fedlab_core.models.shufflenet

ShuffleNet in PyTorch.

See the paper “ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices” for more details.

Module Contents

Classes

ShuffleBlock
Bottleneck
ShuffleNet

Functions

ShuffleNetG2()
ShuffleNetG3()
test()

class fedlab_core.models.shufflenet.ShuffleBlock(groups)

Bases: torch.nn.Module

forward(self, x)

Channel shuffle: [N,C,H,W] -> [N,g,C/g,H,W] -> [N,C/g,g,H,w] -> [N,C,H,W]

class fedlab_core.models.shufflenet.Bottleneck(in_planes, out_planes, stride, groups)

Bases: torch.nn.Module

forward(self, x)

class fedlab_core.models.shufflenet.ShuffleNet(cfg)

Bases: torch.nn.Module

_make_layer(self, out_planes, num_blocks, groups)

forward(self, x)

fedlab_core.models.shufflenet.ShuffleNetG2()

fedlab_core.models.shufflenet.ShuffleNetG3()

fedlab_core.models.shufflenet.test()