Just another repository
Project-Based Course Overview Welcome to TensorFlow Beginner: Basic Image Classification. This is a project-based course which should take approximately 2 hours to finish. Before diving into the project, please take a look at the course objectives and structure:
Course Objectives In this course, we are going to focus on three learning objectives:
- Learn to create, train and evaluate neural network models with TensorFlow and Keras.
- Understand the basics of neural networks.
- Learn to solve classification problems with the help of neural networks. By the end of this course, you will be able to create a neural network model which will be able to classify images of hand written digits with a high degree of accuracy.
Project Structure
The hands on project on Basic Image Classification is divided into following tasks:
Task 1:Introduction
- Introduction to the basic image classification problem.
- What is TensorFlow?
- Introduction to the Rhyme interface.
Task 2: The Dataset
- Importing the MNIST dataset.
- A quick look at the structure of the dataset.
- A quick look at the MNIST image examples.
Task 3: One Hot Encoding
- What is one hot encoding?
- How to encode the labels from the dataset.
Task 4: Neural Networks
- Graphical representation of linear equations.
- What are neural networks?
- What are activation functions?
Task 5: Pre-processing the Examples
- Unrolling the input features.
- Data normalization with mean and standard deviation.
Task 6: Creating the Model
- Creating a sequential model with Keras.
- Model architecture - hidden layers and hidden units.
- Softmax and ReLU activation functions.
- Compiling the model by specifying an optimizer and a loss function.
Task 7: Training the Model
- Training the model to fit to training data.
- Evaluating the model on the test data.
Task 8: Predictions
- Predictions on the test set.
- Visualizing the predictions.