{# Copyright (c) 2015-2016, NVIDIA CORPORATION. All rights reserved. #}

Specifying a custom Caffe network

You should enter a train_val network here. Some cleanup is done for you automatically:

The 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:

Specifying a custom Torch network

You should enter a Torch network description. Refer to the documentation for more information.