I've been looking through the documentation of TensorFlow the last few days, and I'm really starting to find myself getting over PyBrain.
 |
|  |
|
|
It's not like I fell in love with PyBrain when I began the process and am dumping it at the first glance at some other more curvaceous library. I appreciate that first dip, but in all seriousness, I think TensorFlow is going to prove far more accessible. "We're excited to see people using TensorFlow in over 6000 open-source repositories online." With that in mind, I would like to take a deeper dive into TensorFlow.
New Industry Reading link: Google Research for TensorFlow.
WHAT?! The deploy section of the TensorFlow site directly talks about distributed TensorFlow server clusters. This is really starting to sound like it's what I was hoping to find. After reading more about Distributed TensorFlow, I'm going to fall back on a familiar phrase, I need to get more comfortable with the basics before I jump straight into the deep end. I don't know the first thing about distributed computing. It's a goal to learn it, and not a prudent starting point.
So, let's start an install of TensorFlow on my MacBook Air and see how far we get.
Install TensorFlow on OSX: The first question I need to answer is do I want to tackle finding out information about my GPU, so that I can make an informed decision about whether I want GPU support. I'm running this on a MacBook Air, so I'm guessing I don't have "a NVIDIA CUDA GPU meeting the prerequisites". Even if I did, I'm not planning to intentionally " run performance-critical applications". Let's just go for the CPU support only install.
Now that there is a decision on which version to install, I need to decide how to install. Since I'm not an expert, installing from sources is out of the question right now. This leaves, virtualenv, native pip, and Docker. Docker doesn't support TensorFlow with GPU support on the Mac which isn't an issue. The hundreds of MBs are not an issue, but still, I don't think I want to bother with Docker. Since I don't have an app in Docker, I don't have a reason to use it. The warnings about cross interference of Python packages and the disabling of SIP make me shy away from doing a native pip install.
So...that leaves virtualenv.
Step one: install pip
So, let's start an install of TensorFlow on my MacBook Air and see how far we get.
Install TensorFlow on OSX: The first question I need to answer is do I want to tackle finding out information about my GPU, so that I can make an informed decision about whether I want GPU support. I'm running this on a MacBook Air, so I'm guessing I don't have "a NVIDIA CUDA GPU meeting the prerequisites". Even if I did, I'm not planning to intentionally " run performance-critical applications". Let's just go for the CPU support only install.
Now that there is a decision on which version to install, I need to decide how to install. Since I'm not an expert, installing from sources is out of the question right now. This leaves, virtualenv, native pip, and Docker. Docker doesn't support TensorFlow with GPU support on the Mac which isn't an issue. The hundreds of MBs are not an issue, but still, I don't think I want to bother with Docker. Since I don't have an app in Docker, I don't have a reason to use it. The warnings about cross interference of Python packages and the disabling of SIP make me shy away from doing a native pip install.
So...that leaves virtualenv.
Step one: install pip
Step Two: Upgrade virtualenv
Step Three: The command you run Depends on which version of Python you're running. I'm on 2.7.
Step Four: Activate the virtualenv. Note the prompt will change after running this command.
Step Five: Now we actually install TensorFlow. Because I'm using Python 2.7 and pip is 8.1 or greater, the following command is run. Validate your install, and remember to activate the virtualenv (Step 4) whenever you open a new terminal.