Shortcuts

wide_resnet50_2

torchvision.models.wide_resnet50_2(*, weights: Optional[Wide_ResNet50_2_Weights] = None, progress: bool = True, **kwargs: Any) ResNet[source]

Wide ResNet-50-2 model from Wide Residual Networks.

The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048 channels, and in Wide ResNet-50-2 has 2048-1024-2048.

Parameters:
  • weights (Wide_ResNet50_2_Weights, optional) – The pretrained weights to use. See Wide_ResNet50_2_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.ResNet base class. Please refer to the source code for more details about this class.

class torchvision.models.Wide_ResNet50_2_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. Wide_ResNet50_2_Weights.DEFAULT is equivalent to Wide_ResNet50_2_Weights.IMAGENET1K_V2. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.

Wide_ResNet50_2_Weights.IMAGENET1K_V1:

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

acc@1 (on ImageNet-1K)

78.468

acc@5 (on ImageNet-1K)

94.086

min_size

height=1, width=1

categories

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

num_params

68883240

recipe

link

GFLOPS

11.40

File size

131.8 MB

The inference transforms are available at Wide_ResNet50_2_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].

Wide_ResNet50_2_Weights.IMAGENET1K_V2:

These weights improve upon the results of the original paper by using TorchVision’s new training recipe. Also available as Wide_ResNet50_2_Weights.DEFAULT.

acc@1 (on ImageNet-1K)

81.602

acc@5 (on ImageNet-1K)

95.758

min_size

height=1, width=1

categories

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

num_params

68883240

recipe

link

GFLOPS

11.40

File size

263.1 MB

The inference transforms are available at Wide_ResNet50_2_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