torch7

https://en.wikipedia.org/wiki/Torch_(machine_learning) http://torch.ch/ https://github.com/torch/torch7

Yes, kind of, but it depends on NumPy which is fairly big if your goal is for students to grasp and demystify the whole way down to the hardware. Other candidates would be torch7 [1], but it is somewhat married to the Lua API which drives it. [1]: https://github.com/torch/torch7

With https://github.com/torch/torch7 on https://luajit.org/luajit.html maybe?

In those days there was a lovely LuaJIT based tensor manipulation language torch7 [1,2] developed by Leon Bottou. It later became basis for PyTorch. I still believe that Lua in general and LuaJIT in particular are much superior to Python for Deep Learning. [1] http://torch.ch/ [2] https://github.com/torch/torch7

Lua torch has been dead for a while https://github.com/torch/torch7. pytorch doesn't use any Lua.

> Wrt to repl: the torch7 repl is quite serviceable, so it's worth giving it a try Sounds great, but: $ luarocks install trepl Error: No results matching query were found. Also the torch7 repo[1] mentions: > Torch is not in active developement Is there a maintained torch7 repl somewhere? [1] https://github.com/torch/torch7

This could be interesting to integrate support for racket to allow it to interact with Torch. You would just create a small language to compile to lua and then have that run in Torch. https://github.com/torch/torch7 http://racket-lang.org

You're right about Caffe2 [1], but Torch and PyTorch have existed for a long time and don't seem infected [2] and [3]. For completeness, both TensorFlow [4] and MXNET [5] are Apache 2. [1] https://github.com/caffe2/caffe2/blob/master/PATENTS [2] https://github.com/torch/torch7/blob/master/COPYRIGHT.txt [3] https://github.com/pytorch/pytorch/blob/master/LICENSE [4] https://github.com/tensorflow/tensorflow/blob/master/LICENSE [5] https://github.com/dmlc/mxnet/blob/master/LICENSE

it's the same license file as https://github.com/torch/torch7 and http://torch.ch The C libraries are shared among the Lua and Python variants

There's a thread at https://github.com/torch/torch7/pull/287 of people who have managed to install on Windows, and a wiki page at https://github.com/torch/torch7/wiki/Windows , which is looking pretty comprehensive :-)

I'm sorry if this is only tangentially on topic: I was reading the article and got to the part related to installing CUDA drivers. I am currently on the market for a laptop which will be used for self-learning purposes and I am interested in trying GPU-based ML solutions. In my search for the most cost-effective machine, some of the laptops that I came across are equipped with AMD GPUs and it seems that support for them is not as good as for their Nvidia counterparts: so far I know of Theano and Caffe supporting OpenCL and I know support might come in the future from TensorFlow [1], in addition I saw that there are solutions for Torch [2] although they seem to be developed by single individuals. I was wondering if someone with experience in ML could give me some advice: is the AMD route viable? [1] https://github.com/tensorflow/tensorflo

You could try Torch libraries. There are a few examples on how to (almost) replicate some of Google's neural network models on Imagenet. Check https://github.com/torch/torch7/wiki/Cheatsheet#demos.

Sure, the best way to get attention is to open an issue on github.com/torch/torch7 (that way you get the attention of all the core developers). If you'd like to ask something more discrete, I'd suggest you email one of the four here: https://github.com/orgs/torch/members

I am one of the maintainers. From information first-hand, Torch is used by: - Facebook - Google DeepMind and slowly Google Brain is moving as well. - Certain people at IBM - NYU - IDIAP - LISA LAB (not exclusively, but some students started using it) - Purdue e-lab - Several smaller companies (10-100 companies) There will definitely be several commonly asked questions, and this is my personal perspective on them. Why torch/lua, why not python+?* No reason. Just because. Mostly because LuaJIT is awesome (with it's quirks) and LuaJIT is extremely portable. (we embed torch routinely in tiny devices, afaik not practically possible with python). Is Torch better than Theano/etc.etc.? Better and worse. Every framework has it’s oddities. I like the super-simple design and the compactness of traversing from high-level easy-to-use API to bare-metal