OpenGVLab/all-seeing
[ICLR 2024] This is the official implementation of the paper "The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World"
Python
Issues
- 3
About 100k of answers of sam data is `"what is the difference between a man and a woman?"'
#18 opened by janghyuncho - 1
llava module not found
#15 opened by daniekpo - 1
- 1
- 1
[Question]Can all-seeing-v2 handle images which the target does not exist for the grounding task?
#11 opened by HeliumCake - 2
when will CRPE benchmark be released?
#4 opened by Moonteresa - 1
- 1
ZeroDivisionError and ModelProto error
#20 opened by anjugopinath - 1
- 1
- 9
- 3
- 1
Usage of dataset Browser is quite tricky and often encountered with obvious mistake.
#2 opened by Yindong-Zhang - 3
v2中box的坐标是怎么normalized的?
#6 opened by Baboom-l - 1
Issue on bounding box coordinates
#10 opened by tibetgao - 3
Special tokens
#9 opened by KooSung - 0
AS-V2中坐标问题
#7 opened by fang-h