Final Assignment for ECS7013P: Deep Learning for Audio and Music.
In this assignment we were requested to implement two distinct deep learning methods in order to infer two aspects from a chosen audio file. The proposed approach consisted of a first network that classifies an audio file into music or non-music. Given that the file is classified as music, it is then passed into the second network, where the task of music genre classification is performed. At the beginning of each file there is a brief description of the task, the resources and references used, as well as information about the datasets and the chosen audio file. It was implemented using Python 3.6.6 and PyTorch.
Network model and weights after training available at:
https://drive.google.com/drive/u/0/folders/1v5cUQL2dV8SLldHkkB4HNE9laWcl0AD8