AlexNet

class paddle.vision.models. AlexNet ( num_classes=1000 ) [source]

AlexNet model from “ImageNet Classification with Deep Convolutional Neural Networks”.

Parameters

num_classes (int, optional) – Output dim of last fc layer. If num_classes <= 0, last fc layer will not be defined. Default: 1000.

Returns

Layer. An instance of AlexNet model.

Examples

>>> import paddle
>>> from paddle.vision.models import AlexNet

>>> alexnet = AlexNet()
>>> x = paddle.rand([1, 3, 224, 224])
>>> out = alexnet(x)
>>> print(out.shape)
[1, 1000]
forward ( inputs )

forward

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters
  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments