Great work. I am very new to this field and I have a question.
I am trying to train a shared GPLVM in python between two different domains.
Similar to this is Matlab example: https://github.com/SheffieldML/SGPLVM
My training data is 3D shape from one domain (Y) and I have a few corresponding shape examples for 3D data from another domain (Z). I have extracted various kinds of features (similar to landmarks/joints) from the data and performed PCA for dimensionality reduction.
I want to learn the shared latent space (X) between (Y) and (Z) [LEARNING STEP] and then be able to go from new Y input to generate Z output [MAPPING STEP].
I am unable to find relevant GPy examples for training a shared latent space model. Can someone please help me with this/guide me in the right direction? Is there an example using GPy? Also any suggestions of computing Ky and Kz as done in the above Matlab example for human motion data.
Sorry, if it's a very basic question. Just trying to understand better.
Great work. I am very new to this field and I have a question.
I am trying to train a shared GPLVM in python between two different domains. Similar to this is Matlab example: https://github.com/SheffieldML/SGPLVM
My training data is 3D shape from one domain (Y) and I have a few corresponding shape examples for 3D data from another domain (Z). I have extracted various kinds of features (similar to landmarks/joints) from the data and performed PCA for dimensionality reduction.
I want to learn the shared latent space (X) between (Y) and (Z) [LEARNING STEP] and then be able to go from new Y input to generate Z output [MAPPING STEP].
I am unable to find relevant GPy examples for training a shared latent space model. Can someone please help me with this/guide me in the right direction? Is there an example using GPy? Also any suggestions of computing Ky and Kz as done in the above Matlab example for human motion data.
Sorry, if it's a very basic question. Just trying to understand better.