{# Copyright (c) 2015, NVIDIA CORPORATION. All rights reserved. #}
You should enter a train_val network here. Some cleanup is done for you automatically:
data_param.source
blank, it will be filled in for you with the appropriate pathThe deploy network will be created for you automatically. Once caffe implements their "all-in-one" nets feature, you will be able to specify which layers to include in the deploy file. Until then, these things are done automatically:
train_
are not included in the deploy filedeploy_
are only included in the deploy file