How to perform object detection?
#9
by
Godsing
- opened
The Model card mentions:
Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
I can't find any usage examples. And when I try to write prompts by myself, it fails to obtain the expected result..
So, is there an usage example?
I think I have found it: https://github.com/QwenLM/Qwen2.5-VL/blob/main/cookbooks/spatial_understanding.ipynb
Godsing
changed discussion status to
closed