Replies: 1 comment 2 replies
-
Hey @Leman5, This will be due to the randomness in deep learning. A deep learning model learns by starting with random patterns (initialized by the model) and then adjusting those over time by looking at data. However, every time you create a model it starts with different random patterns each time and will learn slightly different patterns each time it trains (again due to randomness). Controlling randomnessIf you'd like to control the randomness being used to generate different patterns you can do so using a random seed. See here for setting the random seed in TensorFlow: https://www.tensorflow.org/api_docs/python/tf/random/set_seed |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Once we have created a model and try to fit it over some data, every time we try running it, it gives different output. What is the reason behind this? Also what changes need to be made so that we get the same result always?
Beta Was this translation helpful? Give feedback.
All reactions