composer.models.resnet9_cifar10.model

A ResNet-9 model extending ComposerClassifier and ResNet-9 architecture.

Classes

CIFAR10_ResNet9	A ResNet-9 model extending ComposerClassifier.
ResNet9	A 9-layer residual network, excluding BatchNorms and activation functions.

class composer.models.resnet9_cifar10.model.CIFAR10_ResNet9(num_classes=10)

Bases: composer.models.base.ComposerClassifier

A ResNet-9 model extending ComposerClassifier.

See myrtle.ai blog for more details.

Parameters

num_classes (int, optional) – The number of classes. Needed for classification tasks. Default: 10.

Example:

from composer.models import CIFAR10_ResNet9

model = CIFAR10_ResNet9()  # creates a resnet9 for cifar image classification

class composer.models.resnet9_cifar10.model.ResNet9(num_classes=10)

Bases: torch.nn.modules.module.Module

A 9-layer residual network, excluding BatchNorms and activation functions.

Based on the myrtle.ai blog and Deep Residual Learning for Image Recognition (He et al, 2015).

Parameters

num_classes (int, optional) – The number of classes. Needed for classification tasks. Default: 10.