mobilenet_v2 — Torchvision 0.22 documentation (original) (raw)

torchvision.models.mobilenet_v2(*, weights: Optional[MobileNet_V2_Weights] = None, progress: bool = True, **kwargs: Any) → MobileNetV2[source]¶

MobileNetV2 architecture from the MobileNetV2: Inverted Residuals and Linear Bottlenecks paper.

Parameters:

• weights (MobileNet_V2_Weights, optional) – The pretrained weights to use. SeeMobileNet_V2_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.mobilenetv2.MobileNetV2base class. Please refer to the source codefor more details about this class.

class torchvision.models.MobileNet_V2_Weights(value)[source]¶

The model builder above accepts the following values as the weights parameter.MobileNet_V2_Weights.DEFAULT is equivalent to MobileNet_V2_Weights.IMAGENET1K_V2. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.

MobileNet_V2_Weights.IMAGENET1K_V1:

These weights reproduce closely the results of the paper using a simple training recipe.

The inference transforms are available at MobileNet_V2_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_V2_Weights.IMAGENET1K_V2:

These weights improve upon the results of the original paper by using a modified version of TorchVision’snew training recipe. Also available as MobileNet_V2_Weights.DEFAULT.

The inference transforms are available at MobileNet_V2_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].