search

BayesWatch / deep-kernel-transfer

Official pytorch implementation of the paper "Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels" (NeurIPS 2020)
https://arxiv.org/abs/1910.05199
197 stars 29 forks source link

DKT Regression #11

Closed surtantheta closed 2 years ago

surtantheta commented 2 years ago

Your paper mentions about in-range and out-range mse in the regression use case. However, we don't find these errors separately in the codebase. On running test_regression.py we receive a single MSE. Can you kindly elaborate what this value represents (in-range or out-range) ? Is the code and data available only for QMUL or sines also.

mpatacchiola commented 2 years ago

Hi @surtantheta I have now added the code for the sines experiments in the folder:

https://github.com/BayesWatch/deep-kernel-transfer/tree/master/sines

Follow the instructions in the README for setting up the out-of-range experiments.