Project source code for the exam of "Elaborazione dei Segnali Multimediali".
https://towardsdatascience.com/generating-music-using-deep-learning-cb5843a9d55e
forked from HeineCantor/AsItSounds
-
Notifications
You must be signed in to change notification settings - Fork 0
A deep learning project that generates music (piano rolls) using a Variational Autoencoder (VAE). The generation is conditioned on the 'mood' detected from an input image, using a VGG16 model fine-tuned on the KDEF facial expression dataset. Project source code for the exam of "Elaborazione dei Segnali Multimediali".
vlb20/AsItSounds
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A deep learning project that generates music (piano rolls) using a Variational Autoencoder (VAE). The generation is conditioned on the 'mood' detected from an input image, using a VGG16 model fine-tuned on the KDEF facial expression dataset. Project source code for the exam of "Elaborazione dei Segnali Multimediali".
Topics
Resources
Stars
Watchers
Forks
Languages
- Jupyter Notebook 99.0%
- Python 1.0%