Closed XiruiTeng closed 3 weeks ago
Thank you for your feedback. The code for image-text retrieval is located in the retrieval folder, and the code for referring expression comprehension is in the grounding folder. Currently, the code only supports single-GPU execution; it will take some time to enable multi-GPU support.
Thanks for you reply! I also find you are the author of the paper Calibrating Prompt from History for Continual Vision-Language Retrieval and Grounding. When will you release the code of this paper?
Thank you for your feedback. The code for image-text retrieval is located in the retrieval folder, and the code for referring expression comprehension is in the grounding folder. Currently, the code only supports single-GPU execution; it will take some time to enable multi-GPU support.