I classified some images using the keras pretrained deep networks and the result is shown in this picture. I am wondering why the points follow such a pattern from 0, 0.2, 0.4, 0.6 and 0.8? Why are there no values in between? Is this a recognizable pattern in a way or is my data weird?

enter image description here


put on hold as unclear what you're asking by mkt, Peter Flom Feb 12 at 11:15

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ Can you label/explain the axes? It's hard to say anything without knowing what you plotted. $\endgroup$ – ExabytE Feb 12 at 9:42
  • $\begingroup$ So the y axis is the output of the deep NN when an image is used as input for the pretrained keras models and the X is the probability of the image being classified as a 1 or 0 taking into account other features alongside the deep NN output which is considered another input feature for the whole classification. $\endgroup$ – Atirag Feb 12 at 9:49