igibson.learn package

Submodules

igibson.learn.completion module

class igibson.learn.completion.AdaptiveNorm2d(nchannel, momentum=0.05)

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

class igibson.learn.completion.CompletionNet(norm=<class 'igibson.learn.completion.AdaptiveNorm2d'>, nf=64, skip_first_bn=False)

Bases: torch.nn.modules.module.Module

The “Goggle” neural network from Gibson v1

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 igibson.learn.completion.Perceptual(features)

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

igibson.learn.completion.identity_init(m)

Module contents