1

(I downloaded the deep dream source code from https://github.com/google/deepdream)

First of all, I'm not interested in purely Deep Dream only, but machine learning, and deep learning in particular, as a whole. I know programming (but by no means an expert) and python syntax etc. However, I'm not familiar with external libraries and how to properly install them.

Thus, I'm struggling with simply getting the source code for Deep Dream to run. Here's what I've done so far:

  1. Installed Python, but it couldn't run the .ipynb (nor did it include any of the libraries) file so I:
  2. Installed Anaconda, but it didn't include Caffe so I:
  3. Downloaded Caffe, but it requires cudNN(??) so I:
  4. Downloaded cudNN (Does it require Cuda (whatever that is?))

What are the next steps? There are so many things to download and install and I have no experience with any of it except for Python programming itself.

I tried reading the install instructions but they get me even more confused.

What are the steps I should take next in order to get it running?

Keep in mind that I'm a beginner. No hate please. Official documentation and terminology are still hard to understand. I'm simply looking for step-by-step instructions.

Thanks in advance!

Edit: I'm using Windows

talonmies
  • 70,661
  • 34
  • 192
  • 269
Lobs001
  • 365
  • 4
  • 14
  • 1
    Cuda is the technology nVidia uses in their graphics card to allow custom workloads to be executed on the GPU. It's almost certainly required for a performance boost (if not to work at all). An .`ipynb` is a Python notebook. [See here](https://ipython.org/ipython-doc/1/interactive/notebook.html) for info. Did you follow the Deep Dream [install guide](https://github.com/google/deepdream/blob/master/dream.ipynb)? Specifically the linked section on [installing Caffee](http://caffe.berkeleyvision.org/installation.html)? It talks you through installation, including dependencies like CUDA – Basic Mar 18 '17 at 12:28
  • Thanks for the comment! I did try to follow it but there are so many dependencies and things that I should install and tune the settings for that I simply felt lost. Assuming that I'm installing everything from scratch, would I need to download anything more than Anaconda, Caffe, cudNN, CUDA and boost? – Lobs001 Mar 18 '17 at 13:06
  • Let's start with... What OS are you on? (Incidentally, I have to leave shortly and won't be back for a day or two. I'll respond when I can) – Basic Mar 18 '17 at 15:14
  • 1
    Or... If you're not familiar with it, Docker is going to be your easiest option. Think of a docker container as as a portable VM. You can install docker on almost any OS and then use it to load a container which has all the software pre-installed. You can [get docker here](https://www.docker.com/community-edition) and you can get the CPU / GPU container by following the [instructions here](https://github.com/BVLC/caffe/tree/master/docker). Note that Docker's really handy for other things too - eg I have containers for Centos 6/6.5/7, RHEL, SLES, Windows, etc... for testing and as servers. – Basic Mar 18 '17 at 15:21
  • 1
    Thanks for the suggestion. I got it working with Docker! With that said, however, I would still like to get it to work on Windows as I followed the instructions exactly on both the official realease as well as two forks. All produced errors, of different kinds, when trying to build the Caffe solution in Visual Studio. (I want to know what went wrong mainly because I'm frustrated and believe I did everything right, even though I obviously did something wrong :)) But since I got it working on Docker, and "moved on" to TensorFlow to learn more about DL/AI, it's not a big priority for me anymore. – Lobs001 Mar 19 '17 at 09:11
  • Ok, I'm going to make that comment an answer. If it solves your problem, please accept and close this question. As to your install issue... It sounds like something that would interesting to investigate. If you'd care to start a new question including details like OS Version/Build, and a precise set of steps to reproduce exactly what you've been trying. Then post a link here and I'll be happy to check it out and do what I can. All the best. – Basic Mar 19 '17 at 21:41

1 Answers1

2

[Promoted from a comment]

If you're not familiar with it, Docker is going to be your easiest option. Think of a docker container as as a portable, fully self-contained VM.

You can install docker on almost any OS, then use it to load a container which has all the software pre-installed.

You can get docker here and you can get the CPU / GPU container by following the instructions here.

Note that Docker's really handy for other things too - eg I have containers for Centos 6/6.5/7, RHEL, SLES, Windows, etc... for testing and as servers.

Basic
  • 26,321
  • 24
  • 115
  • 201