composer.models.efficientnetb0.model#

A ComposerClassifier wrapper around the EfficientNet-b0 architecture.

Classes

EfficientNetB0

A ComposerClassifier wrapper around the EfficientNet-b0 architecture.
class composer.models.efficientnetb0.model.EfficientNetB0(num_classes=1000, drop_connect_rate=0.2)[source]#

Bases: composer.models.tasks.classification.ComposerClassifier

A ComposerClassifier wrapper around the EfficientNet-b0 architecture. From Rethinking Model Scaling for Convolutional Neural Networks (Tan et al, 2019).

Parameters

  • num_classes (int, optional) โ€“ The number of classes. Needed for classification tasks. Default: 1000.

  • drop_connect_rate (float, optional) โ€“ Probability of dropping a sample within a block before identity connection. Default: 0.2.

Example:

from composer.models import EfficientNetB0

model = EfficientNetB0()  # creates EfficientNet-b0 for image classification