I am an average solo user / applied researcher using Windows locally with a GTX 1070 8GB and looking for speed and documentation first, so Theano is way ahead in these departments. That said, we are also told TensorFlow is the next big thing because of scalability (?). TensorFlow works under Windows with Anaconda and Python 3.5 through Keras as well, so I have it available indeed and can try the benchmarks. Where do we stand, really? Thanks.
Ask HN: Why TensorFlow instead of Theano for deep learning?
1–10 of 54 posts
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#2Personally, I use a combination of Tensorflow and Appex frameworks. I find Theano simply lacking in features.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#3r/Machine Learning
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#4TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#5TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
I am kind of new to all of this but as far as I understood you can use Keras with TensorFlow as well.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#6TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
>Pytorch is better for research.
and yet a lot of researchers are using Caffe.
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#7TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
"PyTorch is better for research" is a weird, unsubstantiated statement. The fact is that few serious researchers use PyTorch (and even those complain about it). It's mostly grad students in a handful of labs. The only researchers I know who use PyTorch have been from FaceBook, and that's because they were implicitly forced to use it (PyTorch is developed by FaceBook).
According to https://medium.com/@karpathy/icml-accepted-papers-institutio... , 3 of the top research labs in the world are DeepMind, Google Brain (and the rest of Google), and Microsoft Research. Let's see:
* DeepMind: TensorFlow
* Google Brain: TensorFlow
* Microsoft Research: CNTK
Ok, so what about academia? The top deep learning groups in academia are:
* Montreal: Theano
* Toronto: TensorFlow
* IDSIA: TensorFlow
So, what about the greater academic research community? Maybe we could get some data about who uses what by looking at the frameworks cited by researchers in their papers. Andrej did that: it's mainly TensorFlow and Caffe. https://medium.com/@karpathy/a-peek-at-trends-in-machine-lea...
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#8TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
I am kind of new to all of this but as far as I understood you can use Keras with TensorFlow as well.
Yes you can - if you're new its a remarkably painless way to get started, at least compared to the pain you would otherwise endure :-)
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#9TensorFlow is better for deployment. Pytorch is better for research. Theano/Keras is simpler to use and a little faster than TensorFlow
"PyTorch is better for research" is a weird, unsubstantiated statement. The fact is that few serious researchers use PyTorch (and even those complain about it). It's mostly grad students in a handful of labs. The only researchers I know who use PyTorch have been from FaceBook, and that's because they were implicitly forced to use it (PyTorch is developed by FaceBook). According to https://medium.com/@karpathy/icml-ac…
Few people use PyTorch largely because it is relatively new (0.1.12). It even doesn't have distributed training capabilities (coming in 0.2). Your arguments don't say anything about frameworks themselves. It is unfair!
When people say PyTorch is better for research, they mean it is more flexible, and it is easier to implement non-trivial network architectures with it, such as recursive network, which is a cumbersome task for TensorFlow. MXNet's documentation provides a good overview to these two different styles (http://mxnet.io/architecture/program_model.html).
Re: Ask HN: Why TensorFlow instead of Theano for deep learning?
#10Earlier quoted context omitted.
"PyTorch is better for research" is a weird, unsubstantiated statement. The fact is that few serious researchers use PyTorch (and even those complain about it). It's mostly grad students in a handful of labs. The only researchers I know who use PyTorch have been from FaceBook, and that's because they were implicitly forced to use it (PyTorch is developed by FaceBook). According to https://medium.com/@karpathy/icml-ac…
Few people use PyTorch largely because it is relatively new (0.1.12). It even doesn't have distributed training capabilities (coming in 0.2). Your arguments don't say anything about frameworks themselves. It is unfair! When people say PyTorch is better for research, they mean it is more flexible, and it is easier to implement non-trivial network architectures with it, such as recursive network, which is a cumbersome…
All of these frameworks are "relatively new". TensorFlow: 1.6 years. CNTK: 1 year. PyTorch: 0.5 year. Are they really impossible to compare?
> When people say PyTorch is better for research, they mean
That's not what "people" say. They tend to say the opposite. Maybe we can ask OP what he meant when he said it.
> it is easier to implement non-trivial network architectures with it, such as recursive network
It is interesting that you mention recursive networks. There are only a few dozens of researchers who work with recursive networks, and they are all accounted for, we know what tools they use. They use Chainer and DyNet.