maskrcnn_resnet50_fpn¶
- torchvision.models.detection.maskrcnn_resnet50_fpn(*, weights: Optional[MaskRCNN_ResNet50_FPN_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, weights_backbone: Optional[ResNet50_Weights] = ResNet50_Weights.IMAGENET1K_V1, trainable_backbone_layers: Optional[int] = None, **kwargs: Any) MaskRCNN [source]¶
Mask R-CNN model with a ResNet-50-FPN backbone from the Mask R-CNN paper.
Warning
The detection module is in Beta stage, and backward compatibility is not guaranteed.
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 in0-1
range. Different images can have different sizes.The behavior of the model changes depending on if it is in training or evaluation mode.
During training, the model expects both the input tensors and targets (list of dictionary), containing:
boxes (
FloatTensor[N, 4]
): the ground-truth boxes in[x1, y1, x2, y2]
format, with0 <= x1 < x2 <= W
and0 <= y1 < y2 <= H
.labels (
Int64Tensor[N]
): the class label for each ground-truth boxmasks (
UInt8Tensor[N, H, W]
): the segmentation binary masks for each instance
The model returns a
Dict[Tensor]
during training, containing the classification and regression losses for both the RPN and the R-CNN, and the mask loss.During inference, the model requires only the input tensors, and returns the post-processed predictions as a
List[Dict[Tensor]]
, one for each input image. The fields of theDict
are as follows, whereN
is the number of detected instances:boxes (
FloatTensor[N, 4]
): the predicted boxes in[x1, y1, x2, y2]
format, with0 <= x1 < x2 <= W
and0 <= y1 < y2 <= H
.labels (
Int64Tensor[N]
): the predicted labels for each instancescores (
Tensor[N]
): the scores or each instancemasks (
UInt8Tensor[N, 1, H, W]
): the predicted masks for each instance, in0-1
range. In order to obtain the final segmentation masks, the soft masks can be thresholded, generally with a value of 0.5 (mask >= 0.5
)
For more details on the output and on how to plot the masks, you may refer to Instance segmentation models.
Mask R-CNN is exportable to ONNX for a fixed batch size with inputs images of fixed size.
Example:
>>> model = torchvision.models.detection.maskrcnn_resnet50_fpn(weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT) >>> model.eval() >>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)] >>> predictions = model(x) >>> >>> # optionally, if you want to export the model to ONNX: >>> torch.onnx.export(model, x, "mask_rcnn.onnx", opset_version = 11)
- Parameters:
weights (
MaskRCNN_ResNet50_FPN_Weights
, optional) – The pretrained weights to use. SeeMaskRCNN_ResNet50_FPN_Weights
below for more details, and possible values. By default, no pre-trained weights are used.progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.
num_classes (int, optional) – number of output classes of the model (including the background)
weights_backbone (
ResNet50_Weights
, optional) – The pretrained weights for the backbone.trainable_backbone_layers (int, optional) – number of trainable (not frozen) layers starting from final block. Valid values are between 0 and 5, with 5 meaning all backbone layers are trainable. If
None
is passed (the default) this value is set to 3.**kwargs – parameters passed to the
torchvision.models.detection.mask_rcnn.MaskRCNN
base class. Please refer to the source code for more details about this class.
- class torchvision.models.detection.MaskRCNN_ResNet50_FPN_Weights(value)[source]¶
The model builder above accepts the following values as the
weights
parameter.MaskRCNN_ResNet50_FPN_Weights.DEFAULT
is equivalent toMaskRCNN_ResNet50_FPN_Weights.COCO_V1
. You can also use strings, e.g.weights='DEFAULT'
orweights='COCO_V1'
.MaskRCNN_ResNet50_FPN_Weights.COCO_V1:
These weights were produced by following a similar training recipe as on the paper. Also available as
MaskRCNN_ResNet50_FPN_Weights.DEFAULT
.box_map (on COCO-val2017)
37.9
mask_map (on COCO-val2017)
34.6
categories
__background__, person, bicycle, … (88 omitted)
min_size
height=1, width=1
num_params
44401393
recipe
GFLOPS
134.38
File size
169.8 MB
The inference transforms are available at
MaskRCNN_ResNet50_FPN_Weights.COCO_V1.transforms
and perform the following preprocessing operations: AcceptsPIL.Image
, batched(B, C, H, W)
and single(C, H, W)
imagetorch.Tensor
objects. The images are rescaled to[0.0, 1.0]
.
Examples using
maskrcnn_resnet50_fpn
:Visualization utilities