Abdul Fatir
Abdul Fatir
@kwotsin Sorry, I forgot to respond. I don't need them anymore but discriminators would be a great addition to this repo, especially with more and more recent methods using pretrained...
@nghiahhnguyen were you able to reproduce the results for this dataset? @lxuechen Could you please clarify which KL reweighting coefficient from {1, 0.1, 0.01, 0.001} worked best in your experiments...
Thanks for your reply, @nghiahhnguyen! Can you please share insights/hyperparameters from your setup that led to the improvement? On my end I am getting the lower-bound around 1e7 and test...
Thanks a lot @nghiahhnguyen! I did use trainable scales in my experiments but only as a trainable vector (not output from a NN as in the paper). Thanks for sharing...
Hi @mostoo45 How do I reproduce the issue?
Many people are facing this issue. Can someone look into it?
Thanks for the clarification. Didn't notice the parentheses.
@canerturkmen I removed the test directory and moved it to a standalone script in the main folder. I don't want to add it to the main gluonts tests. 1. It...
@benidis I changed the gluonts functions as we discussed. Please check that the forecasting experiments run as expected, whenever you can. If everything works, we can clean up the requirements...
Hi, I don't have the model now.