`fedlab_core.models.mobilenetv2`¶

MobileNetV2 in PyTorch.

See the paper “Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation” for more details.

Module Contents¶

Classes¶

`Block`	expand + depthwise + pointwise
`MobileNetV2`

Functions¶

class fedlab_core.models.mobilenetv2.Block(in_planes, out_planes, expansion, stride)¶

Bases: torch.nn.Module

expand + depthwise + pointwise

forward(self, x)¶

class fedlab_core.models.mobilenetv2.MobileNetV2(num_classes=10)¶

Bases: torch.nn.Module

cfg = [[1, 16, 1, 1], [6, 24, 2, 1], [6, 32, 3, 2], [6, 64, 4, 2], [6, 96, 3, 1], [6, 160, 3, 2], [6, 320, 1, 1]]¶

_make_layers(self, in_planes)¶

forward(self, x)¶

fedlab_core.models.mobilenetv2.test()¶