Search Unity

  1. We are migrating the Unity Forums to Unity Discussions by the end of July. Read our announcement for more information and let us know if you have any questions.
    Dismiss Notice
  2. Dismiss Notice

Question Saving visual observations as image files

Discussion in 'ML-Agents' started by sneakingsquid, Apr 30, 2024.

  1. sneakingsquid


    Dec 2, 2020
    I'm making a ML Agent project that involves an agent trained with two visual observations.
    What I am curious about is how to check the visible form of the visual observations that actually inputted to RL network.
    I just want to make sure that the visual observation is being inputted as I intended.
    For example, I want some methods such as saving the two visual observations that I'm inputing for network as image files.
    As far as I have checked, it seems that this feature is not provided in Unity ML Agents Toolkit.
    If there's something I've missed, I would appreciate your help.
    Thank you.
    Last edited: Apr 30, 2024