Octave Convolution卷积

Octave Convolution卷积

MXNet implementation 实现for:

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

ImageNet

Ablation

  • Loss: Softmax
  • Learning rate: Cosine (warm-up: 5 epochs, lr: 0.4)
  • MXNet API: Symbol API

https://github.com/facebookresearch/OctConv

 Octave Convolution卷积

 

 Note:

  • Top-1 / Top-5, single center crop accuracy is shown in the table. (testing script)
  • All residual networks in ablation study adopt pre-actice version for convenience.

笔记:

  • 表中显示了Top-1 / Top-5,单中心crop精度。(测试脚本
  • 为了方便起见,消融研究中的所有残留网络均采用了预训练版本

Others

  • Learning rate: Cosine (warm-up: 5 epochs, lr: 0.4)
  • MXNet API: Gluon API

 Octave Convolution卷积

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={Proceedings of the IEEE International Conference on Computer Vision},

  year={2019}

}

Third-party Implementations

 

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.

 

上一篇:Spark分区器HashPartitioner和RangePartitioner代码详解


下一篇:一种联合分类与检测训练的方法——YOLO9000