cifar10 train_quick

Iteration 900, loss = 0.97627
I0512 10:31:00.577219  3503 solver.cpp:259]     Train net output #0: loss = 0.97627 (* 1 = 0.97627 loss)
I0512 10:31:00.577229  3503 sgd_solver.cpp:138] Iteration 900, lr = 0.001
I0512 10:31:01.580283  3503 solver.cpp:358] Iteration 1000, Testing net (#0)
I0512 10:31:01.939452  3503 solver.cpp:425]     Test net output #0: accuracy = 0.6285
I0512 10:31:01.939481  3503 solver.cpp:425]     Test net output #1: loss = 1.0814 (* 1 = 1.0814 loss)
I0512 10:31:01.943264  3503 solver.cpp:243] Iteration 1000, loss = 0.961738
I0512 10:31:01.943294  3503 solver.cpp:259]     Train net output #0: loss = 0.961738 (* 1 = 0.961738 loss)
I0512 10:31:01.943301  3503 sgd_solver.cpp:138] Iteration 1000, lr = 0.001
 

 

 

 

 Iteration 4900, loss = 0.4016
I0512 10:31:46.033463  3533 solver.cpp:259]     Train net output #0: loss = 0.4016 (* 1 = 0.4016 loss)
I0512 10:31:46.033473  3533 sgd_solver.cpp:138] Iteration 4900, lr = 0.0001
I0512 10:31:47.042505  3533 solver.cpp:606] Snapshotting to HDF5 file examples/cifar10/cifar10_quick_iter_5000.caffemodel.h5
I0512 10:31:47.050315  3533 sgd_solver.cpp:317] Snapshotting solver state to HDF5 file examples/cifar10/cifar10_quick_iter_5000.solverstate.h5
I0512 10:31:47.055429  3533 solver.cpp:332] Iteration 5000, loss = 0.539803
I0512 10:31:47.055459  3533 solver.cpp:358] Iteration 5000, Testing net (#0)
I0512 10:31:47.408751  3533 solver.cpp:425]     Test net output #0: accuracy = 0.7491
I0512 10:31:47.408798  3533 solver.cpp:425]     Test net output #1: loss = 0.753487 (* 1 = 0.753487 loss)
I0512 10:31:47.408812  3533 solver.cpp:337] Optimization Done.
I0512 10:31:47.408820  3533 caffe.cpp:254] Optimization Done