cntk - 我可以将样本权重添加到训练数据集中吗？

Question

是否可以添加到配置（例如，SGD 块）样本权重？每个训练示例在哪里分配一个权重？

在许多情况下，一个简单的 1/N（其中 N 是训练数据集中的样本总数）就足够了，但在其他情况下，我希望网络在某些示例中添加额外的“重点”。这可以在 CNTK 中完成吗？

谢谢，

佩德罗

Answer 1

Yes, it can be done. If your task is binary classification you can use WeightedLogistic (label, probability, weight).

Typically weight will be an Input() which you can hook up to a stream in your data (assuming you are using CNTKTextFormatReader you can just have a |weight stream).

It can also be done for tasks other than binary classification with a little more effort.