News for hackers. Stuff that matters.

A comment on Fast.ai and why Python is not the future of ML with Jeremy Howard. Parent comment

Re:Fast.ai and why Python is not the future of ML with Jerem... by fxtentacle on Tuesday September 08, 2020 @03:53AM (#24406136)
My advice would be to use TensorFlow because it works flawlessly on Google Colab and in Jupyter notebooks.

The latter two are tools to send ML models and training pipelines around, so kind of like Google Docs for AI. Colab is on the internet, Jupyter on your PC.

That way, you can easily exchange your experiments with others and/or asks for help online.

[ Parent | on HN ]
Re:Fast.ai and why Python is not the future of ML with Jerem... by dunefox on Tuesday September 08, 2020 @05:46AM (#24406802)
Tensorflow is much worse than PyTorch, IMO. I wouldn't recommend it to a beginner in any case.
[ Parent | on HN ]
Re:Fast.ai and why Python is not the future of ML with Jerem... by 0-_-0 on Tuesday September 08, 2020 @07:14AM (#24407267)
What are the main differences that make pytorch better?
[ Parent | on HN ]
Re:Fast.ai and why Python is not the future of ML with Jerem... by mark_l_watson on Tuesday September 08, 2020 @09:48PM (#24415874)
You might want to recommend the Keras APIs for TensorFlow for people learning DL. The fastai and PyTorch libraries are also good when learning.
[ Parent | on HN ]