deep learning - How to compute test/validation loss in pycaffe -

i trying compute test loss in own training loop in python. calling solver.test_nets[0].forward() seems update score blob not loss one. idea how updated?

i using following solver config:

net: "/tmp/tmp8ikb9sg2/train.prototxt" test_net: "/tmp/tmp8ikb9sg2/test.prototxt" test_iter: 1 test_interval: 2147483647 base_lr: 0.1 lr_policy: "fixed" test_initialization: false 

and train , test.prototxt same except phase definition @ top of file:

name: "pycaffenet" state {   phase: train  # set test in test.prototxt } ... layer {   name: "loss"   type: "softmaxwithloss"   bottom: "score"   bottom: "output"   top: "loss" } 

it different issue thought. loss blob being updated remained same because weights of solver.test_nets[0] not changing. looks not automatically shared solver.net. can done calling:

solver.test_nets[0].share_with(solver.net)