Over 60k stars on github for TF. It won.
Ask HN: Why TensorFlow instead of Theano for deep learning?
21–30 of 54 posts
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#22I found this to be informative - https://svds.com/getting-started-deep-learning/
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#23tensorflow has tensorboard, a great application that allows your to explore your models in depth. it makes neural networks less of a black box.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#24We've moved over to Tensorflow from Theano around a year ago. I'm a Software Engineer on the team and here's what I think are advantages from my POV:
1) Transition was fairly straightforward, both APIs' interfaces are more-or-less similar and share some design characteristics.
2) Having said that, TF's API is easier to use and without a doubt a lot easier to read.
3) Consistency: Deploying Theano in different environments surprised me on several occasions with different output compared to the training environment. TF is more consistent on this front (never had such issues).
4) Running multiprocessing with Theano + GPU is a disaster (due to forking) so I end up having to create process pools before initializing Theano. No such issues with TF.
5) TF provides many helpful operators (such as queues and batching ops) as well as monitoring tools (Tensorboard) and debugging tools.
6) Its development is extremely rapid, new releases every couple of months with a lot of improvements and new features every time.
In short, TF is what Theano should have been. A lot of new papers are being developed in TF as well so it helps to understand it.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#25Use a AI program to answer that question!
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#26Over 60k stars on github for TF. It won.
If people weren't lemmings, that would be a valuable indicator. But, it turns out that...
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#27One other benefit with TensorFlow is that transitioning to cloud based processing on Google Cloud / Tensor Processing Units is seamless. It will turbo charge your training when compared to typical GPU performance.
Disclosure: Work for Google Cloud
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#28Have you considered using Pytorch? Actually, many in the DL community thinks it is the next big thing as it is more intuitive and dynamic than Tensorflow.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#29TensorFlow automatically discovers and uses GPUs and multiple cores, and I'm assuming Google is working on better supporting multiple GPUs, which currently requires hacks/tweaking to get speedups (it's easy to 'use' them) TensorFlow is a platform "winner" and approx 100% of all innovations will quickly be ported to TensorFlow - TBD which of the others will "keep up" with innovations as they continue to come out. othe…
Your comments are mostly valid, but I disagree about Keras. Although it's marvellous for patching something together quickly, if you want to branch out at all then it quickly becomes an absolute mess.
Far better, in my view, is to work with the newer Estimators API. It is almost as fool-proof as Keras, but instead of trying to be a framework as such, the Estimators/learn API essentially just wraps up some of the boilerplate that you need with raw tensorflow, and internally looks fairly similar to the code you might write yourself. Consequently, it preserves the composability of TF far better than Keras.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#30An observation when taking a step back: The discussion about deep learning frameworks seems almost as complicated as the Javascript framework discussions a couple of years ago. Google and Facebook pushing their own frameworks (among other participants) also adds to the deja vu! Why is the choice of framework such a big deal? Is it unreasonable to expect someone well-versed in one framework to be able to pick up anoth…
To answer your first question, I actually don't think it's a big deal.
It may become important if you end up having a ton of models running in production that need to be maintained and further developed, but in general for new applications I would say that substantially less than 5% of your time would (should!) be spent actually writing any code.