2

I will train my own cascade, using python and opencv. I want it to be as precise as possible, so as I read it is common that training takes one or two weeks to compile. I want to use cloud computing to not wait that long. I research but cannot find a single guide that explains what to do. I have pozitive and negative images, and a python code. How I can compile my code on cloud with least additional efford? (till now I just use my desktop, just wrote and compile scripts. I have no experience on cloud computing.) I found zero answers when searching opencv,python,cloud computing together. topics like this are for permanent web applications, I guess. I just want to run the code and get results, basically.

Community
  • 1
talha
  • 21
  • 2
  • PS: Somehow I get no response when I ask questions on this site. Just look at my history. So, if I'm doing something wrong, please tell me so I'll correct it. I really need an answer, thanks – talha Jan 24 '15 at 16:29
  • I dont think its as simple as you think. Cloud computing doesnt magically make things go faster. It still might take two weeks on the cloud – Aaron Jan 24 '15 at 18:36
  • Even so, I would get stable platform that run foe two weeks without worrying about crush on my laptop. If you guide me to move my code to cloud computing I really appreciate it. Thanks for reply – talha Jan 24 '15 at 18:41

1 Answers1

1

I created a google cloud platform compute engine. It gives you the option to choose the number of CPUs and ram size to choose from. So I experimented with a couple of combinations.

  1. 4 CPU 26gb ram - after starting the training I realised it used only ~7 GB of ram with all 4 CPUs running at 100%
  2. 8 CPU ~25gb ram - used around 9gb ram
  3. 24 CPU ~35gb ram. - used around 9gb ram.

All three instances ran at 100% CPU usage. With the increase in the CPU count, the faster the output files were generated.

55597
  • 111
  • 2