NGC | Catalog
Welcome Guest
CatalogModelsEfficientNet-V1-B0 checkpoint (TensorFlow2, AMP, Imagenet)

EfficientNet-V1-B0 checkpoint (TensorFlow2, AMP, Imagenet)

For downloads and more information, please view on a desktop device.
Logo for EfficientNet-V1-B0 checkpoint (TensorFlow2, AMP, Imagenet)

Description

EfficientNet v1 B0 trained on Luna-A100 with batch_size=8192

Publisher

NVIDIA Deep Learning Examples

Use Case

Classification

Framework

TensorFlow2

Latest Version

21.09.0

Modified

March 8, 2022

Size

81.28 MB

Model Overview

EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, being an order-of-magnitude smaller and faster.

Model Architecture

EfficientNets are developed based on AutoML and Compound Scaling. In particular, a mobile-size baseline network called EfficientNet-B0 is developed from AutoML MNAS Mobile framework, the building block is mobile inverted bottleneck MBConv with squeeze-and-excitation optimization. Then, through a compound scaling method, this baseline is scaled up to obtain EfficientNet-B1 to B7.

Efficientnet_structure

Training

This model was trained using script available on NGC and in GitHub repo

Dataset

The following datasets were used to train this model:

  • ImageNet - Image database organized according to the WordNet hierarchy, in which each noun is depicted by hundreds and thousands of images.

Performance

Performance numbers for this model are available in NGC

References

License

This model was trained using open-source software available in Deep Learning Examples repository. For terms of use, please refer to the license of the script and the datasets the model was derived from.