Hello, I need to realize the task of parallelizing in the field of machine learning. What I essentially have is that there are several detected areas - their number is from 0 to 5, you need to run the trained classifier on these areas, how is this better implemented?

Closed due to the fact that the question is too general for the participants jfs , aleksandr barakin , D-side , zRrr , Grundy May 11, 16 at 14:42 .

Please correct the question so that it describes the specific problem with sufficient detail to determine the appropriate answer. Do not ask a few questions at once. See “How to ask a good question?” For clarification. If the question can be reformulated according to the rules set out in the certificate , edit it .

  • Tried to use something? Try a multiprocessing library, for example. Great review of libraries for ParallelProcessing here . - approximatenumber
  • I forgot to say that these areas stand out in real-time, while not really trying to do anything, just started up threads, but the prediction on areas occurs at different times + there is a tangle openCV - lao712
  • one
    The question is too extensive. Do you have a specific problem? - jfs

0