resnet50¶

paddle.vision.models. resnet50 ( pretrained=False, **kwargs ) [源代码] ¶

50 层的 ResNet 模型，来自论文 "Deep Residual Learning for Image Recognition" 。

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：False。

返回¶

50 层的 ResNet 模型，Layer 的实例。

代码示例¶

          import paddle
from paddle.vision.models import resnet50

# build model
model = resnet50()

# build model and load imagenet pretrained weight
# model = resnet50(pretrained=True)

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

print(out.shape)
# [1, 1000]

         