autoregressive
autoregressive copied to clipboard
cheind
:kiwi_fruit: Autoregressive Models in PyTorch.
I am attempting to use your wavenet implementation to model some climate data, where my condition vector changes with time. The code mentions only global conditioning is currently supported. What...
PixelCNN++ argues that neighboring intensity usually correlate is not captured by the softmax distribution. Instead, they propose a mixture model consisting of the logitic distribution (like normal but with heavier...
currently we assume that what we get as input is what we will predict as output (just shifted). However, thinking towards other research areas it might make sense that we...
drawback: all conditions would have to be embeddable (i.e integers) - except the embedding layer is not part of the model, but lives outside.
https://towardsdatascience.com/squeeze-and-excitation-networks-9ef5e71eacd7
https://www.lighttag.io/blog/complement-objective-training-with-pytorch-lightning/