This Microsoft Capstone project's goal is to build a deep learning model to predict the types of appliances (Labels) from spectrograms of current and voltage measurements (Images). A spectrogram is a visual representation of the various frequencies of sound as they vary with time.
The project is organized into following parts:
Introduction
Importing Libaries
Loading Images
Create training data
Preprocessing Training Data
Data Normalization and Spriting
Building the Model (MLP Model)
Evaluating the MLP Model
Building the Model (CNN Model)
Evaluating the CNN Model
Saving the built Model
Loading and Predicting with the new Built Model
Making Prediction on Testing Data
Conclusion
To view the code for the project check file named "DeepLearning.ipynb"