composer.models.classify_mnist.model#

A simple convolutional neural network extending ComposerClassifier.

Classes

MNIST_Classifier

A simple convolutional neural network extending ComposerClassifier.

Model

Toy convolutional neural network architecture in pytorch for MNIST.
class composer.models.classify_mnist.model.MNIST_Classifier(num_classes=10, initializers=None)[source]#

Bases: composer.models.tasks.classification.ComposerClassifier

A simple convolutional neural network extending ComposerClassifier. This class makes Model compatible with Trainer

Parameters

  • num_classes (int, optional) โ€“ The number of classes. Needed for classification tasks. Default: 10

  • initializers (List[Initializer], optional) โ€“ list of Initializers for the model. None for no initialization. Default: None

Example:

from composer.models import MNIST_Classifier

model = MNIST_Classifier()
class composer.models.classify_mnist.model.Model(initializers, num_classes=10)[source]#

Bases: torch.nn.modules.module.Module

Toy convolutional neural network architecture in pytorch for MNIST.