How To Predict Float Vector Labels With Caffe?

I was wondering if it's possible to predict a 1-by-n feature associated to an input image using caffe. In this post there is a solution to make caffe predict a binary vector such a

Solution 1:

You can also think about this MultiTaskData Layer. It can parse float typed label vector as you mentioned in your question.

Solution 2:

Yes; I believe that if you simply follow the instructions in the post you referenced, but use float labels in place of the binary ones, that you'll get useful results. Caffe is happy to support you. :-)