How to do multitask learning using Caffe?

Question

I wonder how to do multitask learning using Caffe. Should I simply use the output layer SigmoidCrossEntropyLoss or EuclideanLoss, and define more than one outputs?

E.g. is the following architecture valid (3 outputs, i.e. 3 tasks concurrently learnt)?

enter image description here

Corresponding prototxt file:

name: "IrisNet"
layer {
  name: "iris"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  hdf5_data_param {
    source: "iris_train_data.txt"
    batch_size: 1

  }
}

layer {
  name: "iris"
  type: "HDF5Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  hdf5_data_param {
    source: "iris_test_data.txt"
    batch_size: 1

  }
}

layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "data"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 50
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}


layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}




layer {
  name: "loss"
  type: "SigmoidCrossEntropyLoss" 
  # type: "EuclideanLoss" 
  # type: "HingeLoss"  
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}

score 1 · Answer 1 · answered Mar 03 '16 at 23:39

Every Blob in caffe can be assigned a nonzero loss weight.

And you can have an arbitrary number of outputs.

This means you can just learn n different networks on the same data with different targets and assign every loss function it's own weight. Caffe takes care of adding up all the loss.

How to do multitask learning using Caffe?

1 Answers1