Add better docs for FasterRCNN, MaskRCNN and KeypointRCNN (#943)

torchvision/models/detection/faster_rcnn.py

@@ -99,7 +99,41 @@ class FasterRCNN(GeneralizedRCNN):
 
     Example::
 
-        >>> model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
+        >>> import torchvision
+        >>> from torchvision.models.detection import FasterRCNN
+        >>> from torchvision.models.detection.rpn import AnchorGenerator
+        >>> # load a pre-trained model for classification and return
+        >>> # only the features
+        >>> backbone = torchvision.models.mobilenet_v2(pretrained=True).features
+        >>> # FasterRCNN needs to know the number of
+        >>> # output channels in a backbone. For mobilenet_v2, it's 1280
+        >>> # so we need to add it here
+        >>> backbone.out_channels = 1280
+        >>>
+        >>> # let's make the RPN generate 5 x 3 anchors per spatial
+        >>> # location, with 5 different sizes and 3 different aspect
+        >>> # ratios. We have a Tuple[Tuple[int]] because each feature
+        >>> # map could potentially have different sizes and
+        >>> # aspect ratios
+        >>> anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),),
+        >>>                                    aspect_ratios=((0.5, 1.0, 2.0),))
+        >>>
+        >>> # let's define what are the feature maps that we will
+        >>> # use to perform the region of interest cropping, as well as
+        >>> # the size of the crop after rescaling.
+        >>> # if your backbone returns a Tensor, featmap_names is expected to
+        >>> # be [0]. More generally, the backbone should return an
+        >>> # OrderedDict[Tensor], and in featmap_names you can choose which
+        >>> # feature maps to use.
+        >>> roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],
+        >>>                                                 output_size=7,
+        >>>                                                 sampling_ratio=2)
+        >>>
+        >>> # put the pieces together inside a FasterRCNN model
+        >>> model = FasterRCNN(backbone,
+        >>>                    num_classes=2,
+        >>>                    rpn_anchor_generator=anchor_generator,
+        >>>                    box_roi_pool=roi_pooler)
         >>> model.eval()
         >>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
         >>> predictions = model(x)

torchvision/models/detection/keypoint_rcnn.py

@@ -101,7 +101,47 @@ class KeypointRCNN(FasterRCNN):
 
     Example::
 
-        >>> model = torchvision.models.detection.keypointrcnn_resnet50_fpn(pretrained=True)
+        >>> import torchvision
+        >>> from torchvision.models.detection import KeypointRCNN
+        >>> from torchvision.models.detection.rpn import AnchorGenerator
+        >>>
+        >>> # load a pre-trained model for classification and return
+        >>> # only the features
+        >>> backbone = torchvision.models.mobilenet_v2(pretrained=True).features
+        >>> # KeypointRCNN needs to know the number of
+        >>> # output channels in a backbone. For mobilenet_v2, it's 1280
+        >>> # so we need to add it here
+        >>> backbone.out_channels = 1280
+        >>>
+        >>> # let's make the RPN generate 5 x 3 anchors per spatial
+        >>> # location, with 5 different sizes and 3 different aspect
+        >>> # ratios. We have a Tuple[Tuple[int]] because each feature
+        >>> # map could potentially have different sizes and
+        >>> # aspect ratios
+        >>> anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),),
+        >>>                                    aspect_ratios=((0.5, 1.0, 2.0),))
+        >>>
+        >>> # let's define what are the feature maps that we will
+        >>> # use to perform the region of interest cropping, as well as
+        >>> # the size of the crop after rescaling.
+        >>> # if your backbone returns a Tensor, featmap_names is expected to
+        >>> # be [0]. More generally, the backbone should return an
+        >>> # OrderedDict[Tensor], and in featmap_names you can choose which
+        >>> # feature maps to use.
+        >>> roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],
+        >>>                                                 output_size=7,
+        >>>                                                 sampling_ratio=2)
+        >>>
+        >>> keypoint_roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],
+        >>>                                                          output_size=14,
+        >>>                                                          sampling_ratio=2)
+        >>> # put the pieces together inside a FasterRCNN model
+        >>> model = KeypointRCNN(backbone,
+        >>>                      num_classes=2,
+        >>>                      rpn_anchor_generator=anchor_generator,
+        >>>                      box_roi_pool=roi_pooler,
+        >>>                      keypoint_roi_pool=keypoint_roi_pooler)
+        >>> model.eval()
         >>> model.eval()
         >>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
         >>> predictions = model(x)

torchvision/models/detection/mask_rcnn.py

@@ -104,7 +104,46 @@ class MaskRCNN(FasterRCNN):
 
     Example::
 
-        >>> model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)
+        >>> import torchvision
+        >>> from torchvision.models.detection import MaskRCNN
+        >>> from torchvision.models.detection.rpn import AnchorGenerator
+        >>>
+        >>> # load a pre-trained model for classification and return
+        >>> # only the features
+        >>> backbone = torchvision.models.mobilenet_v2(pretrained=True).features
+        >>> # MaskRCNN needs to know the number of
+        >>> # output channels in a backbone. For mobilenet_v2, it's 1280
+        >>> # so we need to add it here
+        >>> backbone.out_channels = 1280
+        >>>
+        >>> # let's make the RPN generate 5 x 3 anchors per spatial
+        >>> # location, with 5 different sizes and 3 different aspect
+        >>> # ratios. We have a Tuple[Tuple[int]] because each feature
+        >>> # map could potentially have different sizes and
+        >>> # aspect ratios
+        >>> anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),),
+        >>>                                    aspect_ratios=((0.5, 1.0, 2.0),))
+        >>>
+        >>> # let's define what are the feature maps that we will
+        >>> # use to perform the region of interest cropping, as well as
+        >>> # the size of the crop after rescaling.
+        >>> # if your backbone returns a Tensor, featmap_names is expected to
+        >>> # be [0]. More generally, the backbone should return an
+        >>> # OrderedDict[Tensor], and in featmap_names you can choose which
+        >>> # feature maps to use.
+        >>> roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],
+        >>>                                                 output_size=7,
+        >>>                                                 sampling_ratio=2)
+        >>>
+        >>> mask_roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=[0],
+        >>>                                                      output_size=14,
+        >>>                                                      sampling_ratio=2)
+        >>> # put the pieces together inside a FasterRCNN model
+        >>> model = MaskRCNN(backbone,
+        >>>                  num_classes=2,
+        >>>                  rpn_anchor_generator=anchor_generator,
+        >>>                  box_roi_pool=roi_pooler,
+        >>>                  mask_roi_pool=mask_roi_pooler)
         >>> model.eval()
         >>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
         >>> predictions = model(x)
@@ -149,8 +188,10 @@ class MaskRCNN(FasterRCNN):
             mask_head = MaskRCNNHeads(out_channels, mask_layers, mask_dilation)
 
         if mask_predictor is None:
-            mask_dim_reduced = 256  # == mask_layers[-1]
-            mask_predictor = MaskRCNNPredictor(out_channels, mask_dim_reduced, num_classes)
+            mask_predictor_in_channels = 256  # == mask_layers[-1]
+            mask_dim_reduced = 256
+            mask_predictor = MaskRCNNPredictor(mask_predictor_in_channels,
+                                               mask_dim_reduced, num_classes)
 
         super(MaskRCNN, self).__init__(
             backbone, num_classes,