Implementation of ResNet34 & ResNet50 networks using PyTorch as the base.
conda env create -f environment.yml- Performance comparable to PyTorch's own ResNet34 model on CIFAR100 dataset see assets for graph.
- Reached 73% validation accuracy on CIFAR10 dataset using ResNet34 model.
- Trained for approximately an hour and reached 75% validation accuracy on CIFAR10 dataset using ResNet50 model
- Website: morealfit
- Github: @mhd53
Give a ⭐️ if this project helped you!
This project is MIT licensed.
- Deep Residual Learning for Image Recognition, He et al. 2015
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, He et al. 2015
- Very Deep Convolutional Networks For Large-Scale Image Recognition, Simonyan & Zisserman. 2015
- Network In Network, Lin et al. 2014