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.