Тёмный

YOLO-WORLD: Custom Object Detection Without Retraining 

The Next Phase
Подписаться 884
Просмотров 1,9 тыс.
50% 1

Опубликовано:

 

5 окт 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 8   
@rickyS-D76
@rickyS-D76 3 месяца назад
Nice, can you please make a video on detecting objects from a video using yolo world with boudiing box and confidence score. Thanks
@nitishreddynandyala2609
@nitishreddynandyala2609 6 месяцев назад
very useful, thank you
@fintech1378
@fintech1378 7 месяцев назад
is it vision language model like CLIP?
@next_phase
@next_phase 7 месяцев назад
yes, it is similar to that. But this also provides bounding boxes.
@informative7410
@informative7410 7 месяцев назад
How to convert it into tflite ??
@next_phase
@next_phase 6 месяцев назад
I could not figure out a way to do that. I tried to do it using ultralytics but did not work out. You can check my code here: colab.research.google.com/drive/1cxqMiSuNPSwy4z8nhgxIVK8YQxINbak_?usp=sharing
@lxt-j1q
@lxt-j1q 5 месяцев назад
The accuracy of yolo-world is too low.
@next_phase
@next_phase 5 месяцев назад
I agree. However, don’t forget that this is the first version of YOLO with such ability. The next versions will be better.
Далее
Yolo-World. Is it good for real production?
4:42
Просмотров 1,7 тыс.
Has Generative AI Already Peaked? - Computerphile
12:48
Women’s Free Kicks + Men’s 😳🚀
00:20
Просмотров 6 млн
How AI 'Understands' Images (CLIP) - Computerphile
18:05