ShuffleNet v2

model	accuracy	top 5 accuracy
0.5x	0.607	0.822
1.0x	0.688	0.886

You can download ImageNet trained checkpoints from here.

How to use the pretrained models

You only need two things:

File architecture.py. It contains a definition of the graph.
Checkpoint. You can load it into the graph using tf.train.Saver or tf.train.init_from_checkpoint.

For an example of using the pretrained model see: inference_with_trained_model.ipynb.

All measurements were done using batches of size 8, images of size 224x224, and NVIDIA GTX 1080 Ti.
See benchmark_speed.ipynb for the code.

MobileNet v1 results are taken from here. MobileNet v2 results are taken from here.

Prepare ImageNet. See data/README.md.
Set the right parameters in the beginning of train.py file.
Run python train.py.
Run tensorboard to see the loss curves. Examples of loss curves are in images/.
Use evaluation.ipynb for the final evaluation on ImageNet.

The training code is heavily inspired by: