InceptionV3¶

class paddle.vision.models. InceptionV3 ( num_classes=1000, with_pool=True ) [source]

Inception v3 model from “Rethinking the Inception Architecture for Computer Vision”.

Parameters

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

• with_pool (bool, optional) – Use pool before the last fc layer or not. Default: True.

Returns

Layer. An instance of Inception v3 model.

Examples

>>> import paddle
>>> from paddle.vision.models import InceptionV3

>>> inception_v3 = InceptionV3()

>>> x = paddle.rand([1, 3, 299, 299])
>>> out = inception_v3(x)

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

forward ( x )

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