MixRNet(Using mixup as regularization and tuning hyper-parameters for ResNets)
MixRNet(Using mixup as regularization and tuning hyper-parameters for ResNets)
Using mixup data augmentation as reguliraztion and tuning the hyper parameters of ResNet 50 models to achieve 94.57% test accuracy on CIFAR-10 Dataset. Link to paper
| network | error % |
|---|---|
| resnet-50 | 6.97 |
| resnet-110 | 6.61 |
| resnet-164 | 5.93 |
| resnet-1001 | 7.61 |
| This method | 5.43 |
Overview
- Change the wandb api key to valid api key.
- Python 3.8 and pytorch 1.9 (works on older versions as well)
- main.py is to train model
- sweep.py and sweep_config.py are for hyperparameter optimization for experiment tracking wandb is used please change api key
- pred.py is to run the trained model on the custom data. (Appropriately provide model paths)
Important
If you want to run