Using TensorFlow to Compose Music Like the One of Bach or The Beatles

At TensorFlow Dev Summit 2017, the Magenta project — cultivated by the Google Brain team — to facilitate music generation, storytelling, image style transfer, etc. was discussed. This blog post highlights the Magenta team experience of training a model, employing the Gibbs sampling, and explains why output evaluation is of critical importance.

Like what you read? Give Altoros a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.