标签目录
合照
各模型训练数据截止时该标签已有的作品数——用于估计模型对该标签的掌握程度,与我们是否有配图无关。
An image consisting of at least three characters. All characters should be taking up about the equivalent amount of space in the image so that everyone is in focus, rather than being focused on one character with the others in the background or off to the side.
4 个模型中有 3 个