Disentangled-Sequential-Autoencoder
Disentangled-Sequential-Autoencoder copied to clipboard
Variational Autoencoder for Unsupervised and Disentangled Representation Learning of content and motion features in sequential data (Mandt et al.).
I have corrected many errors in the code, but I'm still not able to run the code, e.g. the error in the title. Can anyone provide a runnable script or...
Thanks for releasing this script! I suspect there may be a mistake in create_lpc_dataset.py in the function prepare_tensor. Under the action 'slash' we have row indices (14,15), (15,16), (16,17) but...
In the appendix of the paper they mention that they use a prior which is modeled by an LSTM, but in the code here I see that only normal prior...
Hi, I understand z has time index and f doesn't have time index. So I think that kl divergence of f does not match the time scale unless you multiply...
I found some typo/bugs in your repo, feel sorry to ask, but could you provide a runner script which reproduce the experments in your paper
Hello! Thanks for your work! Can you publish the codes for speech data?