Implementation_DeepLearningPaper

< Implementation of Model in Deep learning Paper with PyTorch >
You can read the reviews about these models from my blog : https://mole-starseeker.tistory.com

CNN (Classification)

0. Standard (Just ToyNet for Implementation of Deep Learning Model) [Code]

1. VGG16 (Very Deep Convolutional Networks for Large-Scale Image Recognition) [Code] [Paper]

2. GoogLeNet (Going Deeper with Convolutions) [Code] [Paper]

3. Inception V2, V3 (Rethinking the Inception Architecture for Computer Vision) [Code] [Paper]

4. ResNet (Deep Residual Learning for Image Recognition) [Code] [Paper]

5. Inception V4 (Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning) [Code] [Paper]

6. Inception-ResNet V1, V2 (Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning) [Code1] [Code2] [Paper]

7. DenseNet (Densely Connected Convolutional Networks) [Code] [Paper]

8. SqueezeNet (SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size) [Code] [Paper]

9. Xception (Xception: Deep Learning with Depthwise Separable Convolutions) [Code] [Paper]

10. MobileNet (MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications) [Code] [Paper]

11. ResNext (Aggregated Residual Transformations for Deep Neural Networks) [Code] [Paper]

---

SR (Super Resolution)

1. SRCNN (Image Super-Resolution Using Deep Convolutional Networks) [Code] [Paper]

2. VDSR (Accurate Image Super-Resolution Using Very Deep Convolutional Networks) [Code] [Paper]

3. SESR (SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks) [Code] [Paper]

---

GAN (Generatice Adversarial Networks)

1. Vanilla GAN (Generatice Adversarial Networks) [Code] [Paper]