如何使用 tensorflow 进行多标签分类以进行自动标记?

How to perform a multi label classification with tensorflow in purpose of auto tagging?

我是tensorflow的新手,想知道是否有任何具有多个网络输出的多标签分类的教程或示例。

我问这个是因为我有一个文章集,其中每篇文章可以有多个标签。

开箱即用,tensorflow 通过 tf.nn.sigmoid_cross_entropy_with_logits loss function or the like (see the complete list in ). If your tags are binary, in other words there's a predefined set of possible tags and each one can either be present or not, you can safely go with that. A single model to classify all labels at once. There are a lot of examples of such networks, e.g. one from .

支持 binary multi-label 分类

很遗憾,tensorflow 不支持 multi-nomial multi-label 分类。如果是这种情况,则必须为每个标签构建一个单独的分类器,每个标签都使用 tf.nn.softmax_cross_entropy_with_logits 或类似的分类器。