resnext101_32x4d¶

paddle.vision.models. resnext101_32x4d ( pretrained=False, **kwargs ) [source]

ResNeXt-101 32x4d model from “Aggregated Residual Transformations for Deep Neural 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 ResNet.

Returns

Layer. An instance of ResNeXt-101 32x4d model.

Examples

import paddle
from paddle.vision.models import resnext101_32x4d

# build model
model = resnext101_32x4d()

# build model and load imagenet pretrained weight
# model = resnext101_32x4d(pretrained=True)

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

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