Process for saving weights to file

[nmante]

How were the weights saved to disk? Were they extracted from Torch using getParameters then saved as a torch object using torch.save? I'm interested because I've trained my own smaller network and would like to load the weights from torch/lua training in C++.

[chrisranderson]

Maybe this will be helpful: https://github.com/jhjin/overfeat-torch

[nmante]

That's a nice option. For my purposes, I needed to load my own custom network (with it's own weights and structure). I ended up using https://github.com/mvitez/thnets to do this. It's a standalone library that let's you load, save and use custom networks directly in C++. I tweaked a bit to run on my machine (OS X). It worked for me, maybe it'll work for anyone else who sees this.