Copied the content from here: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet

EfficientNets to run on GPU

[1] ICML 2019 paper, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Arxiv link: https://arxiv.org/abs/1905.11946.

1. About EfficientNet Models

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

Google developed EfficientNets based on AutoML and Compound Scaling. In particular, they first use AutoML Mobile framework to develop a mobile-size baseline network, named as EfficientNet-B0; Then, they use the compound scaling method to scale up this baseline to obtain EfficientNet-B1 to B7.

EfficientNets achieve state-of-the-art accuracy on ImageNet with an order of magnitude better efficiency:

• In high-accuracy regime, Google's EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet with 66M parameters and 37B FLOPS, being 8.4x smaller and 6.1x faster on CPU inference than previous best Gpipe.

• In middle-accuracy regime, Google's EfficientNet-B1 is 7.6x smaller and 5.7x faster on CPU inference than ResNet-152, with similar ImageNet accuracy.

• Compared with the widely used ResNet-50, Google's EfficientNet-B4 improves the top-1 accuracy from 76.3% of ResNet-50 to 82.6% (+6.3%), under similar FLOPS constraint.

2. Using Pretrained EfficientNet Checkpoints

Here is a list of EfficientNet checkpoints for EfficientNet-B0, EfficientNet-B1, EfficientNet-B2, and EfficientNet-B3.

A quick way to use these checkpoints is to use the following commands:

$ export MODEL=efficientnet-b0
$ wget https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/${MODEL}.tar.gz
$ tar zxf ${MODEL}.tar.gz
$ python eval_ckpt_main.py --model_name=$MODEL --ckpt_dir=$MODEL --example_img=panda.jpg --labels_map_file=labels_map.txt

Output