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