https://github.com/DensoITLab/TeachAugment

Official Implementation of TeachAugment: Data Augmentation Optimization Using Teacher Knowledge (CVPR2022, Oral)
https://github.com/DensoITLab/TeachAugment

classification cvpr2022 deeplearning pytorch

Last synced: 4 months ago
JSON representation

Official Implementation of TeachAugment: Data Augmentation Optimization Using Teacher Knowledge (CVPR2022, Oral)

• Host: GitHub
• URL: https://github.com/DensoITLab/TeachAugment
• Owner: DensoITLab
• License: other
• Created: 2021-11-17T07:26:12.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-06-06T07:32:19.000Z (about 2 years ago)
• Last Synced: 2024-01-16T05:31:26.393Z (5 months ago)
• Topics: classification, cvpr2022, deeplearning, pytorch
• Language: Python
• Homepage:
• Size: 29.3 KB
• Stars: 62
• Watchers: 5
• Forks: 12
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• Awesome-Autonomous-Driving - AlignMixup

README

        
# TeachAugment: Data Augmentation Optimization Using Teacher Knowledge (CVPR2022, Oral)

Official Implementation of TeachAugment in PyTorch.  

arXiv: https://arxiv.org/abs/2202.12513

## Requirements

- PyTorch >= 1.9

- Torchvision >= 0.10

## Run

Training with single GPU

```

python main.py --yaml ./config/$DATASET_NAME/$MODEL

```

Training with single node multi-GPU

```

python -m torch.distributed.launch --nproc_per_node=$N_GPUS main.py \

    --yaml ./config/$DATASET_NAME/$MODEL --dist

```

Examples

```

# Training WRN-28-10 on CIFAR-100

python main.py --yaml ./config/CIFAR100/wrn-28-10.yaml

# Training ResNet-50 on ImageNet with 4 GPUs

python -m torch.distributed.launch --nproc_per_node=4 main.py \

    --yaml ./config/ImageNet/resnet50.yaml --dist

```

If the computational resources are limited, please try `--save_memory` option.

## Citation

If you find our project useful in your research, please cite it as follows:

```

@InProceedings{Suzuki_2022_CVPR,

    author    = {Suzuki, Teppei},

    title     = {TeachAugment: Data Augmentation Optimization Using Teacher Knowledge},

    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

    month     = {June},

    year      = {2022},

    pages     = {10904-10914}

}

```

## Acknowledgement

The files in ```./lib/models``` and the code in ```./lib/augmentation/imagenet_augmentation.py``` are based on the implementation of [Fast AutoAugment](https://github.com/kakaobrain/fast-autoaugment).