Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
王一凡 9b72dabc6a | 1 year ago | |
---|---|---|
.. | ||
classification | 1 year ago | |
clip | 1 year ago | |
clip_finetune_imagenet | 1 year ago | |
detection | 1 year ago | |
distillation | 1 year ago | |
segmentation | 1 year ago | |
README-classification.md | 1 year ago | |
README-clip.md | 1 year ago | |
README-distillation.md | 1 year ago | |
README-object-detection.md | 1 year ago | |
README-segmentation.md | 1 year ago | |
README.md | 1 year ago |
RangeAugment is an automatic augmentation method that allows us to learn model- and task-specific
magnitude range of each augmentation operation.
We provide training and evaluation code along with pretrained models and configuration files for the following tasks:
Note: In the codebase, we refer RangeAugment as Neural Augmentor (or NA).
If you find our work useful, please cite:
@article{mehta2022rangeaugment,
title={RangeAugment: Efficient Online Augmentation with Range Learning},
author = {Mehta, Sachin and Naderiparizi, Saeid and Faghri, Fartash and Horton, Maxwell and Chen, Lailin and Farhadi, Ali and Tuzel, Oncel and Rastegari, Mohammad},
journal={arXiv preprint arXiv:2212.10553},
year={2022},
url={https://arxiv.org/abs/2212.10553},
}
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》