In this chapter, we'll use the following tools:
- A command line or Bash to launch Magenta from the Terminal
- Python and its libraries to write specific training configuration for a model
- Magenta and Magenta GPU to train our models
- TensorBoard to verify the training metrics
- Google Cloud Platform to offload the training in the cloud
In Magenta, we'll make the use of the Drums RNN, Melody RNN, and MusicVAE models for training. We'll be explaining the training for those models, but if you feel like you need more information, the model's README in Magenta's source code (github.com/tensorflow/magenta/tree/master/magenta/models) is a good place to start. You can also take a look at Magenta's code, which is well documented. We have also provided additional content in the last section, Further reading.
The code for this chapter is in...
