Shufflenet V2¶
摘要¶
Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.
使用方式¶
from mmpretrain import inference_model
predict = inference_model('shufflenet-v2-1x_16xb64_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])
import torch
from mmpretrain import get_model
model = get_model('shufflenet-v2-1x_16xb64_in1k', pretrained=True)
inputs = torch.rand(1, 3, 224, 224)
out = model(inputs)
print(type(out))
# To extract features.
feats = model.extract_feat(inputs)
print(type(feats))
Prepare your dataset according to the docs.
训练：
python tools/train.py configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py
测试：
python tools/test.py configs/shufflenet_v2/shufflenet-v2-1x_16xb64_in1k.py https://download.openmmlab.com/mmclassification/v0/shufflenet_v2/shufflenet_v2_batch1024_imagenet_20200812-5bf4721e.pth
Models and results¶
Image Classification on ImageNet-1k¶
模型 |
预训练 |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
配置文件 |
下载 |
|---|---|---|---|---|---|---|---|
|
从头训练 |
2.28 |
0.15 |
69.55 |
88.92 |
引用¶
@inproceedings{ma2018shufflenet,
title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
booktitle={Proceedings of the European conference on computer vision (ECCV)},
pages={116--131},
year={2018}
}