Tensorflow sucks
nicodjimenez.github.io
Tensorflow sucks
1–10 of 133 posts
Re: Tensorflow sucks
#2Personally, I hate it that all these libraries are so much geared towards neural networks.
Why can't we just have compute networks that can be used for anything, from computational linear algebra to deep learning?
> Let’s be honest, when you have about half a dozen open source high-level libraries out there built on top of your already high-level library to make your library usable, you know something has gone terribly wrong
I consider that not a bug but a feature.
Re: Tensorflow sucks
#3Personally, I hate it that all these libraries are so much geared towards neural networks. Why can't we just have compute networks that can be used for anything, from computational linear algebra to deep learning? > Let’s be honest, when you have about half a dozen open source high-level libraries out there built on top of your already high-level library to make your library usable, you know something has gone terrib…
Why can't we just have compute networks that can be used for anything, from computational linear algebra to deep learning?
You mean, like Tensorflow?
Re: Tensorflow sucks
#4> Pytorch’s interface is objectively much better than Tensorflow’s
Ummm. No. 'Objectively' is utter nonsense. For an objective view we would need to define "better" first and measure both interfaces performance. I think it is preference. I prefer the Tensorflow interface and don't mind it's declarative style.
However, if one wants to criticize something one could start with the static nature of Tensorflow (which you rightfully mentioned), which makes it hard to do stuff like LSTMs and dynamic batching. That works better in Torch. To me that is the only real attack point for Tensorflow. But keep in mind, that Tensorflow is still "1.x" software and stuff like Tf-Fold addresses the problem with static graphs already and Google plans for more dynamic graphs in Tf 2.0.
Also it would have been nice of you to measured performance of the both frameworks on common problems. But looking at the interface and shouting "bad" at Tensorflow is not really critique but a personal dissatisfaction with Tensorflow.
I think that Tf currently aims more at production code than research stuff. The mentioned problem with being to low-level for simple stuff like layers is also not right. Have a look at the shipped contrib modules, you'll find common layers in there.
Re: Tensorflow sucks
#5Wait, (s)he’s arguing that the code isn’t imperative enough, but the punchline is they don’t like having to type session.run? I don’t understand their vendetta against the graph, which is a powerful abstraction that lets you choose different backend, and let’s tensorboard show you an awesome view of your computation. Session.run isn’t hard to type and it takes at most a few days to grok that everything is lazily evaluated.
Would (s)he like eager apis? Does (s)he want better c++ apis? Or does the author just want to hate on tensorflow because it’s been hyped so much?
Re: Tensorflow sucks
#6> Pytorch’s interface is objectively much better than Tensorflow’s Ummm. No. 'Objectively' is utter nonsense. For an objective view we would need to define "better" first and measure both interfaces performance. I think it is preference. I prefer the Tensorflow interface and don't mind it's declarative style. However, if one wants to criticize something one could start with the static nature of Tensorflow (which you…
In my experience (computer vision, deep learning) PyTorch is substantially faster as well, especially in data augmentation where it’s not just a thin layer over cudnn.
That said, you’re right. There’s no way I’d deploy it to production.
Re: Tensorflow sucks
#7It seems to me the reason for insisting on a verbose declaritivization of everything is obvious: it guarantees you can build run/traintime environments which scale your model automatically.
Google’s mindset isn’t “train this model to multiply by three”. It’s “train this model on a 1% sample of search traffic over the last year.” That’s reflected in the design choices of tensorflow.
Re: Tensorflow sucks
#8...and that's why you are using Keras instead.
Re: Tensorflow sucks
#9An appropriate quote: "If you can't intelligently argue for both sides of an issue, you don't understand the issue well enough to argue for either."
There are many people for whom the declarative paradigm is a huge plus. I would say there are at least 2 major approaches in running fast neural networks: 1. Figure out the common big components and make fast versions of those. 2. Figure out the common small components and how to make those run fast together.
Different libraries have different strengths and weaknesses that match the abstraction level that they work at. For example, Caffe is the canonical example of approach 1, which makes writing new kinds of layers much harder than with other libraries, but makes connecting those layers quite easy as well as enabling new techniques that work layer-wise (such as new kinds of initialization). Approach 2 (TensorFlow's approach) introduces a lot of complexity, but it allows for different kinds of research. For example, because how you combine the low-level operations is decoupled from how those things are optimized together, you can more easily create efficient versions of new layers without resorting to native code.
Re: Tensorflow sucks
#10Personally, I hate it that all these libraries are so much geared towards neural networks. Why can't we just have compute networks that can be used for anything, from computational linear algebra to deep learning? > Let’s be honest, when you have about half a dozen open source high-level libraries out there built on top of your already high-level library to make your library usable, you know something has gone terrib…
Have you looked at the APIs for any of these libraries? I think there is a perception that these are all for NN only because NN is the hot topic that everyone is jumping on noe; but tf for example is a general matrix manipulation library with a bunch of amazing, extra NN stuff shipped alongside it.