Buy Now AED 170.99 + VAT

Monthly Subscription Starting at AED 99 + VAT

Customising your models with TensorFlow 2
  • Level Professional
  • المدة 27 ساعات hours
  • الطبع بواسطة Imperial College London
  • Offered by

عن

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.

الوحدات

Introduction to the course

    • 2 Videos
    • 4 Readings
    • 1 Discussion
    • 1 Plugin
Show info about module content

1 Discussions

  • Introduce yourself

2 Videos

  • Welcome to Customising your Models with TensorFlow 2
  • Interview with Laurence Moroney

4 Readings

  • About Imperial College & the team
  • How to be successful in this course
  • Grading policy
  • Additional readings & helpful references

The Keras functional API

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Multiple inputs and outputs

3 Videos

  • The Keras functional API
  • Multiple inputs and outputs
  • [Coding tutorial] Multiple inputs and outputs

Variables and Tensors

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Variables and Tensors

3 Videos

  • Variables
  • Tensors
  • [Coding tutorial] Variables and Tensors

Accessing model layers

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Accessing model layers

3 Videos

  • Accessing layer Variables
  • Accessing layer Tensors
  • [Coding tutorial] Accessing model layers

Layer nodes

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] Layer nodes

Freezing layers

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Freezing layers

2 Videos

  • Freezing layers
  • [Coding tutorial] Freezing layers

Device placement

    • 1 Readings
Show info about module content

1 Readings

  • Device placement

Programming assignment: Transfer learning

    • 1 Videos
    • 1 Lab
    • 1 Programming
    • 1 Assignment
Show info about module content

1 Programming

  • Transfer learning

1 Assignment

  • [Knowledge check] Transfer learning

1 Labs

  • Transfer learning

1 Videos

  • Wrap up and introduction to the programming assignment

Keras datasets

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Keras datasets

3 Videos

  • Welcome to week 2 - Data Pipeline
  • Keras datasets
  • [Coding tutorial] Keras datasets

Dataset generators

    • 2 Videos
    • 1 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • [Knowledge check] Python generators

1 Labs

  • [Coding tutorial] Dataset generators

2 Videos

  • Dataset generators
  • [Coding tutorial] Dataset generators

Image data augmentation

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Keras image data augmentation

2 Videos

  • Keras image data augmentation
  • [Coding tutorial] Keras image data augmentation

Data generators for time series

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] TimeSeriesGenerator

Introducing the tf.data module

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] The Dataset class

2 Videos

  • The Dataset class
  • [Coding tutorial] The Dataset class

Creating Dataset objects from other data sources

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] Creating Datasets from different sources

Training with Datasets

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Training with Datasets

2 Videos

  • Training with Datasets
  • [Coding tutorial] Training with Datasets

TensorFlow Datasets

    • 1 Readings
Show info about module content

1 Readings

  • TensorFlow Datasets

Programming Assignment: Data pipeline with Keras and tf.data

    • 1 Videos
    • 1 Lab
    • 1 Programming
Show info about module content

1 Programming

  • Data pipeline with Keras and tf.data

1 Labs

  • Data pipeline with Keras and tf.data

1 Videos

  • Wrap up and introduction to the programming assignment

Introduction to the week 3 - Sequence Modelling

    • 2 Videos
Show info about module content

2 Videos

  • Welcome to week 3 - Sequence Modelling
  • Interview with Doug Kelly

Preprocessing sequence data

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Preprocessing sequence data

3 Videos

  • Preprocessing sequence data
  • [Coding tutorial] The IMDB dataset
  • [Coding tutorial] Padding and masking sequence data

Tokenising text data

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] Tokenizing text Data

Embeddings

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Embeddings

3 Videos

  • The Embedding layer
  • [Coding tutorial] The Embedding layer
  • [Coding tutorial] The Embedding Projector

Recurrent neural networks

    • 2 Videos
    • 1 Lab
    • 1 Assignment
Show info about module content

1 Assignment

  • [Knowledge check] Recurrent neural networks

1 Labs

  • [Coding tutorial] Recurrent neural network layers

2 Videos

  • Recurrent neural network layers
  • [Coding tutorial] Recurrent neural network layers

Stacked and bidirectional RNNs

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Stacked RNNs and the Bidirectional wrapper

2 Videos

  • Stacked RNNs and the Bidirectional wrapper
  • [Coding tutorial] Stacked RNNs and the Bidirectional wrapper

Stateful RNNs

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] Stateful RNNs

Programming Assignment: Language model for the Shakespeare dataset

    • 1 Videos
    • 1 Lab
    • 1 Programming
Show info about module content

1 Programming

  • Language model for the Shakespeare dataset

1 Labs

  • Language model for the Shakespeare dataset

1 Videos

  • Wrap up and introduction to the programming assignment

Model subclassing

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Model subclassing

3 Videos

  • Welcome to week 4 - Model subclassing and custom training loops
  • Model subclassing
  • [Coding tutorial] Model subclassing

Custom layers

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Custom layers

2 Videos

  • Custom layers
  • [Coding tutorial] Custom layers

Allowing flexible inputs for custom layers

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] The build method

Automatic differentiation

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Automatic differentiation

2 Videos

  • Automatic differentiation
  • [Coding tutorial] Automatic differentiation

Custom training loops

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] Custom training loops

2 Videos

  • Custom training loops
  • [Coding tutorial] Custom training loops

Tracking metrics in custom training loops

    • 1 Lab
Show info about module content

1 Labs

  • [Reading] Tracking metrics in custom training loops

Optimising performance with tf.function

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • [Coding tutorial] tf.function decorator

2 Videos

  • tf.function decorator
  • [Coding tutorial] tf.function decorator

Programming Assignment: ResNet

    • 1 Videos
    • 1 Lab
    • 1 Programming
Show info about module content

1 Programming

  • Residual network

1 Labs

  • Residual network

1 Videos

  • Wrap up and introduction to the programming assignment

Neural translation model

    • 2 Videos
    • 1 PeerReview
    • 1 Plugin
    • 1 Lab
Show info about module content

1 Peer Review

  • Capstone Project

1 Labs

  • Capstone Project

2 Videos

  • Welcome to the Capstone Project
  • Goodbye video

Auto Summary

Dive into TensorFlow 2 with this advanced course designed for data science and AI enthusiasts. Guided by an expert instructor, you'll master custom deep learning models using TensorFlow's lower-level APIs. Engage in practical coding tutorials, graded assignments, and a Capstone Project to develop a neural translation model. Perfect for professionals with Python proficiency and foundational machine learning knowledge. Available on Coursera with various subscription options.

Dr Kevin Webster
Instructor

Dr Kevin Webster