googlenet¶

paddle.vision.models. googlenet ( pretrained=False, **kwargs ) [源代码] ¶

GoogLeNet（Inception v1）模型，来自论文 "Going Deeper with Convolutions" 。

参数¶

pretrained (bool，可选) - 是否加载预训练权重。如果为 True，则返回在 ImageNet 上预训练的模型。默认值为 False。

**kwargs (可选) - 附加的关键字参数，具体可选参数请参见 GoogLeNet。

返回¶

Layer，GoogLeNet（Inception v1）模型实例。

代码示例¶

          import paddle
from paddle.vision.models import googlenet

# build model
model = googlenet()

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

x = paddle.rand([1, 3, 224, 224])
out, out1, out2 = model(x)

print(out.shape, out1.shape, out2.shape)
# [1, 1000] [1, 1000] [1, 1000]

         