Explore

Customising your models with TensorFlow 2

Approx. 27 hours to complete

Save Course

Go to Course

Course Summary

Learn how to customize and optimize TensorFlow 2 models for better performance and accuracy.

Key Learning Points

Understand the importance of customizing models in TensorFlow 2 for better performance
Learn how to use TensorFlow 2 to customize and optimize models
Discover the different techniques to improve model performance and accuracy

Learning Outcomes

Ability to customize and optimize TensorFlow 2 models for better performance
Understanding of different techniques to improve model accuracy
Preparation for a career in machine learning, data science, or artificial intelligence

Prerequisites or good to have knowledge before taking this course

Basic knowledge of TensorFlow 2 and Python programming
Familiarity with machine learning and deep learning concepts

Course Difficulty Level

Intermediate

Course Format

Online
Self-Paced
Video Lectures
Assignments

Similar Courses

Advanced Machine Learning with TensorFlow on Google Cloud Platform
Applied Data Science with Python Specialization

Related Education Paths

Related Books

Description

Welcome to this course on Customising your models with TensorFlow 2!

In this course you will deepen your knowledge and skills with TensorFlow, in order to develop fully customised deep learning models and workflows for any application. You will use lower level APIs in TensorFlow to develop complex model architectures, fully customised layers, and a flexible data workflow. You will also expand your knowledge of the TensorFlow APIs to include sequence models. You will put concepts that you learn about into practice straight away in practical, hands-on coding tutorials, which you will be guided through by a graduate teaching assistant. In addition there is a series of automatically graded programming assignments for you to consolidate your skills. At the end of the course, you will bring many of the concepts together in a Capstone Project, where you will develop a custom neural translation model from scratch. TensorFlow is an open source machine library, and is one of the most widely used frameworks for deep learning. The release of TensorFlow 2 marks a step change in the product development, with a central focus on ease of use for all users, from beginner to advanced level. This course follows on directly from the previous course Getting Started with TensorFlow 2. The additional prerequisite knowledge required in order to be successful in this course is proficiency in the python programming language, (this course uses python 3), knowledge of general machine learning concepts (such as overfitting/underfitting, supervised learning tasks, validation, regularisation and model selection), and a working knowledge of the field of deep learning, including typical model architectures (MLP, CNN, RNN, ResNet), and concepts such as transfer learning, data augmentation and word embeddings.

Outline

The Keras functional API
Welcome to Customising your Models with TensorFlow 2
Interview with Laurence Moroney
The Keras functional API
Multiple inputs and outputs
[Coding tutorial] Multiple inputs and outputs
Variables
Tensors
[Coding tutorial] Variables and Tensors
Accessing layer Variables
Accessing layer Tensors
[Coding tutorial] Accessing model layers
Freezing layers
[Coding tutorial] Freezing layers
Wrap up and introduction to the programming assignment
About Imperial College & the team
How to be successful in this course
Grading policy
Additional readings & helpful references
Device placement
[Knowledge check] Transfer learning

Data Pipeline
Welcome to week 2 - Data Pipeline
Keras datasets
[Coding tutorial] Keras datasets
Dataset generators
[Coding tutorial] Dataset generators
Keras image data augmentation
[Coding tutorial] Keras image data augmentation
The Dataset class
[Coding tutorial] The Dataset class
Training with Datasets
[Coding tutorial] Training with Datasets
Wrap up and introduction to the programming assignment
TensorFlow Datasets
[Knowledge check] Python generators

Sequence Modelling
Welcome to week 3 - Sequence Modelling
Interview with Doug Kelly
Preprocessing sequence data
[Coding tutorial] The IMDB dataset
[Coding tutorial] Padding and masking sequence data
The Embedding layer
[Coding tutorial] The Embedding layer
[Coding tutorial] The Embedding Projector
Recurrent neural network layers
[Coding tutorial] Recurrent neural network layers
Stacked RNNs and the Bidirectional wrapper
[Coding tutorial] Stacked RNNs and the Bidirectional wrapper
Wrap up and introduction to the programming assignment
[Knowledge check] Recurrent neural networks

Model subclassing and custom training loops
Welcome to week 4 - Model subclassing and custom training loops
Model subclassing
[Coding tutorial] Model subclassing
Custom layers
[Coding tutorial] Custom layers
Automatic differentiation
[Coding tutorial] Automatic differentiation
Custom training loops
[Coding tutorial] Custom training loops
tf.function decorator
[Coding tutorial] tf.function decorator
Wrap up and introduction to the programming assignment

Capstone Project
Welcome to the Capstone Project
Goodbye video

Summary of User Reviews

The Customising Models with TensorFlow 2 course on Coursera is highly recommended by users. Learners enjoyed the interactive and engaging approach to learning how to build custom models with TensorFlow 2.

Key Aspect Users Liked About This Course

Interactive and engaging approach to learning

Pros from User Reviews

Great instructor who explains concepts clearly
Hands-on exercises reinforce learning
Challenging assignments push learners to improve
Content is up-to-date and relevant
Community forum provides helpful support

Cons from User Reviews

Some learners found the course too difficult for beginners
The pace of the course can be fast for some learners
Some learners experienced technical difficulties with the platform
The course can be time-consuming with long lectures and assignments
The course does not cover advanced topics in depth

Recommended for you

Deep Learning: Recurrent Neural Networks in Python

GRU, LSTM, Time Series Forecasting, Stock Predictions, Natural Language Processing (NLP) using Artificial Intelligence *** NOW IN TENSORFLOW 2 and PYTHON 3 *** Learn about one of the most powerful Deep Learning architectures yet!...

Save Course

Data Science 2021 : Complete Data Science & Machine Learning

Machine Learning A-Z, Data Science, Python for Machine Learning, Math for Machine Learning, Statistics for Data Science Well, you have come to the right place....

Save Course

Deep Learning for Computer Vision with Tensor Flow and Keras

ConvNets, VGG-16, ResNet, Inception, Faster R-CNN, TensorFlow Object Detection, YOLO v2-v3-v4. Train your own data. X (not 2....

Save Course

Introduction to TensorFlow

This course is focused on using the flexibility and “ease of use” of TensorFlow 2. x and Keras to build, train, and deploy machine learning models....

Save Course