When comparing Pytorch vs Torch, the Slant community recommends Torch for most people. In the question“What are the best artificial intelligence frameworks?” Torch is ranked 7th while Pytorch is ranked 9th. The most important reason people chose Torch is:
It takes little more than a type cast of your inputs to go from CPU to GPU computation.
Ranked in these QuestionsQuestion Ranking
Pros
Pro Easy to install
Pro It has a rich ecosystem
Pro Supports both CPU and GPU
Even CPU Performance is good compared to other frameworks.
Pro Interops excellent with Python
Pro Easy to debug
Pro It is easy to write extension packages
Pro Easy switch between CPU and GPU
It takes little more than a type cast of your inputs to go from CPU to GPU computation.
Pro Lots of easy to combine modular pieces
Torch is a very modular framework. As such, you can choose which modules you need to implement and which modules to eliminate from your solution.
Cons
Con Not easily accessible to the academic community
Being written in Lua instead of the more widely used Python, it's not as accessible to academics as other solutions which are implemented in Python. With Python being one of the most widely used languages in scientific computing.