Caffe Iteration loss versus Train Net loss

问题:

I'm using caffe to train a CNN with a Euclidean loss layer at the bottom, and my solver.prototxt file configured to display every 100 iterations. I see something like this,

Iteration 4400, loss = 0
I0805 11:10:16.976716 1936085760 solver.cpp:229]     Train net output #0: loss = 2.92436 (* 1 = 2.92436 loss)

I'm confused as to what the difference between the Iteration loss and Train net loss is. Usually the iteration loss is very small (around 0) and the Train net output loss is a bit larger. Can somebody please clarify?

回答1:

Evan Shelhamer already gave his answer on https://groups.google.com/forum/#!topic/caffe-users/WEhQ92s9Vus.

As he pointe out, The net output #k result is the output of the net for that particular iteration / batch while the Iteration T, loss = X output is smoothed across iterations according to the average_loss field.