alven

Results 2 issues of alven

my gpu is Tesla P40, 24GBmemory when i run train_net.py on single gpu, it's about **39** samples/sec, and it seems not much faster on 4-gpu with train_nets_mgpu_new.py(still around 40). and...

add evaluate.py according to val.ipynb. then make some changes on gpu/cpu switch, mat file reading and ground truth extracting.