Is there any reason this might not work in windows? I see no installation docs for it.
PyTorch – Tensors and Dynamic neural networks in Python
21–30 of 91 posts
Re: PyTorch – Tensors and Dynamic neural networks in Python
#22I've never fiddled with machine learning thing so don't know anything about it. I am wondering if CUDA is mandatory for torch installation ? I use a Macbook air which doesn't have graphics card, so not sure if torch can be installed and used on my machine.
It's not mandatary, but for some problems such as using image data, it provides as substantial speedup when training a classifier.
Re: PyTorch – Tensors and Dynamic neural networks in Python
#23At this point I've used PyTorch, Tensorflow and Theano. Which one do people prefer? I haven't done a ton of benchmarking, but I'm not seeing huge differences in speed (mostly executing on the GPU).
Keras is going to be the interface to Tensorflow - https://news.ycombinator.com/item?id=13413487
Re: PyTorch – Tensors and Dynamic neural networks in Python
#24I've never fiddled with machine learning thing so don't know anything about it. I am wondering if CUDA is mandatory for torch installation ? I use a Macbook air which doesn't have graphics card, so not sure if torch can be installed and used on my machine.
You could probably train MNIST on your Macbook Air but anything much more complicated for that you would want to use A GPU.
Re: PyTorch – Tensors and Dynamic neural networks in Python
#25Guess there's no escaping Python. I had hoped Lua(jit) might emerge as a scientific programming alternative but with Torch now throwing its hat into the Python ring I sense a monoculture in the making. Bit of a shame really because Lua is a nice language and was an interesting alternative.
Re: PyTorch – Tensors and Dynamic neural networks in Python
#26At this point I've used PyTorch, Tensorflow and Theano. Which one do people prefer? I haven't done a ton of benchmarking, but I'm not seeing huge differences in speed (mostly executing on the GPU).
Keras is going to be the interface to Tensorflow - https://news.ycombinator.com/item?id=13413487
Yes, but Keras works just fine using Theano as a backend as well...
Re: PyTorch – Tensors and Dynamic neural networks in Python
#27Is there any reason this might not work in windows? I see no installation docs for it.
the C libraries are compatible with Windows, they are used in Torch windows ports. We just dont have any Windows devs on the project to help and maintain it :( .
Re: PyTorch – Tensors and Dynamic neural networks in Python
#28Is this related to lua's Torch at all? http://torch.ch/
They don't seem to explicitly say it, but it might be using the same core code given the structure of the framework and their mentioning that it's a mature codebase several years old. The license file also goes back to NYU before being taken over by Facebook, similar to Torch.
The core libraries are the same as in Lua torch, but the interface is redesigned and new.
Re: PyTorch – Tensors and Dynamic neural networks in Python
#29Guess there's no escaping Python. I had hoped Lua(jit) might emerge as a scientific programming alternative but with Torch now throwing its hat into the Python ring I sense a monoculture in the making. Bit of a shame really because Lua is a nice language and was an interesting alternative.
Lua is extremely flexible to the point where there is basically no standard library. This causes problems with code reuse and moving between codebases because everyone does things drastically differently. Compare this to Numpy in the Python world, a single fundamental package for scientific computing in Python.
Lua is less used than Python in the scientific community, and a lot of the most innovative machine learning researchers already work with C++ and Python. Using yet another language with only marginal benefit increases cognitive load and drains from the researcher's mental innovation budget, forcing the researcher to learn the ins and outs of Lua rather than working on innovative machine learning solutions.
Lua is a nice language. Python 3 is a nice language and there are many new exciting features and development styles (hello async programming?) in the making which will prevent a monoculture from forming in the near term.
Re: PyTorch – Tensors and Dynamic neural networks in Python
#30Guess there's no escaping Python. I had hoped Lua(jit) might emerge as a scientific programming alternative but with Torch now throwing its hat into the Python ring I sense a monoculture in the making. Bit of a shame really because Lua is a nice language and was an interesting alternative.
Lua is extremely flexible to the point where there is basically no standard library. This causes problems with code reuse and moving between codebases because everyone does things drastically differently. Compare this to Numpy in the Python world, a single fundamental package for scientific computing in Python. Lua is less used than Python in the scientific community, and a lot of the most innovative machine learning…
Thanks for the interesting and informative comment. Do I sense just a tiny bit of regret though? Yet another Python interface. YAPI. You heard it here first. And no, Py3 is not that nice. Too much cruft by far. And lua is miles faster than Python when you're outside the tensor domain, ie while you're sourcing and wrangling your data. Arguably luajit obviates the need for C , something you can't say about Python. Disclosure: I am a massive, but increasingly disenchanted, user of Python. I had actually started looking at Torch7, foregoing tensorflow, precisely because of Lua. But the walls are closing in....