Awesome

AIM

Official PyTorch implementation for AIM: an Auto-Augmenter for Images and Meshes. The code has been implemented and tested on the Ubuntu operating system only.

Install CUDA Toolkit and cuDNN

Install the CUDA Toolkit and the cuDNN library matching the version of your Ubuntu operating system. Installation of the Anaconda Python Distribution is required as well. We recommend installing CUDA10.2.

Download the data set

CUB200 dataset </br> The datasets should be place in datasets/CUB_200_2011 </br> Training data should be in datasets/CUB_200_2011/train/<categories> </br> Test set should be in datasets/CUB_200_2011/test/<categories> </br>

Train

python train.py

Test

python test.py

Citation

If you found this work helpful for your research, please consider citing us.

@inproceedings{singh2022aim,
  title={AIM: An Auto-Augmenter for Images and Meshes},
  author={Singh, Vinit Veerendraveer and Kambhamettu, Chandra},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={722--731},
  year={2022}
}