Shortcuts

wide_resnet101_2

torchvision.models.wide_resnet101_2(*, weights: Optional[Wide_ResNet101_2_Weights] = None, progress: bool = True, **kwargs: Any) ResNet[source]

Wide ResNet-101-2 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-101 has 2048-512-2048 channels, and in Wide ResNet-101-2 has 2048-1024-2048.

Parameters:
  • weights (Wide_ResNet101_2_Weights, optional) – The pretrained weights to use. See Wide_ResNet101_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_ResNet101_2_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. Wide_ResNet101_2_Weights.DEFAULT is equivalent to Wide_ResNet101_2_Weights.IMAGENET1K_V2. You can also use strings, e.g. weights='DEFAULT' or weights='IMAGENET1K_V1'.

Wide_ResNet101_2_Weights.IMAGENET1K_V1:

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

acc@1 (on ImageNet-1K)

78.848

acc@5 (on ImageNet-1K)

94.284

min_size

height=1, width=1

categories

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

num_params

126886696

recipe

link

GFLOPS

22.75

File size

242.9 MB

The inference transforms are available at Wide_ResNet101_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_ResNet101_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_ResNet101_2_Weights.DEFAULT.

acc@1 (on ImageNet-1K)

82.51

acc@5 (on ImageNet-1K)

96.02

min_size

height=1, width=1

categories

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

num_params

126886696

recipe

link

GFLOPS

22.75

File size

484.7 MB

The inference transforms are available at Wide_ResNet101_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