fedlab_core.models.preact_resnet

Pre-activation ResNet in PyTorch.

Reference: [1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

Identity Mappings in Deep Residual Networks. arXiv:1603.05027

Module Contents

Classes

PreActBlock	Pre-activation version of the BasicBlock.
PreActBottleneck	Pre-activation version of the original Bottleneck module.
PreActResNet

Functions

PreActResNet18()
PreActResNet34()
PreActResNet50()
PreActResNet101()
PreActResNet152()
test()

class fedlab_core.models.preact_resnet.PreActBlock(in_planes, planes, stride=1)

Bases: torch.nn.Module

Pre-activation version of the BasicBlock.

expansion = 1

forward(self, x)

class fedlab_core.models.preact_resnet.PreActBottleneck(in_planes, planes, stride=1)

Bases: torch.nn.Module

Pre-activation version of the original Bottleneck module.

expansion = 4

forward(self, x)

class fedlab_core.models.preact_resnet.PreActResNet(block, num_blocks, num_classes=10)

Bases: torch.nn.Module

_make_layer(self, block, planes, num_blocks, stride)

forward(self, x)

fedlab_core.models.preact_resnet.PreActResNet18()

fedlab_core.models.preact_resnet.PreActResNet34()

fedlab_core.models.preact_resnet.PreActResNet50()

fedlab_core.models.preact_resnet.PreActResNet101()

fedlab_core.models.preact_resnet.PreActResNet152()

fedlab_core.models.preact_resnet.test()