wide_resnet101_2

paddle.vision.models. wide_resnet101_2 ( pretrained: bool = False, **kwargs: Unpack[_ResNetOptions] ) → ResNet [source]

Wide ResNet-101-2 model from “Wide Residual Networks”.

Parameters

• pretrained (bool, optional) – Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False.

• **kwargs (optional) – Additional keyword arguments. For details, please refer to ResNet.

Returns

Layer. An instance of Wide ResNet-101-2 model.

Examples

>>> import paddle
>>> from paddle.vision.models import wide_resnet101_2

>>> # build model
>>> model = wide_resnet101_2()

>>> # build model and load imagenet pretrained weight
>>> # model = wide_resnet101_2(pretrained=True)

>>> x = paddle.rand([1, 3, 224, 224])
>>> out = model(x)

>>> print(out.shape)
[1, 1000]