AdaptLLM/remote-sensing-VQA-benchmark
收藏Hugging Face2025-03-28 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/AdaptLLM/remote-sensing-VQA-benchmark
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含用于评估多模态大型语言模型（MLLMs）的遥感视觉指令任务。数据集分为CLRS、UC_Merced、FloodNet和NWPU-Captions等不同名称，每个名称下都有用于测试的具体数据文件。README文件提供了如何下载和使用数据集、在基准测试上评估MLLMs以及运行推理的环境设置的详细说明。
The dataset contains remote sensing visual instruction tasks for evaluating Multimodal Large Language Models (MLLMs). It is categorized under different names such as CLRS, UC_Merced, FloodNet, and NWPU-Captions, each with specific data files for testing. The README file provides detailed instructions on how to download and use the datasets, evaluate MLLMs on the benchmarks, and setup the environment for running the inference.
提供机构：
AdaptLLM
