EfficientNet-V1-B4 checkpoint (TensorFlow2, AMP, Imagenet)

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

EfficientNet v1 is developed based on AutoML and Compound Scaling. In particular, a mobile-size baseline network called EfficientNet v1-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 v1-B1 to B7.

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

• Original paper
• NVIDIA model implementation in NGC
• NVIDIA model implementation on GitHub

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.