0

I am trying to train model for handwritten digits. My data consists of images, each of size 80X80. So I get 6400 features as inputs. While trying to train model as per code used in https://www.kaggle.com/kakauandme/digit-recognizer/tensorflow-deep-nn, my systems hangs after 200 iterations with training accuracy 0.06.

Why is this happening? I don't get any errors. My system just freezes. Also, how do I set pooling and convolution layers parameters? Is the problem related to these parameters?

PS: I'm not using GPU.

stkusr1234
  • 61
  • 7
  • BTW, I've seen TensorFlow hang my system when it used too much memory, so you may want to try running it with `top` to see if memory is exploding – Yaroslav Bulatov Oct 13 '16 at 17:59
  • Yes that was my first thought too. But surprisingly, I have a lot of memory still available just before it hangs. – stkusr1234 Oct 14 '16 at 05:22
  • Hi, @stkusr1234 - if still relevant, can you provide more information about your system? Windows of Linux? And when you say freezes - is it just TF, or your entire computer? (If this isn't relevant still, might be best to close the question if you don't want an answer.) – dga Nov 18 '17 at 23:18

0 Answers0