paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a GoogLeNet model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.googlenet.GoogLeNet`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    googlenet

docs/source/models/googlenet_quant.rst

+Quantized GoogLeNet
+===================
+
+.. currentmodule:: torchvision.models.quantization
+
+The Quantized GoogleNet model is based on the `Going Deeper with Convolutions <https://arxiv.org/abs/1409.4842>`__
+paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a quantized GoogLeNet
+model, with or without pre-trained weights. All the model builders internally
+rely on the ``torchvision.models.quantization.googlenet.QuantizableGoogLeNet``
+base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/googlenet.py>`_
+for more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    googlenet

docs/source/models/inception.rst

+Inception V3
+============
+
+.. currentmodule:: torchvision.models
+
+The InceptionV3 model is based on the `Rethinking the Inception Architecture for
+Computer Vision <https://arxiv.org/abs/1512.00567>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate an InceptionV3 model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.inception.Inception3`` base class. Please refer to the `source
+code <https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    inception_v3

docs/source/models/inception_quant.rst

+Quantized InceptionV3
+=====================
+
+.. currentmodule:: torchvision.models.quantization
+
+The Quantized Inception model is based on the `Rethinking the Inception Architecture for
+Computer Vision <https://arxiv.org/abs/1512.00567>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a quantized Inception
+model, with or without pre-trained weights. All the model builders internally
+rely on the ``torchvision.models.quantization.inception.QuantizableInception3``
+base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/inception.py>`_
+for more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    inception_v3

docs/source/models/keypoint_rcnn.rst

+Keypoint R-CNN
+==============
+
+.. currentmodule:: torchvision.models.detection
+
+The Keypoint R-CNN model is based on the `Mask R-CNN
+<https://arxiv.org/abs/1703.06870>`__ paper.
+
+.. betastatus:: detection module
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a Keypoint R-CNN model,
+with or without pre-trained weights. All the model builders internally rely on
+the ``torchvision.models.detection.KeypointRCNN`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/detection/keypoint_rcnn.py>`__
+for more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    keypointrcnn_resnet50_fpn

docs/source/models/lraspp.rst

+LRASPP
+======
+
+.. currentmodule:: torchvision.models.segmentation
+
+The LRASPP model is based on the `Searching for MobileNetV3 <https://arxiv.org/abs/1905.02244>`_ paper.
+
+.. betastatus:: segmentation module
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a FCN model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.segmentation.LRASPP`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/lraspp.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    lraspp_mobilenet_v3_large

docs/source/models/mask_rcnn.rst

+Mask R-CNN
+==========
+
+.. currentmodule:: torchvision.models.detection
+
+The Mask R-CNN model is based on the `Mask R-CNN <https://arxiv.org/abs/1703.06870>`__
+paper.
+
+.. betastatus:: detection module
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a Mask R-CNN model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.detection.mask_rcnn.MaskRCNN`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/detection/mask_rcnn.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    maskrcnn_resnet50_fpn
+    maskrcnn_resnet50_fpn_v2

docs/source/models/maxvit.rst

+MaxVit
+===============
+
+.. currentmodule:: torchvision.models
+
+The MaxVit transformer models are based on the `MaxViT: Multi-Axis Vision Transformer <https://arxiv.org/abs/2204.01697>`__
+paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate an MaxVit model with and without pre-trained weights.
+All the model builders internally rely on the ``torchvision.models.maxvit.MaxVit`` 
+base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/maxvit.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    maxvit_t

docs/source/models/mnasnet.rst

+MNASNet
+=======
+
+.. currentmodule:: torchvision.models
+
+
+The MNASNet model is based on the `MnasNet: Platform-Aware Neural Architecture
+Search for Mobile <https://arxiv.org/pdf/1807.11626.pdf>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate an MNASNet model.
+All the model builders internally rely on the
+``torchvision.models.mnasnet.MNASNet`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/mnasnet.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    mnasnet0_5
+    mnasnet0_75
+    mnasnet1_0
+    mnasnet1_3

