I have been using Deep Learning with Tensorflow for a pet project only for educational purpose, and have been able to obtain quite good results with a CNN of my own.

However, the process I used to get there is not satisfying, because it looks like trial/error based on basic metrics: performance on training set and evaluation sets. I do not know if this is efficient, or if some layers are useless or over/under sized. Same for the kernel sizes.

Do you have any book or article or blog to recommend on the subject, for learning to be a better practitioner ? I have read "The Bengio" ("Deep Learning") and another book in French about practicing Tensorflow ("Comprendre le Deep Learning: Une introduction aux réseaux de neurones"), but none gave a practical method. This looks like craftmanship only.

  • $\begingroup$ welcome to SO; SO is not a recommendation site. If you're looking for resources, there are dozens out there, and everyone will have a different opinion of what is the best route $\endgroup$ Sep 5 '18 at 19:33
  • 2
    $\begingroup$ Please take a look at this link github.com/ChristosChristofidis/awesome-deep-learning.. $\endgroup$
    – N.IT
    Sep 5 '18 at 21:19
  • $\begingroup$ Search for CS 231N $\endgroup$
    – Aditya
    Sep 6 '18 at 0:53