GitHub - facebookresearch/OctConv: Code for paper
source link: https://github.com/facebookresearch/OctConv
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
Octave Convolution
MXNet implementation for:
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Note:
- This repo is under development.
To Do List
- Code for ablation study (by Symbol API)
- Code for the rest exps (by Gluon API)
- Training script
- Training logs
- Trained models
ImageNet
Ablation
- Loss: Softmax
- Learning rate: Cosine (warm-up: 5 epochs, lr: 0.4)
- MXNet API: Symbol API
Note:
- All residual networks in ablation study adopt pre-actice version[1] for convenience.
Others
- Learning rate: Cosine (warm-up: 5 epochs, lr: 0.4)
- MXNet API: Gluon API
Model alpha label smoothing[2] mixup[3] #Params #FLOPs Top1 0.75 MobileNet (v1) .375
2.6 M 213 M 70.6 1.0 MobileNet (v1) .5
4.2 M 321 M 72.4 1.0 MobileNet (v2) .375 Yes
3.5 M 256 M 72.0 1.125 MobileNet (v2) .5 Yes
4.2 M 295 M 73.0 Oct-ResNet-152 .125 Yes Yes 60.2 M 10.9 G 81.4 Oct-ResNet-152 + SE .125 Yes Yes 66.8 M 10.9 G 81.6
Citation
@article{chen2019drop,
title={Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution},
author={Chen, Yunpeng and Fan, Haoqi and Xu, Bing and Yan, Zhicheng and Kalantidis, Yannis and Rohrbach, Marcus and Yan, Shuicheng and Feng, Jiashi},
journal={arXiv preprint arXiv:1904.05049},
year={2019}
}
Third-party Implementations
- MXNet Implementation with imagenet training log by terrychenism
- Keras Implementation with cifar10 results by koshian2
Acknowledgement
- Thanks MXNet, Gluon-CV and TVM!
- Thanks @Ldpe2G for sharing the code for calculating the #FLOPs (
link
) - Thanks Min Lin (Mila), Xin Zhao (Qihoo Inc.), Tao Wang (NUS) for helpful discussions on the code development.
Reference
[1] He K, et al "Identity Mappings in Deep Residual Networks".
[2] Christian S, et al "Rethinking the Inception Architecture for Computer Vision"
[3] Zhang H, et al. "mixup: Beyond empirical risk minimization.".
License
The code and the models are MIT licensed, as found in the LICENSE file.
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK