Shortcuts

mobilenet_v3_large

torchvision.models.mobilenet_v3_large(*, weights: Optional[MobileNet_V3_Large_Weights] = None, progress: bool = True, **kwargs: Any) MobileNetV3[source]

Constructs a large MobileNetV3 architecture from Searching for MobileNetV3.

Parameters:
  • weights (MobileNet_V3_Large_Weights, optional) – The pretrained weights to use. See 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.

  • **kwargs – parameters passed to the torchvision.models.resnet.MobileNetV3 base class. Please refer to the source code for more details about this class.

class torchvision.models.MobileNet_V3_Large_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. MobileNet_V3_Large_Weights.DEFAULT is equivalent to MobileNet_V3_Large_Weights.IMAGENET1K_V2. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.

MobileNet_V3_Large_Weights.IMAGENET1K_V1:

These weights were trained from scratch by using a simple training recipe.

acc@1 (on ImageNet-1K)

74.042

acc@5 (on ImageNet-1K)

91.34

min_size

height=1, width=1

categories

tench, goldfish, great white shark, … (997 omitted)

num_params

5483032

recipe

link

_ops

0.217 giga floating-point operations per sec

_weight_size

21.114 MB (file size)

The inference transforms are available at MobileNet_V3_Large_Weights.IMAGENET1K_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 resized to resize_size=[256] using interpolation=InterpolationMode.BILINEAR, followed by a central crop of crop_size=[224]. Finally the values are first rescaled to [0.0, 1.0] and then normalized using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

MobileNet_V3_Large_Weights.IMAGENET1K_V2:

These weights improve marginally upon the results of the original paper by using a modified version of TorchVision’s new training recipe. Also available as MobileNet_V3_Large_Weights.DEFAULT.

acc@1 (on ImageNet-1K)

75.274

acc@5 (on ImageNet-1K)

92.566

min_size

height=1, width=1

categories

tench, goldfish, great white shark, … (997 omitted)

num_params

5483032

recipe

link

_ops

0.217 giga floating-point operations per sec

_weight_size

21.107 MB (file size)

The inference transforms are available at MobileNet_V3_Large_Weights.IMAGENET1K_V2.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 resized to resize_size=[232] using interpolation=InterpolationMode.BILINEAR, followed by a central crop of crop_size=[224]. Finally the values are first rescaled to [0.0, 1.0] and then normalized using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources