[mastazi]

> given the migration of the Torch community from Lua to Python via PyTorch, and subsequent waning support for Lua Torch, Cortex began evaluating alternatives to Lua Torch

I'm a bit out of the loop, has PyTorch really become so much more popular than Lua Torch, in the short time span since it launched? And is it true that most of the original Lua Torch community switched to PyTorch?

[Eridrus]

PyTorch is rivaling TensorFlow in popularity now. Lua Torch is basically dead.

[mastazi]

Thanks, I saw many articles about PyTorch lately, but didn't realise that most people had switched for good.

[mlthoughts2018]

PyTorch is catching up to TensorFlow, but still has a far way to go especially compared with the user experience of Keras with TensorFlow.

In PyTorch you have to do quite a bit more work specifying gradients, zeroing the gradients between update steps, specifically describing the operations of the backward pass in a custom layer, even in cases when it could just be inferred by the computation graph library as in TensorFlow.

I’ve heard anecdata that PyTorch performance can be better, but I think it’s still a case-by-case topic, and both libraries are still changing rapidly.

I attribute the switch from Lua Torch to PyTorch as just an obvious effect based on how bad of a language Lua is for the type of interactive and experimental programming needed for this type of work. Lua is a good language for some applications, but not this — and the value of spending effort to build the primary Torch frontend in Python became obvious quickly.