• Extend the model in this notebook into one which maps (X,Y) -> (R,G,B)
• Add at least 2 more layers to the network.
• Experiment with alternative activation functions and optimizers.
• In a paragraph or so, describe how the image we have created differs from a normal image.
Submission:
Notebook - JupyterNoteboook and PDF
README - Reflection
Submission:
Notebook - JupyterNoteboook and PDF
README - Reflection
Using the Colab Notebook provided experiment with training your own LSTM audio model and generating some example sequences Provide a report (~500 words, pdf) detailing your experiments, including media examples (audio) where appropriate
Submission:
Notebook - JupyterNotebook and PDF
Report - PDF
Audio Files - output1.wav and output2.wav
README - Google Colab Links