News for hackers. Stuff that matters.

A comment on Introduction to Recurrent Neural Networks in Pytorch. Parent comment

Re:Introduction to Recurrent Neural Networks in Pytorch by Larrikin on Wednesday March 14, 2018 @05:34PM (#16588505)
As someone learning Keras right now, why are you wanting too switch?
[ Parent | on HN ]
Re:Introduction to Recurrent Neural Networks in Pytorch by chrisfosterelli on Wednesday March 14, 2018 @05:54PM (#16588658)
Not the parent, but the imperative interface supported by the dynamic graph approach Pytorch takes is much nicer.

Additionally, in my personal opinion Tensorflow is often too low level and Keras is often too high level for the things I'm trying to do for research. While you can jump between the two of course, I think PyTorch hits a much more natural middle ground in its API.

Tensorflow/Keras is making improvements in these areas with the eager execution, and is still great for putting models into production, but I think PyTorch is much better for doing research or toying with new concepts.

This article has some good comparison: http://www.goldsborough.me/ml/ai/python/2018/02/04/20-17-20-...

[ Parent | on HN ]
Re:Introduction to Recurrent Neural Networks in Pytorch by 220V_USKettle on Wednesday March 14, 2018 @05:56PM (#16588675)
Also, I believe the newer fast.ai course uses Pytorch, and the prior used Keras?

I would like to know more from the article about setting x,y,m1, and m2. Any explanation is appreciated.

[ Parent | on HN ]