shufflenet_v2_x0_25¶

paddle.vision.models. shufflenet_v2_x0_25 ( pretrained=False, **kwargs ) [source]

ShuffleNetV2 with 0.25x output channels, as described in “ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design”.

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 ShuffleNetV2.

Returns

Layer. An instance of ShuffleNetV2 with 0.25x output channels.

Examples

>>> import paddle
>>> from paddle.vision.models import shufflenet_v2_x0_25

>>> # build model
>>> model = shufflenet_v2_x0_25()

>>> # build model and load imagenet pretrained weight
>>> # model = shufflenet_v2_x0_25(pretrained=True)

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

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