A tutorial on Residual Networks which was originally proposed by Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun from Microsoft Research Team.
ResNets achieved 1st places in all five main tracks,
- ImageNet Classification: “Ultra-deep” 152-layer nets
- ImageNet Detection: 16% better than 2nd
- ImageNet Localization: 27% better than 2nd
- COCO Detection: 11% better than 2nd
- COCO Segmentation: 12% better than 2nd
The will be a programming tutorial on ResNets with Keras which is added as another Jupyter Notebook in this repo. Original paper is also added.
Happy Learning :)