how to add val process in train process

[zhonhel]

Hi,

I used DeepLabv2 VGG16 model.
I add data layer and accuracy layer for val in a certain-parameter train.prototxt which I have modified previously, then I try to train by caffe command, but I got this issue:

F0525 11:24:22.370501 3794 solver.cpp:126] Check failed: param_.test_iter_size() == num_test_nets (1 vs. 0) test_iter must be specified for each test network.

Can you tell me how to add val process in train process when use DeepLab ?