Chevron Left
Getting started with TensorFlow 2 に戻る

インペリアル・カレッジ・ロンドン(Imperial College London) による Getting started with TensorFlow 2 の受講者のレビューおよびフィードバック



Welcome to this course on Getting started with TensorFlow 2! In this course you will learn a complete end-to-end workflow for developing deep learning models with Tensorflow, from building, training, evaluating and predicting with models using the Sequential API, validating your models and including regularisation, implementing callbacks, and saving and loading 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 an image classifier deep learning 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 is intended for both users who are completely new to Tensorflow, as well as users with experience in Tensorflow 1.x. The 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/feedforward and convolutional neural networks), activation functions, output layers, and optimisation....




I already knew the subject, so I was able to go fast, but I really loved the completeness of this course, the approach, the tests, and the capstone project. Basically everything. Very good indeed!



Provided clear and useful insight into TensorFlow 2. Before the course I had read many of the TF2 guides and tutorials. This course helped solidify my understanding of core TF concepts.


Getting started with TensorFlow 2: 26 - 50 / 157 レビュー

by Baskar


Well defined course. I got a very good experience. well planned handson session. Thank You

by Lim G


Provides detailed coverage of tensorflow 2's fundamentals. Thoroughly enjoyed the course.



An excellent course for those who want to learn how to implement tensorflow2.0

by Deep M


The best course if you want to get started with Tensorflow 2.0

by 101chsu


It provides a systematic way for me to learn TensorFlow 2.



It is an excellent course for beginners in Tensorflow

by Ishan M


Excellent course for getting started with Tensorflow.



Loved the course. Really practical and hands-on.

by Santiago G


Thanks for all, really useful course!

by Diego A A R


Very clear and well organized.

by Sean M


Awesome course. Learnt a lot

by Charles J


Great overview of TF2

by Shaik S


Great course.

by Sina A N


Good beginner

by Ikaro S


FYI This uses tensorflow 2.0 would be nice to have an updated version for 2.4>

by Nana O


Awesome content, I learned A LOT from this course but encountered numerous technical issues with the Capstone project -- including not being able to generate the PDF via the instructions.

by Michael D


The perfect course to follow up the Deep Learning Specialization. I left that specialization feeling like I had an acceptable academic understanding of deep learning, but that I would be unable to apply it in practice. This course was great for solidifying that pragmatic component.

I read some of the most helpful comments before starting and one of the biggest frustrations was the auto-grader failing. That was not my experience at all. As of this post (5/2021) the grading system worked completely fine for me via Coursera's notebook system.

A concern among other TF specializations was that they did not provide any information that could not be gained outside the doc examples. For this first course, at least, I found the material well exceeded the explanations in the TensorFlow/Keras docs in terms of quality. The labs were very thoughtfully structured and provided the right amount of application to cement the concepts mentally.

tldr found this course to be very worth the time and money

by Мартынов А А


This is just a wonderful course!

Previously I've taken well-kown Machine Learning course and Deep Learning specialization by Andrew Ng. After completing these courses, I had the feeling that I had received a good knowledge of the theoretical aspects of Machine and Deep Learning, but I had no understanding of how to make some even simple models from start to finish (I am not criticizing these courses, most likely the problem is in me).

And this course was a real godsend for me. This course is completely dedicated to practice, this is exactly what I needed. The information presented in it is absolutely clear and contains everything you need to complete programming tasks and to start the independent development of simple models in tensorflow.

No doubt, 5 stars!

by Felipe C


I really liked this course. The pace is very good. The focus is also great.

The final project (Capstone Project) is really good practice, I'm not super experienced in ML so doing a kind of "real world hands on project" fell great, even if I spent a lot of time doing it (I made an initial wrong assumption about the data structure which made the model trainings take forever).

You are going to need to know about Python and Numpy, maybe a little Pandas too.

My only constructive criticism would be that it would be great if you got a good mic… these makes videos much more pleasurable. Audio isn't great.

by p.w.ouwehand


Excellent course on the Keras API of TensorFlow 2 for those who already know about fully connected and convolutional neural nets. If you don't have that background just yet, I recommend the first four courses of DeepLearning.AI's Deep Learning Specialization for a good introduction.

The "Getting Started with TensorFlow 2" is a step up in technical difficulty, and you'll be able to construct your own neural networks with ease and speed once you've completed this course.

by Tse-Shao C


This is an excellent course teaching you how to use Tensorflow 2 from scratch with step-by-step instruction. They provide just enough knowledge you should have for starting using TensorFlow 2. To start this course, you should have some basic understanding of deep learning since they assume you already know these. I enjoy learning from this group. I highly recommend it. Denefinally, take the second course - Customising your models with TensorFlow 2.

by Alejandro D G


Great practical course: if you have previous understanding of the Deep Learning models (for this course, multi layer perceptrons and convolutional neural network, for which I recommend to do before the Deep Learning specialization from this course is very good for learning the practical implementations in the tensorflow2's sequential API. Great programming materials, videos and exercises.

by Mark N


I absolutely enjoyed this course. I liked the mix of lecture and TA/mentor time, the exercises done alongside our TAs/mentors were extremely instructive and helpful. The textbook recommendations were great. The weekly exercises were well-designed. I highly recommend this course, and I am looking forward to our next course in the sequence. Thank you for putting together such a fine class.

by Feng J


This is one of the best course I have taken in coursera !!! The course is very well designed. I have learned a lot about the sequential model in tf2.0, I also build the deep learning model by myself through the practice in this courser. And finally gather all of the knowledge in the final capstone project. I look the video lectures again after one month time, and understand it more clearly.

by Maxim V


Initially I wanted to do only Probabilistic DL (3rd course) because this material is not taught anywhere else as far as I am aware, but I learned quite a bit from other two courses as well even though I thought I knew the material. The entire specialisation is highly recommended, very good quality and very relevant content. The best of 2020 on Coursera, in my estimation.