The State of Machine Learning Frameworks
thegradient.pub
The State of Machine Learning Frameworks
1–10 of 201 posts
Re: The State of Machine Learning Frameworks
#2Why?
Re: The State of Machine Learning Frameworks
#3Why?
research: the API.
industry: tensorRT.
Re: The State of Machine Learning Frameworks
#4And Amazon is still trying to desperately get people to adopt MXNet.
Re: The State of Machine Learning Frameworks
#5Why?
Well, you could read the article :^)
As a summary, though:
PyTorch has become dominant in research because of its API (both its stability + having eager mode).
TF has become dominant in industry because A. it came out several years before PyTorch and industry is slow to move, B. It supported a lot of production use cases (mobile, serving, removing Python overhead) that PyTorch didn't for a long time.
Re: The State of Machine Learning Frameworks
#6Why?
Well, you could read the article :^) As a summary, though: PyTorch has become dominant in research because of its API (both its stability + having eager mode). TF has become dominant in industry because A. it came out several years before PyTorch and industry is slow to move, B. It supported a lot of production use cases (mobile, serving, removing Python overhead) that PyTorch didn't for a long time.
well, for one pytorch added the python overhead over an otherwise very clean lua jit
Re: The State of Machine Learning Frameworks
#7Anyone has any opinions on TF2.0? They've released it recently, and it seems like it should be much closer to PyTorch now, but I don't know enough to evaluate it properly.
Re: The State of Machine Learning Frameworks
#8If I were to start a theoretical computer vision company today, which would I be better off using?
Re: The State of Machine Learning Frameworks
#9I think tensorflow dominates industry purely because of its capability of exporting the model into a coreml Android model or easy of moving it to production in a GCP environment or in whatever form. Pytorch might have to build a good production pipeline around it to catch up in this game.
With fastai module that's built on Pytorch learning and developing Deep Learning solutions have become a lot easier. So there's a real game on now
Re: The State of Machine Learning Frameworks
#10If I were to start a theoretical computer vision company today, which would I be better off using?
do you plan on having a research team?