Docs->Deep Gaussian Process, Why output dimension is 2? #2128
-
|
Hello! I am a student working on my master thesis related to Gaussian Process. I have read the paper for this tutorial https://arxiv.org/abs/1705.08933, which using the method of doubly stochastic variational GP for prediction. In the tutorial it quite confused me why the output dimension is set for 2 instead for 1? Since in the paper the output dimension is 1 and also in the dataset we applied in this paper is also 1. Thank you! |
Beta Was this translation helpful? Give feedback.
Replies: 2 comments
-
|
*The tutorial link is https://docs.gpytorch.ai/en/stable/examples/05_Deep_Gaussian_Processes/Deep_Gaussian_Processes.html |
Beta Was this translation helpful? Give feedback.
-
|
Perhaps changing the variable name to |
Beta Was this translation helpful? Give feedback.
output_dimshere refers to the number of outputs of the first (hidden layer).Perhaps changing the variable name to
hidden_dimswould be clearer. Please open up a PR if you think that would be a useful change 😄