fasterrcnn_mobilenet_v3_large_320_fpn

torchvision.models.detection.fasterrcnn_mobilenet_v3_large_320_fpn(*, weights: Optional[FasterRCNN_MobileNet_V3_Large_320_FPN_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, weights_backbone: Optional[MobileNet_V3_Large_Weights] = MobileNet_V3_Large_Weights.IMAGENET1K_V1, trainable_backbone_layers: Optional[int] = None, **kwargs: Any) → FasterRCNN

Low resolution Faster R-CNN model with a MobileNetV3-Large backbone tuned for mobile use cases.

Warning

The detection module is in Beta stage, and backward compatibility is not guaranteed.

It works similarly to Faster R-CNN with ResNet-50 FPN backbone. See fasterrcnn_resnet50_fpn() for more details.

Example:

>>> model = torchvision.models.detection.fasterrcnn_mobilenet_v3_large_320_fpn(weights=FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.DEFAULT)
>>> model.eval()
>>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
>>> predictions = model(x)

Parameters:

• weights (FasterRCNN_MobileNet_V3_Large_320_FPN_Weights, optional) – The pretrained weights to use. See FasterRCNN_MobileNet_V3_Large_320_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 (MobileNet_V3_Large_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 6, with 6 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.faster_rcnn.FasterRCNN base class. Please refer to the source code for more details about this class.

class torchvision.models.detection.FasterRCNN_MobileNet_V3_Large_320_FPN_Weights(value)

The model builder above accepts the following values as the weights parameter. FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.DEFAULT is equivalent to FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.COCO_V1. You can also use strings, e.g. weights='DEFAULT' or weights='COCO_V1'.

FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.COCO_V1:

These weights were produced by following a similar training recipe as on the paper. Also available as FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.DEFAULT.

box_map (on COCO-val2017)	22.8
categories	__background__, person, bicycle, … (88 omitted)
min_size	height=1, width=1
num_params	19386354
recipe	link
GFLOPS	0.72
File size	74.2 MB

The inference transforms are available at FasterRCNN_MobileNet_V3_Large_320_FPN_Weights.COCO_V1.transforms and perform the following preprocessing operations: Accepts PIL.Image, batched (B, C, H, W) and single (C, H, W) image torch.Tensor objects. The images are rescaled to [0.0, 1.0].