2018 CVPR论文:Universal Deep Neural Network Compression https://arxiv.org/abs/1802.02271
DNN通用压缩算法,基于权重量化和无损编码。
主要在于压缩模型的体积。
提出了效果更好的 Hessian权重K均值聚类、两种熵编码量化方法(统一量化和迭代方法)、网格量化
In this paper, we focus on finding memory-efficient DNN
models
2018 MobileNetV2: Inverted Residuals and Linear Bottlenecks : https://arxiv.org/pdf/1801.04381.pdf
tensorflow官方实现:https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet
深度 | 级联MobileNet-V2实现人脸关键点检测(附训练源码)
本实验所有代码可在 GitHub 上获得:https://github.com/tensor-yu/cascaded_mobilenet-v2
详细训练步骤可参见博客:http://blog.csdn.net/u011995719/article/details/79435615
Caffe实现:https://github.com/goodluckcwl/Face-alignment-mobilenet-v2
2017 CVPR 论文 MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications https://arxiv.org/abs/1704.04861
MobileNets 论文笔记
官方实现:https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.md
用于目标检测的官方实现:https://github.com/tensorflow/models/tree/master/research/object_detection
其他实现:https://github.com/Zehaos/MobileNet
2016 CVPR论文: Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding https://arxiv.org/abs/1510.00149
【深度神经网络压缩】Deep Compression (ICLR2016 Best Paper)
神经网络压缩:Deep Compression
神经网络压缩和加速
网友评论