Octave Convolution卷積
MXNet implementation 實現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.
筆記：
? 表中顯示了Top-1 / Top-5，單中心crop精度。（測試腳本）
? 為了方便起見，消融研究中的所有殘留網絡均采用了預訓練版本
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實現 與imagenet訓練記錄和預先訓練模型的d-LI14
? 通過Terrychenism 使用imagenet訓練日志進行MXNet實現
? 通過koshian2，Keras實現 與cifar10結果

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.

總結

以上是生活随笔為你收集整理的Octave Convolution卷积的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。