BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
https://github.com/MatthieuCourbariaux/BinaryNet/tree/master/Train-time
代码框架探索
https://github.com/Goingqs/TensorRT-SSD
基于SSD的人脸检测,250fps on gtx1080ti
模型压缩和量化
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
CVPR2018
https://download.csdn.net/download/zhangjunhit/10753249
模型压缩
Constraint-aware deep neural network compression
https://github.com/ChanganVR/ConstraintAwareCompression
自适应模型量化
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
ECCV2018
https://github.com/Microsoft/LQ-Nets
模型量化
Deep Learning with Low Precision by Half-wave Gaussian Quantization
CVPR2017
https://github.com/zhaoweicai/hwgq
模型裁剪的意义
Rethinking the Value of Network Pruning
https://github.com/Eric-mingjie/rethinking-network-pruning
网络裁剪加速
Learning Efficient Convolutional Networks through Network Slimming ICCV2017
https://github.com/liuzhuang13/slimming
CNN网络通道裁剪加速
Channel Pruning for Accelerating Very Deep Neural Networks ICCV2017
https://github.com/yihui-he/channel-pruning
残差网络超快训练
Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates
https://github.com/lnsmith54/super-convergence
通用网络模型加速,不改变网络结构
AAAI 2018
Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks
https://github.com/tianshuichen/Wavelet-like-Auto-Encoder
网络优化
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
https://github.com/jaxony/ShuffleNet
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks
for Real-Time Object Detection for Autonomous Driving
https://github.com/BichenWuUCB/squeezeDet
Coordinating Filters for Faster Deep Neural Networks
https://arxiv.org/abs/1703.09746
https://github.com/wenwei202/caffe/tree/sfm