docs/source/models/mobilenetv2.rst

+MobileNet V2
+============
+
+.. currentmodule:: torchvision.models
+
+The MobileNet V2 model is based on the `MobileNetV2: Inverted Residuals and Linear
+Bottlenecks <https://arxiv.org/abs/1801.04381>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a MobileNetV2 model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.mobilenetv2.MobileNetV2`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv2.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    mobilenet_v2

docs/source/models/mobilenetv2_quant.rst

+Quantized MobileNet V2
+======================
+
+.. currentmodule:: torchvision.models.quantization
+
+The Quantized MobileNet V2 model is based on the `MobileNetV2: Inverted Residuals and Linear
+Bottlenecks <https://arxiv.org/abs/1801.04381>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a quantized MobileNetV2
+model, with or without pre-trained weights. All the model builders internally
+rely on the ``torchvision.models.quantization.mobilenetv2.QuantizableMobileNetV2``
+base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/mobilenetv2.py>`_
+for more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    mobilenet_v2

docs/source/models/mobilenetv3.rst

+MobileNet V3
+============
+
+.. currentmodule:: torchvision.models
+
+The MobileNet V3 model is based on the `Searching for MobileNetV3 <https://arxiv.org/abs/1905.02244>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a MobileNetV3 model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.mobilenetv3.MobileNetV3`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    mobilenet_v3_large
+    mobilenet_v3_small

docs/source/models/mobilenetv3_quant.rst

+Quantized MobileNet V3
+======================
+
+.. currentmodule:: torchvision.models.quantization
+
+The Quantized MobileNet V3 model is based on the `Searching for MobileNetV3 <https://arxiv.org/abs/1905.02244>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a quantized MobileNetV3
+model, with or without pre-trained weights. All the model builders internally
+rely on the ``torchvision.models.quantization.mobilenetv3.QuantizableMobileNetV3``
+base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/quantization/mobilenetv3.py>`_
+for more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    mobilenet_v3_large

docs/source/models/raft.rst

+RAFT
+====
+
+.. currentmodule:: torchvision.models.optical_flow
+
+The RAFT model is based on the `RAFT: Recurrent All-Pairs Field Transforms for
+Optical Flow <https://arxiv.org/abs/2003.12039>`__ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a RAFT model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.optical_flow.RAFT`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/optical_flow/raft.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    raft_large
+    raft_small

docs/source/models/regnet.rst

+RegNet
+======
+
+.. currentmodule:: torchvision.models
+
+The RegNet model is based on the `Designing Network Design Spaces
+<https://arxiv.org/abs/2003.13678>`_ paper.
+
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a RegNet model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.regnet.RegNet`` base class. Please refer to the `source code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.py>`_ for
+more details about this class.
+
+.. autosummary::
+   :toctree: generated/
+   :template: function.rst
+
+   regnet_y_400mf
+   regnet_y_800mf
+   regnet_y_1_6gf
+   regnet_y_3_2gf
+   regnet_y_8gf
+   regnet_y_16gf
+   regnet_y_32gf
+   regnet_y_128gf
+   regnet_x_400mf
+   regnet_x_800mf
+   regnet_x_1_6gf
+   regnet_x_3_2gf
+   regnet_x_8gf
+   regnet_x_16gf
+   regnet_x_32gf

docs/source/models/resnet.rst

+ResNet
+======
+
+.. currentmodule:: torchvision.models
+
+The ResNet model is based on the `Deep Residual Learning for Image Recognition
+<https://arxiv.org/abs/1512.03385>`_ paper.
+
+.. note::
+    The bottleneck of TorchVision places the stride for downsampling to the second 3x3
+    convolution while the original paper places it to the first 1x1 convolution.
+    This variant improves the accuracy and is known as `ResNet V1.5
+    <https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch>`_.
+
+Model builders
+--------------
+
+The following model builders can be used to instantiate a ResNet model, with or
+without pre-trained weights. All the model builders internally rely on the
+``torchvision.models.resnet.ResNet`` base class. Please refer to the `source
+code
+<https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py>`_ for
+more details about this class.
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    resnet18
+    resnet34
+    resnet50
+    resnet101
+    resnet152