Various frameworks have been made to help developers and enterprises implement deep learning models since implementing deep learning models from scratch is a tough and time-consuming process. TensorFlow is one of the most popular frameworks for designing, training, and implementing machine learning and deep learning models. It is an open-source software library created by the Google Brain to make the computing load easier and faster for machine/deep learning applications. Python is one of the programming languages that can interact with this library. TensorFlow assists in every step of data science workflow from implementation to deployments, such as visualization, model development, and evaluation.
TechClass TensorFlow online course aims to provide a practical approach to machine learning and deep learning using TensorFlow with Python. It brings you hands-on experience building your predictive models, state-of-the-art image classifiers, and deep neural networks using TensorFlow and Keras. By the end of this course, you will gain hands-on experience in designing, training, and evaluating variations of neural networks and learn the techniques required for working with large real-world datasets.
- Get familiar with TensorFlow and Keras, and their capabilities
- Learn how to set up and get started with TensorFlow in the Google Colab environment
- Gain hands-on experience building and training neural network models with Keras using Sequential and Functional APIs
- Gain hands-on experience evaluating neural networks and making predictions using them
- Learn how to implement callbacks in TensorFlow
- Get familiar with L1 and L2 regularizations and how to employ them to avoid overfitting
- Learn how to use early stopping, dropout, and batch normalization techniques to avoid overfitting
- Get familiar with convolutional neural networks (CNNs), different layers of CNN, and popular CNN architectures
- Gain hands-on experience implementing CNN in TensorFlow for computer vision tasks
- Learn how to analyze the performance of CNN after training
- Understand the concept of transfer learning and how transfer learning models are made
- Learn how to implement transfer learning models in TensorFlow
- Get familiar with TensorFlow Hub and how to use it for transfer learning applications
Table of contents
Chapter 1: Beginning with This Course
- 1.1. Our Approach in This Course
- 1.2. About TechClass AI Department
- 1.3. Your Expectations, Goals, and Knowledge
Chapter 2: Introduction
- 2.1. What is TensorFlow?
- 2.2. TensorFlow 1.x vs. TensorFlow 2.x
- 2.3. Getting Started with Google Colab
- 2.4. Setting up TensorFlow
Chapter 3: Python Overview
- 3.1. Variables and Operators
- 3.2. Data Structures
- 3.3. Conditional Statements
- 3.4. Loops
- 3.5. Exercise
Chapter 4: Building Models using Keras
- 4.1. What is Keras?
- 4.2. Machine Learning Models in General
- 4.3. Basic Neural Network Sequential Model
- 4.4. Fitting, Evaluation, and Prediction
- 4.5. Functional API Models
- 4.6. Handwritten Digit Recognition using Neural Network
- 4.7. Callbacks
Chapter 5: Convolutional Neural Networks
- 5.1. Why CNN?
- 5.2. CNN Layers
- 5.3. Typical CNN Architecture
- 5.4. Implementing CNN in TensorFlow: Sequential API
- 5.5. Implementing CNN in TensorFlow: Functional API
- 5.6. Popular CNN Architectures for Computer Vision
- 5.7. Training and Evaluating CNN for CIFAR10 Dataset
Chapter 6: Handling Overfitting
- 6.1. What is Overfitting?
- 6.2. Regularization: Basics
- 6.3. L1 and L2 Regularizations
- 6.4. Quiz
- 6.5. Early Stopping
- 6.6. Dropout
- 6.7. Batch Normalization
Chapter 7: Saving and Loading Models
- 7.1. Introduction
- 7.2. Whole-model Saving
- 7.3. Whole-model Loading
- 7.4. Saving the Architecture
- 7.5. Loading the Architecture
- 7.6. Saving Model Weights
- 7.7. Loading Model Weights
Chapter 8: Transfer Learning
- 8.1. What is Transfer Learning?
- 8.2. How to Use Transfer Learning?
- 8.3. Loading Pre-trained Models in Keras
- 8.4. Pre-trained Model as Classifier
- 8.5. Pre-trained Model as Standalone Feature Extractor
- 8.6. Pre-trained Model as Integrated Feature Extractor
- 8.7. TensorFlow Hub
Chapter 9: Final Tasks
- 9.1. Project
- 9.2. Self-study Essay
- 9.3. Congrats! You did it!
Payment & Security
Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.
The topics were well organised and the course platform is good. The final project was nice.
- Opens in a new window.