Chevron Left
Back to Customising your models with TensorFlow 2

Learner Reviews & Feedback for Customising your models with TensorFlow 2 by Imperial College London

4.8
stars
188 ratings

About the Course

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....

Top reviews

JF

Mar 7, 2024

Capstone Project was surprisingly difficult, but your hard work on it is a real confidence builder. Incredibly well-made course that gets you working "hands on" w/o time spent on hours of theory.

NN

Jul 23, 2022

I love the way the course is constructed. Every concept is tested in a lab and you have a well organized assignment in the end of each week. Great course. I learned a lot.

Filter by:

51 - 73 of 73 Reviews for Customising your models with TensorFlow 2

By akshaykiranjose

•

Jun 22, 2022

bravissimo, a really good intro to advanced TF

By GCCC

•

Dec 29, 2023

Outdated Tensorflow version and not updated

By Dmytro K

•

Dec 8, 2023

One of the best courses for Deep Learning

By S. A

•

Dec 2, 2022

well paced guided path through a lowerful

By Gustavo X A M

•

Feb 22, 2021

Great experience, excellent material....

By Ragul N

•

Jan 11, 2021

Assignments were challenging but doable.

By Meng O L

•

Feb 24, 2021

Excellent! Good learning material

By Jeffrey B

•

Jan 27, 2021

Great course, I learned a lot!

By Jac G

•

May 25, 2021

Dr. Kevin Webster thank you.

By Javier G

•

Sep 15, 2021

A challenging course!!

By Ho P D

•

Jun 30, 2021

Nice and comprehensive

By Aleksander M

•

Oct 26, 2020

Amazing course!

By Marios K

•

Nov 20, 2020

Nice course :)

By Nguyen B L

•

Apr 23, 2021

Great course

By Diego A A R

•

Apr 8, 2021

Very usefull

By Natthakorn K

•

Sep 10, 2021

Great!

By Ernest W

•

Apr 21, 2023

The course would be better if the concepts behind Recurrent Neural Networks were better explained. It's difficult to figure out what's going on just through code.

I guess everything that should be covered about functional and subclass API was there.

The final assignment was a challenge! - that's good.

By YU B

•

May 8, 2023

Capstone project is quite a steep learning curve for me, and honestly, pretty difficult.

By Rob S

•

Oct 22, 2020

Interesting course. However, I didn't find the videos as clear as Course 1.

By Anup K

•

Jun 10, 2021

Excellent Course .. but with difficult passing levels.

By Shaokai Z

•

May 16, 2022

The content of the instructions seems unstructued. The introduction of every lessons lasts only a few minuts. The coding tutorials offered by the GTAs are neither insightful nor explanatory, where the learners are simply required to type along. Theere are also consistency issues the way the code, so that many manners can be confusing for beginners.

The assignments are not designed with the resources in mind in that, some of them require an increadibly long time to train, unless it's migrated into colab, where other issues like loading pretrained models and datasets need to be taken care of. Also, the instructions are at times vague, and the problems can only be seen once graded. No or not enough efforts were made for step by step checks and guides to help the student.

Personally, I would recommend the deep learning specialization from deeplearning.ai, which is organized way better.

By Max K

•

Jan 31, 2021

Never recieved my grade. Contacted coursera support. They demanded another motnh of payment for the course or else I will not get my grade. Terrible practice and this is used to punish people that finish their course early since coursera will simply wait until you pay another month before the start grading your paper!

By Jaesub S

•

Mar 30, 2021

The course is not maintained. Do not waste your money. Many of the assignments are impossible to finish due to the broken grader and lack of support.