densenet121¶

paddle.vision.models. densenet121 ( pretrained=False, **kwargs ) [source]

DenseNet 121-layer model from “Densely Connected Convolutional Networks”.

Parameters

• pretrained (bool, optional) – Whether to load pre-trained weights. If True, returns a model pre-trained on ImageNet. Default: False.

• **kwargs (optional) – Additional keyword arguments. For details, please refer to DenseNet.

Returns

Layer. An instance of DenseNet 121-layer model.

Examples

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]