CNN结构模型一句话概述：从LeNet到ShuffleNet

由简入繁，由繁入简。已疯……

1. LeNet：Gradient based learning applied to document recognition
2. AlexNet：ImageNet Classification with Deep Convolutional Neural Networks
3. ZFNet：Visualizing and understanding convolutional networks
4. VGGNet：Very deep convolutional networks for large-scale image recognition
5. NiN：Network in network
6. GoogLeNet：Going deeper with convolutions
7. Inception-v3：Rethinking the inception architecture for computer vision
8. ResNet：Deep residual learning for image recognition
9. Stochastic_Depth：Deep networks with stochastic depth
10. WResNet：Weighted residuals for very deep networks
11. Inception-ResNet：Inception-v4,inception-resnet and the impact of residual connections on learning
12. Fractalnet：Ultra-deep neural networks without residuals
13. WRN：Wide residual networks
14. ResNeXt：Aggregated Residual Transformations for Deep Neural Networks
15. DenseNet：Densely connected convolutional networks
16. PyramidNet：Deep Pyramidal Residual Networks
17. DPN：Dual Path Networks
18. SqueezeNet：AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
19. MobileNets：Efficient Convolutional Neural Networks for Mobile Vision Applications
20. ShuffleNet：An Extremely Efficient Convolutional Neural Network for Mobile Devices
21. LeNet：基于渐变的学习应用于文档识别
22. AlexNet：具有深卷积神经网络的ImageNet分类
23. ZFNet：可视化和理解卷积网络
24. VGGNet：用于大规模图像识别的非常深的卷积网络
25. NiN：网络中的网络
26. GoogLeNet：卷入更深入
27. Inception-v3：重新思考计算机视觉的初始架构
28. ResNet：图像识别的深度残差学习
29. Stochastic_Depth：具有随机深度的深层网络
30. WResNet：非常深的网络的加权残差
31. Inception-ResNet：Inception-v4，inception-resnet以及剩余连接对学习的影响
32. Fractalnet：没有残差的超深层神经网络
33. WRN：宽残留网络
34. ResNeXt：深层神经网络的聚合残差变换
35. DenseNet：密集连接的卷积网络
36. PyramidNet：深金字塔残留网络
37. DPN：双路径网络
38. SqueezeNet：AlexNet级准确度，参数减少50倍，模型尺寸小于0.5MB
39. MobileNets：用于移动视觉应用的高效卷积神经网络
40. ShuffleNet：移动设备极高效的卷积神经网络

原创文章，转载请注明： 转载自URl-team

本文链接地址: CNN结构模型一句话概述：从LeNet到ShuffleNet