-[Script and Sample Code](#script-and-sample-code)
-[Training Process](#training-process)
-[Evaluation Process](#evaluation-process)
-[Evaluation](#evaluation)
-[Model Description](#model-description)
-[Performance](#performance)
-[Training Performance](#evaluation-performance)
-[Inference Performance](#evaluation-performance)
# [ShuffleNetV2 Description](#contents)
ShuffleNetV2 is a much faster and more accurate netowrk than the previous networks on different platforms such as Ascend or GPU.
[Paper](https://arxiv.org/pdf/1807.11164.pdf) Ma, N., Zhang, X., Zheng, H. T., & Sun, J. (2018). Shufflenet v2: Practical guidelines for efficient cnn architecture design. In Proceedings of the European conference on computer vision (ECCV) (pp. 116-131).
# [Model architecture](#contents)
The overall network architecture of ShuffleNetV2 is show below:
GPU: sh run_distribute_train_for_gpu.sh ~/imagenet/train/
```
### Result
Training result will be stored in the example path. Checkpoints will be stored at `. /checkpoint` by default, and training log will be redirected to `./train/train.log`.
## [Eval process](#contents)
### Usage
You can start evaluation using python or shell scripts. The usage of shell scripts as follows:
- GPU: sh run_eval_for_multi_gpu.sh [DEVICE_ID] [EPOCH]