/

/

google-research

Обзор Центр заботыВойти

google-research

Ветки: 311 Коммиты: 4490 Теги: 0

..

google-research

/

concept_explanations

Initial commit for "On Concept-Based Explanations in Deep Neural Networks".

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

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

requirements.txt

Initial commit for "On Concept-Based Explanations in Deep Neural Networks".

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

toy_baseline.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

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

This is the code for the paper "On Concept-Based Explanations in Deep Neural Networks" https://arxiv.org/abs/1910.07969".

Please download all data from "gs://concept_discovery/data/" or "https://console.cloud.google.com/storage/browser/concept_discovery", and change the directory paths when loading data.
To run the toy example, just run python3 toy_main.py.
To create the toy example, just run python3 create_toy.py.
To run the AwA example, just run python3 awa_main.py.

ipca.py is a general helper function for calculating the completeness of a given model, and toy_helper.py and awa_helper.py contain helper functions that are specific to the datasets.

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.