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)