After thinking a bit more, it would be nice to add a few lines to allow loading from other devices. Someone like @Mihonarium might want to load a pre-trained checkpoint and further train with different music data. As mentioned in the paper section 4.2, I've seen small performance gains by using 10% of test-dummy-set as training data. I call this use case as "seen database" to distinguish with general cases of fully "unseen" test set.
...............................................................................................................................................................................................................................................
What's even more strange, the issue with a lot of warnings appears only with run.py train and doesn't appear for generate.
After thinking a bit more, it would be nice to add a few lines to allow loading from other devices. Someone like @Mihonarium might want to load a pre-trained checkpoint and further train with different music data. As mentioned in the paper section 4.2, I've seen small performance gains by using 10% of test-dummy-set as training data. I call this use case as "seen database" to distinguish with general cases of fully "unseen" test set.
............................................................................................................................................................................................................................................... What's even more strange, the issue with a lot of warnings appears only with
run.py trainand doesn't appear forgenerate.The notebook: https://gist.github.com/Mihonarium/e3fd355cb560b82373fd2186139f1bc2 (the last cells show that
generateand training from scratch work).Originally posted by @Mihonarium in https://github.com/mimbres/neural-audio-fp/issues/10#issuecomment-878456349