tsch00001/vlmsareblind_2160
收藏官方服务:
资源简介:
这是一个包含图像和文本的数据集,用于某种特定的任务。数据集由训练集组成,每个样本包括一个图像、一个提示文本、一个真实标签和元数据。训练集共有2160个样本。
This is a dataset consisting of images and text, designed for a specific task. The dataset comprises a training set with each sample including an image, a prompt text, a ground truth label, and metadata. The training set contains a total of 2160 samples.
提供机构:
tsch00001


