深度学习的经典算法的论文、解读和代码实现

CNN网络的经典算法

LeNet-5

• 来源论文：LeCun, Yann, et al. “Gradient-based learning applied to document recognition.” Proceedings of the IEEE 86.11 (1998): 2278-2324.
• 论文详解：CNN入门算法LeNet-5详解
• 代码实现：https://github.com/TaavishThaman/LeNet-5-with-Keras

AlexNet

• 来源论文：Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. “Imagenet classification with deep convolutional neural networks.” Advances in neural information processing systems. 2012.
• 论文详解：CNN经典算法AlexNet介绍
• 代码实现：https://github.com/hjptriplebee/AlexNet_with_tensorflow

VGG

• 来源论文：Simonyan, Karen, and Andrew Zisserman. “Very deep convolutional networks for large-scale image recognition.” arXiv preprint arXiv:1409.1556 (2014).
• 论文详解：CNN经典算法VGGNet介绍
• 代码和预训练资源：VGGNet预训练模型及代码资源

Inception

Inception-v1(GoogLeNet)

• 来源论文：Szegedy, Christian, et al. “Going deeper with convolutions.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
• 论文详解：CNN经典算法之Inception V1（GoogLeNet）
• 代码和预训练资源：GoogLeNet代码资源（Tensorflow）

BN-Inception

• 来源论文：Szegedy, Christian, et al. “Inception-v4, inception-resnet and the impact of residual connections on learning.” Proceedings of the AAAI conference on artificial intelligence. Vol. 31. No. 1. 2017.
• 论文详解：CNN经典算法之BN-Inception
• 代码和预训练资源：BN-Inception代码资源

ResNet

• 来源论文：Targ, Sasha, Diogo Almeida, and Kevin Lyman. “Resnet in resnet: Generalizing residual architectures.” arXiv preprint arXiv:1603.08029 (2016).
• 论文详解：ResNet论文详解
• 代码实现：ResNet代码（超详细注释）+数据集下载地址

R-CNN

R-CNN

• 来源论文：Girshick, Ross, et al. “Rich feature hierarchies for accurate object detection and semantic segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
• 论文详解：R-CNN论文详解
• 代码实现：R-CNN代码

Fast R-CNN

• 来源论文：Girshick, Ross. “Fast r-cnn.” Proceedings of the IEEE international conference on computer vision. 2015.
• 论文详解：Fast R-CNN论文详解
• 代码实现：Fast R-CNN代码

Faster R-CNN

• 来源论文：Ren, Shaoqing, et al. “Faster r-cnn: Towards real-time object detection with region proposal networks.” Advances in neural information processing systems 28 (2015).
• 论文详解：一文读懂Faster RCNN
• 代码实现：Faster R-CNN代码实现

YOLO

YOLO v1

• 来源论文：YOLO v1论文
• 论文详解：YOLO v1详解
• 代码实现：YOLO v1代码实现

YOLO v2

• 来源论文：YOLO v2论文
• 论文详解：YOLO v2详解
• 代码实现：YOLO v2代码实现

YOLO v3

• 来源论文：YOLO v3论文
• 论文详解：YOLO v3详解
• 代码实现：YOLO v3代码

YOLO v4

• 来源论文：YOLO v4论文
• 论文详解：YOLO v4详解
• 代码实现：YOLO v4代码

RNN的经典算法

RNN

• 来源论文：Sherstinsky, Alex. “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network.” Physica D: Nonlinear Phenomena 404 (2020): 132306.
• 论文详解：通俗易懂的RNN
• 代码实现：RNN代码

GRU

• 来源论文：Dey, Rahul, and Fathi M. Salem. “Gate-variants of gated recurrent unit (GRU) neural networks.” 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, 2017.
• 论文详解：GRU(门控循环单元)，易懂
• 代码实现：GRU代码

LSTM

• 来源论文：Huang, Zhiheng, Wei Xu, and Kai Yu. “Bidirectional LSTM-CRF models for sequence tagging.” arXiv preprint arXiv:1508.01991 (2015).
• 论文详解：如何从RNN起步，一步一步通俗理解LSTM
• 代码实现：LSTM代码实现

Encoder-Decoder

• 来源论文：Badrinarayanan, Vijay, Alex Kendall, and Roberto Cipolla. “Segnet: A deep convolutional encoder-decoder architecture for image segmentation.” IEEE transactions on pattern analysis and machine intelligence 39.12 (2017): 2481-2495.
• 论文详解：Encoder-Decoder 模型架构详解
• 代码实现：Encoder-Decoder代码实现

Attention

• 来源论文：Knudsen, Eric I. “Fundamental components of attention.” Annu. Rev. Neurosci. 30 (2007): 57-78.
• 论文详解：注意力机制介绍（attention）
• 代码实现：Attention代码

Transformer

• 来源论文：Kitaev, Nikita, Łukasz Kaiser, and Anselm Levskaya. “Reformer: The efficient transformer.” arXiv preprint arXiv:2001.04451 (2020).
• 论文详解：Transform详解
• 代码实现：Transformer代码