Add regression layer to caffe

Question

I have implemented a smile detection system based on deep learning. The bottom layer is the output of the system and has 10 output according to the amount of the person's smile.
I want to convert these ten output with a numeric output in the range of 1 to 10 with a regression layer.
How can I do this in caffe?
Thanks

score 2 · Answer 1 · answered Sep 17 '15 at 06:37

2

In order to convert the 10 outputs you have to a single one you need an "InnerProduct" layer with 10 inputs and a single output. To train this layer you also need to add a loss layer suitable for regression on top of the 10 output layer you already have.
Such loss layers can be, e.g., Euclidean loss layer or Ross Girshick's smooth L1 loss layer.

answered Sep 17 '15 at 06:37

Shai

111,146
38
238
371

Can you elaborate on `smooth L1 loss layer` where it usually used? – mrgloom Nov 25 '15 at 16:31
@mrgloom you can read more about it in Girshick's [fast RCNN](http://arxiv.org/abs/1504.08083) paper. – Shai Nov 25 '15 at 16:35

Add regression layer to caffe

1 Answers1