search

WentaoTan / MLLM4Text-ReID

Code for Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID (CVPR 2024)
28 stars 0 forks source link

code to use Shikra for image captioning #8

Closed Zoesxw closed 1 month ago

Zoesxw commented 1 month ago

Thank you for your excellent work! You provide the code to use Qwen for image captioning, can you provide the code for Shikra?

WentaoTan commented 1 month ago

The code for generating captions using Shikra is much more complex compared to Qwen. According to Shikra's GitHub repository, we first need to deploy it as a local server, and then use a local client to call the server's API. Please refer to the Server-Client Demo at https://github.com/shikras/shikra for more details.

Zoesxw commented 1 month ago

Thank you for your reply