In V1.1 train_val.prototxt, why are the TRAIN & TEST phase (in loss and accuracy layers) commented out?

[aurotripathy]

Here's the snippet from the train_val.prototxt file for SqueezeNet V1.1. Thank you.

layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "pool10"
  bottom: "label"
  top: "loss"
  #include {
  #  phase: TRAIN
  #}
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "pool10"
  bottom: "label"
  top: "accuracy"
  #include {
  #  phase: TEST
  #}
}
layer {
  name: "accuracy_top5"
  type: "Accuracy"
  bottom: "pool10"
  bottom: "label"
  top: "accuracy_top5"
  #include {
  #  phase: TEST
  #}
  accuracy_param {
    top_k: 5
  }
}

[forresti]

In some of the Caffe examples, phase:TRAIN and phase:TEST are used to only print the accuracy during the Test phase. We found it to be useful to see the accuracy and loss on both the Train and Test sets, so we commented out Phase for these experiments≥