vgg19

paddle.vision.models.vgg19 ( pretrained=False, batch_norm=False, \*kwargs* ) [源代码]

vgg19模型,来自论文 “Very Deep Convolutional Networks For Large-Scale Image Recognition”

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。

  • batch_norm (bool, 可选) - 是否在每个卷积层后添加批归一化层。默认值:False。

返回

vgg19模型,Layer的实例。

代码示例

  1. import paddle
  2. from paddle.vision.models import vgg19
  3. # build model
  4. model = vgg19()
  5. # build vgg19 model with batch_norm
  6. model = vgg19(batch_norm=True)
  7. x = paddle.rand([1, 3, 224, 224])
  8. out = model(x)
  9. print(out.shape)