文章：《OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks》
代码：https://github.com/rbgirshick/rcnn，prototxt文件在\rcnn-master\finetuning\voc_2012_prototxt
文章：《Fast R-CNN》 代码：https://github.com/rbgirshick/fast-rcnn，prototxt文件在.\fast-rcnn-master\models\CaffeNet
文章：《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》 代码：https://github.com/rbgirshick/py-faster-rcnn，prototxt文件在.\py-faster-rcnn-master\models\pascal_voc\VGG16\faster_rcnn_end2end tensorflow的代码：tf-faster-rcnn代码理解
文章：《You Only Look Once: Unified, Real-Time Object Detection》 代码：https://github.com/xingwangsfu/caffe-yolo 文章：《YOLO9000: Better, Faster, Stronger》
文章：《SSD: Single Shot MultiBox Detector》 代码：https://github.com/weiliu89/caffe/tree/ssd 由于SSD中需要运行python examples/ssd/ssd_pascal.py来生成solver.prototxt, train.prototxt, test.prototxt, deploy.prototxt。如果你没有硬件运行代码或嫌麻烦，可以在这里直接看https://gist.github.com/JeffOwOSun/1c284e6177c38b17d83da1db7b8c8ce7
文章：《Feature Pyramid Networks for Object Detection》
文章：《Mask R-CNN》
文章：《Fully Convolutional Networks for Semantic Segmentation》 代码：https://github.com/shekkizh/FCN.tensorflow
文章：《Very Deep Convolutional Networks for Large-scale image recognition》
文章： Inception v1:《Going Deeper with Convolutions》 Inception v2:《Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate 》 Inception v3:《Rethinking the Inception Architecture for Computer Vision》
文章：《Deep Residual Learning for Image Recognition》 代码：https://github.com/KaimingHe/deep-residual-networks 补充文章：《Residual Networks Behave Like Ensembles of Relatively Shallow Networks》
《An overview of gradient descent optimization algorithms*》
《Dropout: A Simple Way to Prevent Neural Networks from Overfitting》
相关解读：神经风格迁移研究概述：从当前研究到未来方向（附论文和代码）
