Deep learning using Tensorflow Lite on Raspberry Pi

Course Curriculum

Chapter 1: Non Linear Trigonometric Functions Approximation

Lecture 1: How Nerual Networks Work

Lecture 2: Non-Linear Function Approximation Understanding

Lecture 3: Trigonometric Function Data Generation

Lecture 4: Data Splitting and Normalizing

Lecture 5: Deep Learning Model Creation

Lecture 6: Model Performance testing and Loss Understanding

Lecture 7: Mean Squared Error Graph Understanding

Lecture 8: Designing New Improved Model

Lecture 9: Model Performance comparisons and Saving

Lecture 10: Github Push after Section Completion

Lecture 11: Github repository and Resources

Chapter 2: Visual Calculator

Lecture 1: Join our free community

Lecture 2: Raspberry PI OS setup

Lecture 3: Construction of Hardware

Lecture 4: Data Strategy for this project

Lecture 5: Producing Custom Data

Lecture 6: Raspberry PI SSH Setup using Vscode

Lecture 7: Video Saving Script

Lecture 8: Data Videos Obtaining

Lecture 9: Understanding Frame Extraction Process

Lecture 10: Hough Circles Understanding

Lecture 11: Number Extraction from Circles

Lecture 12: Data Obtaining and Pre Processing

Lecture 13: Visualizing Data on Google Colab

Lecture 14: 3D printing parts Source

Lecture 15: Model Architecture

Lecture 16: Model Implementation and training

Lecture 17: Model Saving

Lecture 18: Testing Model

Lecture 19: Model Performance Matrices understanding

Lecture 20: Post Quantization

Lecture 21: TFLite Conversion

Lecture 22: TF Lite Model Testing

Lecture 23: Real Time Prediction Script

Lecture 24: Model Inferencing on recorded Data

Lecture 25: Defining Region of Interest

Lecture 26: Testing ROI Improvements

Lecture 27: Raspberry PI Model Inferencing Setup

Lecture 28: RPI Inferencing Testing

Lecture 29: Equation Building

Lecture 30: Number Detection Isolation

Lecture 31: Equation Computation

Lecture 32: Github Push

Chapter 3: Voice Controlled LEDs

Lecture 1: Understanding Wave Files

Lecture 2: Audio Recording Script

Lecture 3: Audio Conversion from Float to Integer

Lecture 4: Data Recording in batches

Lecture 5: Wave file to Binary Tensors

Lecture 6: Data Visualizations

Lecture 7: Spectrogram Conversion

Lecture 8: Data Pre-processing Pipelines

Lecture 9: Model definition and Dataset Splitting

Lecture 10: Model Architecture

Lecture 11: Discussion Model Parameters and Training Model

Lecture 12: Reviewing Training Results

Lecture 13: Model Performance Matrix

Lecture 14: Tensorflow Lite Conversion and prediction

Lecture 15: Input Audio stream pipeline building

Lecture 16: TfLite model predictions

Lecture 17: LED connections and Blink

Lecture 18: Raspberry Pi Model Predictions

Lecture 19: Real Time Audio LED Controlling

Lecture 20: Github Push