densenet161

paddle.vision.models. densenet161 ( pretrained=False, **kwargs ) [源代码]

161层的densenet模型，来自论文 "Densely Connected Convolutional Networks" 。

参数

  • pretrained (bool，可选) - 是否加载在imagenet数据集上的预训练权重。默认值：False。

返回

densenet161模型，Layer的实例。

代码示例

import paddle
from paddle.vision.models import densenet161

# build model
model = densenet161()

# build model and load imagenet pretrained weight
# model = densenet161(pretrained=True)

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

print(out.shape)