composer.algorithms.stochastic_depth.stochastic_layers#
Stochastic forward functions for ResNet Bottleneck modules.
Functions
ResNet Bottleneck forward function where the layers are randomly skipped with probability |
|
Model surgery policy that dictates how to convert a ResNet Bottleneck layer into a stochastic version. |
|
ResNet Bottleneck forward function where samples are randomly dropped with probability |
Classes
|
torchvision.models.resnet.Bottleneck |
- composer.algorithms.stochastic_depth.stochastic_layers.block_stochastic_forward(self, x)[source]#
ResNet Bottleneck forward function where the layers are randomly skipped with probability
drop_rate
during training.