how can i get det location

xinyu1205 / recognize-anything

Open-source and strong foundation image recognition models.

https://recognize-anything.github.io/

Apache License 2.0

2.88k stars 276 forks source link

how can i get det location #42

Open feifaxiaoming opened 1 year ago

feifaxiaoming commented 1 year ago

我在使用inference_ram.py 进行识别的时候，我如何在获取到标签的同时，能把标签对应的位置信息获取到呢。

xinyu1205 commented 1 year ago

Please refer to RAM/Tag2Text with Grounded-SAM. RAM/Tag2Text provides image tags, while Grounded-SAM generates corresponding bounding boxes and masks.

feifaxiaoming commented 1 year ago

您这个就是单独用于识别的是吧，但是您这个识别之前，也需要检测啊，检测的位置信息，不在这个代码中体现吗？

xinyu1205 commented 1 year ago

识别前不需要检测，直接对一张图像输出标签

feifaxiaoming commented 1 year ago

还是有点没懂，识别前不需要检测，那检测完，怎么把标签挂到对应的位置上呢

xinyu1205 commented 1 year ago

通过grounding dino来根据tag生成bounding box

feifaxiaoming commented 1 year ago

明白了，谢谢