This repository contains tensorflow/keras implementations of some of the well-known deep learning architectures. I have tried to implement them just so I could have a better understanding of each model. I hope this helps you as well. Please let me know if you notice any mistake or if you have a comment.
-
- AlexNet: ImageNet Classification with Deep Convolutional Neural Networks (2012)
- VGG Net: Very Deep Convolutional Networks for Large-Scale Image Recognition (2014)]
- Inception v1: Going Deeper with Convolution (2014)
- Inception v2 and v3: Rethinking the Inception Architecture for Computer Vision (2015)
- ResNet v1: Deep Residual Learning for Image Recognition (2015)
- ResNet v2: Identity Mapping in Deep Residual Networks (2016)
- ResNext: Aggregated Residual Transformations for Deep Neural Networks (2017)
- Inception v4, Inception-ResNet V1 and V2: The impact of Residual Connections on Learning (2016)
- Xception Model: Deep Learning with Depthwise Separable Convolutions (2017)
- MobileNet v1: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017)
- MobileNet v2: Inverted Residuals and Linear Bottlenecks (2019)
- HRNet Deep High-Resolution Representation Learning for Visual Recognition (2019)
-
- Fully Convolution Networks for Semantic Segmentation (2014)
- U-Net: CNNs for Biomedical Image Segmentation (2015)
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2016)
- DeepLab v1: Semantic Image Segmentation with Deep Convolutional Nets, and Fully Connected CRFs (2016)
- DeepLab v2: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2017)
- DeepLab v3: Rethinking Atrous Convolution for Semantic Image Segmentation (2017)
- DeepLab v3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018)
- HRNet Deep High-Resolution Representation Learning for Visual Recognition (2019)