0

我正在使用 Create ML 创建一个模型。我添加了 2 个对象的 1000 张图片。500只猫,500只狗。该模型工作得很好,但是当我有一个瀑布成像器时,它与狗/猫无关,例如它返回 100% 狗。任何想法如何处理这个问题?

1)我读到一些图像分类器让你提供一个否定类:意思是与你正在寻找的图像不相关的图像。知道如何使用 Create ML 或其他工具来做到这一点吗?

2)通过添加我的图像来重新训练现有模型而不是制作我的模型更好吗?Create ML 有可能吗?从我读到的你不能。有什么建议吗?

由于我是 Core ML 的新手,如果您有任何方向可以指出,我们将不胜感激。

谢谢

4

1 回答 1

2

If your classifier is only trained on two types of images such as cats and dogs, then you should only use it on pictures of cats and dogs. If you use it on any other picture, it will still predict cat or dog.

If you want to make a classifier for cat / dog / anything else, then you need to add a third category with pictures of things that are not cats or dogs.

Usually this category will have many more pictures in it than the other two categories (since there are lots of things that are not cats or dogs), causing a class imbalance. I'm not sure if Create ML can compensate for that imbalance.

于 2018-09-04T09:14:32.470 回答