Goal: discussion of classification accuracy using the features extracted by our auto-encoder.
Related notebooks: audio_features, audio_classification
- Resolved memory exhaustion.
- Prevent data copy in the PyUNLocBoX toolbox. The toolbox was internally storing multiple copies of the data when instantiating functions and solvers. Store a reference instead. See git commit for further details. The memory consumption of our application was then divided by 5. No significant impact on speed.
- Use 32 bits floating point instead of 64 bits. It saves half the memory and increase the speed by 1.6. We are not memory bandwidth limited anymore. Computations almost always fully load two CPU cores.
- Projection in the L2 ball, not on the ball surface. It is a convex constraint. No significant improvement in speed.
- Insert the energy auto-encoder in the pipeline.
- Data normalization: features or samples ?
- Decrease dimensionality for faster experiments.
- Approaches for faster convergence.
- Experiment with hyper-parameters.
- Create the graph.
- Insert the Dirichlet energy in the objective.