How to use it with multiple regression outputs.

[gautamMalu]

Hi,
I am using it for a multi-task model.
I am using a customized alexnet for a multi-task model for aesthetics prediction and classification. I have a normalized score ( 0 to 1 ) for aesthetics prediction and a single label for classification. I want to check which areas are more salient for aesthetics. After doing
net.forward()
I am setting
net.blobs['aesthetics'].data[0][0] = 1
Then I am running
bw = net.backward()
But I am getting only zero values as input image.
I have set
force_backward: true in my model prototxt file.
I think I am messing up the backward function, let me know if you have any idea about how to use it for regression problems.

[artvandelay]

If you train your model without doing the forward and backward by hand, does that still give you zeros?