MinkowskiEngine.modules package

Submodules

MinkowskiEngine.modules.resnet_block module

class MinkowskiEngine.modules.resnet_block.BasicBlock(inplanes, planes, stride=1, dilation=1, downsample=None, bn_momentum=0.1, dimension=- 1)

Bases: torch.nn.modules.module.Module

expansion = 1

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

class MinkowskiEngine.modules.resnet_block.Bottleneck(inplanes, planes, stride=1, dilation=1, downsample=None, bn_momentum=0.1, dimension=- 1)

Bases: torch.nn.modules.module.Module

expansion = 4

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

MinkowskiEngine.modules.senet_block module

class MinkowskiEngine.modules.senet_block.SEBasicBlock(inplanes, planes, stride=1, dilation=1, downsample=None, reduction=16, D=- 1)

Bases: MinkowskiEngine.modules.resnet_block.BasicBlock

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

class MinkowskiEngine.modules.senet_block.SEBottleneck(inplanes, planes, stride=1, dilation=1, downsample=None, D=3, reduction=16)

Bases: MinkowskiEngine.modules.resnet_block.Bottleneck

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

class MinkowskiEngine.modules.senet_block.SELayer(channel, reduction=16, D=- 1)

Bases: torch.nn.modules.module.Module

forward(x)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool

Module contents