composer.models.resnet9_cifar10.model#

composer.models.resnet9_cifar10.model

Classes

BasicBlock

torchvision.models.resnet.BasicBlock

CIFAR10_ResNet9

A ResNet-9 model extending ComposerClassifier.

ComposerClassifier

Implements the base logic that all classifiers can build on top of.

Initializer

An enumeration.

ResNet9

A 9-layer residual network, excluding BatchNorms and activation functions, as described in this blog post:

Attributes

  • List

  • Optional

class composer.models.resnet9_cifar10.model.CIFAR10_ResNet9(num_classes, initializers=None)[source]#

Bases: composer.models.base.ComposerClassifier

A ResNet-9 model extending ComposerClassifier.

See this blog post for details regarding the architecture: https://myrtle.ai/learn/how-to-train-your-resnet-4-architecture/

Parameters

  • num_classes (int) – The number of classes for the model.

  • initializers (List[Initializer], optional) – Initializers for the model. None for no initialization. (default: None)

class composer.models.resnet9_cifar10.model.ResNet9(num_classes)[source]#

Bases: torch.nn.modules.module.Module

A 9-layer residual network, excluding BatchNorms and activation functions, as described in this blog post:

https://myrtle.ai/learn/how-to-train-your-resnet-4-architecture/