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

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

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

• PyTorch Implementation with imagenet training log and pre-trained model by d-li14
• MXNet Implementation with imagenet training log by terrychenism
• Keras Implementation with cifar10 results by koshian2
• PyTorch实现 与imagenet训练记录和预先训练模型的d-LI14
• 通过Terrychenism 使用imagenet训练日志进行MXNet实现
• 通过koshian2，Keras实现 与cifar10结果

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.