lraspp_mobilenet_v3_large¶
- torchvision.models.segmentation.lraspp_mobilenet_v3_large(*, weights: Optional[LRASPP_MobileNet_V3_Large_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, weights_backbone: Optional[MobileNet_V3_Large_Weights] = MobileNet_V3_Large_Weights.IMAGENET1K_V1, **kwargs: Any) LRASPP [source]¶
Constructs a Lite R-ASPP Network model with a MobileNetV3-Large backbone from Searching for MobileNetV3 paper.
Warning
The segmentation module is in Beta stage, and backward compatibility is not guaranteed.
- Parameters:
weights (
LRASPP_MobileNet_V3_Large_Weights
, optional) – The pretrained weights to use. SeeLRASPP_MobileNet_V3_Large_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).
aux_loss (bool, optional) – If True, it uses an auxiliary loss.
weights_backbone (
MobileNet_V3_Large_Weights
, optional) – The pretrained weights for the backbone.**kwargs – parameters passed to the
torchvision.models.segmentation.LRASPP
base class. Please refer to the source code for more details about this class.
- class torchvision.models.segmentation.LRASPP_MobileNet_V3_Large_Weights(value)[source]¶
The model builder above accepts the following values as the
weights
parameter.LRASPP_MobileNet_V3_Large_Weights.DEFAULT
is equivalent toLRASPP_MobileNet_V3_Large_Weights.COCO_WITH_VOC_LABELS_V1
. You can also use strings, e.g.weights='DEFAULT'
orweights='COCO_WITH_VOC_LABELS_V1'
.LRASPP_MobileNet_V3_Large_Weights.COCO_WITH_VOC_LABELS_V1:
These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC dataset. Also available as
LRASPP_MobileNet_V3_Large_Weights.DEFAULT
.miou (on COCO-val2017-VOC-labels)
57.9
pixel_acc (on COCO-val2017-VOC-labels)
91.2
num_params
3221538
categories
__background__, aeroplane, bicycle, … (18 omitted)
min_size
height=1, width=1
recipe
The inference transforms are available at
LRASPP_MobileNet_V3_Large_Weights.COCO_WITH_VOC_LABELS_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 resized toresize_size=[520]
usinginterpolation=InterpolationMode.BILINEAR
. Finally the values are first rescaled to[0.0, 1.0]
and then normalized usingmean=[0.485, 0.456, 0.406]
andstd=[0.229, 0.224, 0.225]
.