We assume that the required datasets are already downloaded in "datasets" folder.
Here's a list of datasets, their paths and their links.
- Pascal VOC, datasets/VOCdevkit, http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
- IRMAS, datasets/IRMAS-TrainingData, https://zenodo.org/record/1290750/files/IRMAS-TrainingData.zip?download=1
- Urbansound8K, datasets/UrbanSound8K, https://urbansounddataset.weebly.com/urbansound8k.html

In order to get the results, you need to take the following steps.
1. Run all the "preprocess_and_fit" ipynb files
2. Run embedding_models_for_interepretation.ipynb
 