densenet121¶
121 层的 DenseNet 模型,来自论文 "Densely Connected Convolutional Networks" 。
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 DenseNet。
代码示例¶
import paddle
from paddle.vision.models import densenet121
# build model
model = densenet121()
# build model and load imagenet pretrained weight
# model = densenet121(pretrained=True)
x = paddle.rand([1, 3, 224, 224])
out = model(x)
print(out.shape)
# [1, 1000]