ShuffleNet v2
This is an implementation of ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design .
model | accuracy | top 5 accuracy |
---|---|---|
0.5x | 0.608 | 0.822 |
1.0x | 0.689 | 0.885 |
You can download 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
ortf.train.init_from_checkpoint
.
For an example of using the pretrained model see: inference_with_trained_model.ipynb
.
Requirements
- for using the pretrained models:
tensorflow 1.10
- for dataset preparation:
pandas, Pillow, tqdm, opencv, ...
How to train
- Prepare ImageNet. See
data/README.md
. - Set the right parameters in the beginning of
train.py
file. - Run
python train.py
.
Credit
The training code is heavily inspired by:
- https://github.com/tensorflow/models/tree/master/official/resnet
- https://cloud.google.com/tpu/docs/inception-v3-advanced