ShuffleNet V2

Model Name:*

Description with Markdown (optional):

# Summary

**ShuffleNet v2** is a convolutional neural network optimized for a direct metric (speed) rather than indirect metrics like FLOPs. It builds upon [ShuffleNet v1](https://paperswithcode.com/method/shufflenet), which utilised pointwise group convolutions, bottleneck-like structures, and a channel shuffle operation. Differences are shown in the model Figure, including a new channel split operation and moving the channel shuffle operation further down the block. The main building block is a [ShuffleNet v2 Block](https://paperswithcode.com/method/shufflenet-v2-block).

## How do I load this model?

To load a pretrained model:

```python
import torchvision.models as models
shufflenet = models.shufflenet_v2_x1_0(pretrained=True)
```

Replace the model name with the variant you want to use, e.g. `shufflenet_v2_x1_0`. You can find the IDs in the model summaries at the top of this page.

To evaluate the model, use the [image classification recipes](https://github.com/pytorch/vision/tree/master/references/classification) from the library.

```bash
python train.py --test-only --model='<model_name>'
```

## How do I train this model?

You can follow the [torchvision recipe](https://github.com/pytorch/vision/tree/master/references/classification) on GitHub for training a new model afresh.

## Citation

```BibTeX
@article{DBLP:journals/corr/abs-1807-11164,
  author    = {Ningning Ma and
               Xiangyu Zhang and
               Hai{-}Tao Zheng and
               Jian Sun},
  title     = {ShuffleNet {V2:} Practical Guidelines for Efficient {CNN} Architecture
               Design},
  journal   = {CoRR},
  volume    = {abs/1807.11164},
  year      = {2018},
  url       = {http://arxiv.org/abs/1807.11164},
  archivePrefix = {arXiv},
  eprint    = {1807.11164},
  timestamp = {Thu, 14 Mar 2019 14:56:07 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1807-11164.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
```

Paper:*

Code URL (optional):

ID	shufflenet_v2_x1_0
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001

Attached motifs:

SQUEEZE-AND-EXCITATION BLOCK

GLOBAL AVERAGE POOLING

SOFTMAX

CONVOLUTION

MAX POOLING

SHUFFLENET V2 BLOCK

CHANNEL SHUFFLE

1X1 CONVOLUTION

RELU

DEPTHWISE CONVOLUTION

BATCH NORMALIZATION

SHUFFLENET V2 DOWNSAMPLING BLOCK

RESIDUAL CONNECTION

SQUEEZE-AND-EXCITATION BLOCK

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	ShuffleNet V2	Top 1 Accuracy	69.36%	# 281
		Top 5 Accuracy	88.32%	# 281

pytorch / vision

Summary

How do I load this model?

How do I train this model?

Citation

Results

Image Classification on ImageNet

Image Classification

Training Techniques	Weight Decay, SGD with Momentum
Architecture	1x1 Convolution, Channel Shuffle, Depthwise Convolution, Squeeze-and-Excitation Block, ShuffleNet V2 Downsampling Block, Batch Normalization, Convolution, Global Average Pooling, ShuffleNet V2 Block, Residual Connection, ReLU, Max Pooling, Softmax
ID	shufflenet_v2_x1_0
LR	0.1
Epochs	90
LR Gamma	0.1
Momentum	0.9
Batch Size	32
LR Step Size	30
Weight Decay	0.0001
SHOW MORE
SHOW LESS