search

OpenBMB / MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Apache License 2.0
12.38k stars 869 forks source link

Highlighting detected features in an Image with a boundary box #641

Open SrikanthChellappa opened 1 week ago

SrikanthChellappa commented 1 week ago

Team, can you pls let me know if there is a way to draw boundary boxes on the detected features/objects from an image ? I am trying with Llama 2.5 version? Or does the model return any of the features with any of its coordinates ?

LDLINGLINGLING commented 1 week ago

hello，I have trained this model for OCR and grounding tasks, maybe it will help you, the tutorial is below：https://modelbest.feishu.cn/wiki/HLRiwNgKEic6cckGyGucFvxQnJw?from=from_copylink

SrikanthChellappa commented 1 week ago

Thanks @LDLINGLINGLING for the link. I saw this link before this post but couldn't understand the context as it was in Chinese and with translation I was losing the complete context. can you pls assist with some quick notes in English as that would help me further here.