imaginaire.third_party.bias_act package

Submodules

imaginaire.third_party.bias_act.bias_act module

class imaginaire.third_party.bias_act.bias_act.FusedNonlinearity(nonlinearity, num_channels=None, lr_mul=1.0, alpha=None, impl='cuda', gain=None)[source]

Bases: torch.nn.modules.module.Module

forward(x)[source]

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 = None

imaginaire.third_party.bias_act.setup module

Module contents

class imaginaire.third_party.bias_act.FusedNonlinearity(nonlinearity, num_channels=None, lr_mul=1.0, alpha=None, impl='cuda', gain=None)[source]

Bases: torch.nn.modules.module.Module

forward(x)[source]

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 = None