/

/

google-research

Обзор Центр заботыВойти

google-research

Ветки: 311 Коммиты: 4490 Теги: 0

..

google-research

/

milking_cowmask

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Generate_ImageNet_split_shards.ipynb

5 лет назад

Add project 'Milking CowMask for semi-supervised classification'

5 лет назад

main_semisup.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

requirements.txt

Add project 'Milking CowMask for semi-supervised classification'

5 лет назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

train_semisup.py

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

Open-sourcing the code for "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor". https://arxiv.org/abs/2312.07661

9 месяцев назад

README.md

Milking CowMask for semi-supervised image classification

Intern project by Geoff French, hosted by Avital Oliver and Tim Salimans

This project explores the use of CowMask for semi-supervised image classification. It achieves competitive results on CIFAR-10 using a 26 layer Wide ResNet with Shake-shake regularization. It also achieves competitive results on ImageNet.

To train a network on CIFAR-10 using 1,000 supervised samples:

python main_semisup.py

The default values for the command line arguments should replicate a single result from our upcoming paper.

Использование cookies

Мы используем файлы cookie в соответствии с Политикой конфиденциальности и Политикой использования cookies.

Нажимая кнопку «Принимаю», Вы даете АО «СберТех» согласие на обработку Ваших персональных данных в целях совершенствования нашего веб-сайта и Сервиса GitVerse, а также повышения удобства их использования.

Запретить использование cookies Вы можете самостоятельно в настройках Вашего браузера.