Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The intermediate-level Customizing Your Models with TensorFlow 2 online course by Coursera builds a strong knowledge base for TensorFlow. You will learn to develop customized deep-learning models and workflows for any application. Additionally, the certification course will teach you how to build complex model architecture using lower-level APIs in TensorFlow.
Towards the course end, you will be working on a Capstone Project to apply the concepts you acquired over the course duration. You will custom-build a neutral translation model from scratch. The Customising Your Models with TensorFlow 2 programme, is the second course of the three-part Specialization – TensorFlow 2 for Deep Learning Specialisation. Moreover, the world-renowned institute, Imperial College of London, offers the online course, while Dr Kevin Webster instructs it.
You will learn via pre-recorded lectures and development experience, along with the coding assignments, which offer practical and field-relevant practice. A graduate teaching assistant will guide you through the projects. Most importantly, the Customising Your Models with TensorFlow 2 online course is entirely self-paced with flexible deadlines to suit your comfort.
The Highlights
- Shareable electronic certificate
- 100% online learning
- Deep Learning
- Flexibles deadlines
- Intermediate-level course
- Video transcripts
- Approx. 27 hours to complete
- Lectures in English
- Offered by Imperial College London
Programme Offerings
- Specialisation Course
- Flexible Deadlines
- 100% online course
- Intermediate-level Course
- Shareable Certificate
- practice quizzes
- Capstone Project.
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | Imperial College, LondonCoursera |
The Customising Your Models with TensorFlow 2 fee details:
Head | Amount |
1 Month | Rs. 4,115 |
3 Months | Rs. 8,230 |
6 Months | Rs. 12,345 |
Eligibility Criteria
Before you apply for the Customising your models with TensorFlow 2 course by Coursera, you need first to complete the Getting started with TensorFlow course. Additionally, candidates need to be proficient in Python programming (Python 3.0) and should have a basic understanding of the Machine Learning fundamentals.
Candidates should also have a working knowledge of Deep Learning concepts, including Transfer Learning, Data Augmentation, Model Architecture, among others.
What you will learn
After completing the Coursera Customising Your Models with TensorFlow 2 online training, you will get an idea about the following:
- Know how to apple the functional API to create better flexible model architectures with many outputs and inputs
- How to apply tools from Keras and TensorFlow to implement data pipelines
- Process data sequence and understand sequence modelling tasks
- Apply automatic differentiation tools to implement custom training loops
- Exploiting model and layer sub-classing API to develop entirely flexible model architectures
Who it is for
Admission Details
Enrol for the Customising your models with TensorFlow 2 programme by Coursera by simply following the steps mentioned below:
- Visit the course page.
- Type in ‘Customising your models with TensorFlow 2’ in the search bar to locate the course.
- Choose the “Join for Free” option on the top right corner.
- You can create your account on Coursera or log in through Google, Facebook, or Apple. If already have a Coursera account, log in and enrol for the course.
Application Details
Applying for the Customising of your models with TensorFlow 2 online course is quite simple. You do not have to fill out any form. Just sign up and enrol for the certification course, and you will get the course material.
The Syllabus
Videos
- Welcome to Customising your Models with TensorFlow2
- 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
Readings
- About Imperial College & the team
- How to be successful in this course
- Grading policy
- Additional readings & helpful references
- Device placement
Assignment
- [Knowledge check] Transfer learning
Programming Assignment
- Transfer learning
Discussion Prompt
- Introduce yourself
Ungraded Labs
- [Coding tutorial] Multiple inputs and outputs
- [Coding tutorial] Variables and Tensors
- [Coding tutorial] Accessing model layers
- [Reading] Layer nodes
- [Coding tutorial] Freezing layers
- Transfer learning
Plugin
- Pre-Course Survey
Videos
- 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
Readings
- TensorFlow Datasets
Assignment
- [Knowledge check] Python generators
Programming Assignment
- Data pipeline with Keras and tf.data
Ungraded Labs
- [Coding tutorial] Keras datasets
- [Coding tutorial] Dataset generators
- [Coding tutorial] Keras image data augmentation
- [Reading] TimeSeriesGenerator
- [Coding tutorial] The Dataset class
- [Reading] Creating Datasets from different sources
- [Coding tutorial] Training with Datasets
- Data pipeline with Keras and tf.data
Videos
- Welcome to Week 3 - Sequential 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
Assignment
- [Knowledge check] Recurrent neural networks
Programming Assignment
- Language model for the Shakespeare dataset
Ungraded Labs
- [Coding tutorial] Preprocessing sequence data
- [Reading] Tokenizing text Data
- [Coding tutorial] Embeddings
- [Coding tutorial] Recurrent neural network layers
- [Coding tutorial] Stacked RNNs and the Bidirectional wrapper
- [Reading] Stateful RNNs
- Language model for the Shakespeare dataset
Videos
- 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 decorator5m
- Wrap up and introduction to the programming assignment
Programming Assignment
- Residual network
Ungraded Labs
- [Coding tutorial] Model subclassing
- [Coding tutorial] Custom layers
- [Reading] The build method
- [Coding tutorial] Automatic differentiation
- [Coding tutorial] Custom training loops
- [Reading] Tracking metrics in custom training loops
- [Coding tutorial] tf.function decorator
- Residual network
Videos
- Welcome to Capstone Project
- Goodbye video
Peer Review
- Capstone Project
Ungraded Lab
- Capstone Project
Plugin
- Post-Course Survey
Instructors
Imperial College, London Frequently Asked Questions (FAQ's)
You can simply use the same steps mentioned above in the ‘admission details’ section and enrol for the TensorFlow 2 for Deep Learning Specialization.
Yes, financial assistance is available. All you have got to do is fill out your application form by mentioning the requested details, and you will be notified within 15 days.
You do not have to attend anything in person. This is an entirely online course where you can access all the required course material via the web. Moreover, you will receive an electronic certificate.
Yes, since the Customising your models with TensorFlow 2 online course is an intermediate-level course, it requires general knowledge and experience in the fields mentioned above. Additionally, this course is the second part of a three-course Specialization, which is why the completion of the first course, Getting Started with TensorFlow 2, is essential before you apply for this one.
You can get access to all the three courses in TensorFlow 2 for Deep Learning Specialization. You will also receive a certificate after you complete all the required modules in the courses and it will be added to your accomplishments page. You can print this certificate or add it to your LinkedIn account.