Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The State of Machine Learning Frameworks

thegradient.pub

Post reply on HN
Print view View original

41–50 of 201 posts

Re: The State of Machine Learning Frameworks

#41

Post by nbeleski »

We have been using mostly Dlib[0]. There was the need to develop solutions that can be statically compiled and produce dependency-free dlls and dlib delivered remarkbly on that aspect.

I haven't had success doing so using frameworks such as Torch and TF, even if their toolkit is better to develop new solutions.

Also we get to write code in C++, which can be a big positive when developing machine learning SDKs. I personally still do most of the prototyping in Python though.

I'll be checking the link on the post that mentions that pytorch allows models to be converted to c++, looks promising actually.

[0] http://dlib.net/

Re: The State of Machine Learning Frameworks

#42

Post by machinelearning »

Why engineers like Tensorflow:

- More code to check-in (Looks more productive)

- More infrastructure, e.g. checkpoints, exporters etc. (Looks like they're doing more work)

- Fancy visualizations (Allows them to look impressive while presenting loss plots)

- Easier to reuse things others have implemented and still get credit for it (TF model zoo, research repo etc.)

Why researchers like pytorch:

- Way easier to hack together their novel idea

- Looks scrappier (which somehow makes the individual look like a better researcher instead of an ordinary programmer)

- Lots of other researchers release code in pytorch so if you're working off of their idea, you use pytorch to avoid re-producing their results.

Open to debate on these ideas, let me know if you have a counterpoint or any other reasons to add

Re: The State of Machine Learning Frameworks

#43

Post by bonoboTP »

ChefboyOG wrote: post #33
_coveredInBees wrote: post #19

We use Pytorch extensively in our startup. We tackle a lot of new research problems as consultants/partners to help develop products or devise new algorithms/models to solve tasks for our customers. We have never regretted our choice to pick Pytorch. I found the article pretty spot on when comparing Tensorflow and Pytorch. The things that have appealed to me about Pytorch are: 1. Extremely easy to debug and work with…

Agreed, but projects like Cortex are narrowing the gap around deployment imo https://github.com/cortexlabs/cortex

Seems like an AWS specific thing?

Re: The State of Machine Learning Frameworks

#44

Post by chillee »

o10449366 wrote: post #4

And Amazon is still trying to desperately get people to adopt MXNet.

MXNet is actually pretty good. It got to the "mixing eager and graph mode" semantics before either PyTorch or TensorFlow did. On top of that, it's also blazing fast (usually the fastest of the frameworks).

Admittedly, I've never used MXNet so it might have more issues that I'm not aware of. Judging from the benchmarks I've seen, however, MXNet got a lot of things right.

Unluckily, I just don't think it added enough on top of PyTorch or TensorFlow for people to consider switching. People switched from TensorFlow to PyTorch because eager mode was just so much easier to use.

Re: The State of Machine Learning Frameworks

#45

Post by ehsankia »

machinelearning wrote: post #42

Why engineers like Tensorflow: - More code to check-in (Looks more productive) - More infrastructure, e.g. checkpoints, exporters etc. (Looks like they're doing more work) - Fancy visualizations (Allows them to look impressive while presenting loss plots) - Easier to reuse things others have implemented and still get credit for it (TF model zoo, research repo etc.) Why researchers like pytorch: - Way easier to hack t…

Researcher's codes are historically not very clean and re-usable. It may work fine if you want to hack together something to get data for a paper, but if you want to run a real production service, and don't want to drown in tech debt in a year; and that often means more code, as you imply above. I don't think it's unnecessarily verbose, it's just that it's more structured and scalable.

Re: The State of Machine Learning Frameworks

#48

Post by sairahul82 »

I think its matter of time. New things gets adopted first in research. I think pytorch will take over tensorflow. I was also a tensorflow user and when i switched to pytorch i never looked back. I was also participating in a kaggle competition and top 20 models are all implemented in pytorch.

Re: The State of Machine Learning Frameworks

#50

Post by ehsankia »

sails wrote: post #14
rayalez wrote: post #7

Anyone 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. https://www.youtube.com/watch?v=EqWsPO8DVXk

Jeremy Howard [0] has some takes here [1], mostly negative if I recall correctly. [0] https://www.fast.ai/about/ [1] https://www.youtube.com/watch?v=J6XcP4JOHmk&t=4152s

Wouldn't the CEO of Fast AI, a library using PyTorch, be slightly biased?
Post reply on HN