conv-neural-network - 每个类(class)中应有多少张(最少)图像用于训练YOLO？

Question

我正在尝试在自定义数据集上实现YOLOv2。每个类(class)都需要最少数量的图像吗？

Answer 1

每个类(class)没有用于培训的最低图像。当然，您所拥有的数字越小，模型收敛速度越慢，精度也会降低。
根据Alexey的说法(重要的 fork 暗网和YOLO v4的创建者)，重要的是如何改善对象检测:

For each object which you want to detect - there must be at least 1 similar object in the Training dataset with about the same: shape, side of object, relative size, angle of rotation, tilt, illumination. So desirable that your training dataset include images with objects at diffrent: scales, rotations, lightings, from different sides, on different backgrounds - you should preferably have 2000 different images for each class or more, and you should train 2000*classes iterations or more

https://github.com/AlexeyAB/darknet
因此，我想如果要获得最佳精度，则每个类(class)至少应有2000张图像。但是每堂课也不错1000。即使每个类别有数百张图像，您仍然可以获得不错的(不是最佳的)结果。只要收集尽可能多的图像即可。