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.
AA
i recommend the course for anyone want to get solid foundation in TensorFlow as beginner, also capstone project cover all the content you learn in the course.
MW
Awesome course for the students who wanted to start the TensorFlow. Instructors are best, explained the topic in a simple word using appropriate practical examples.
BB
Really good practical course on image analysis with TF. Make sure you know the basics ahead as the main concepts are not explained, just put into practice.
MK
Really nice introduction to TF2. In my case, I have worked professionally with TF1 for some time, so the material was quite trivial. Nevertheless, it was still a nice refresher.
MM
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!
CP
A beautifully structured course. It does require a fair bit of preliminary knowledge in DL, but once you have that, the practical implementation in this course is on point.
GS
Working along with University PhD students is very helpful! Also, the explanations from Kevin are very detailed with good visualization (highlighted source code lines).
RD
Very good course -- explained the basics of tensorflow 2; very confident at this point that I can start developing my own tensorflow/keras applications.
DJ
Decent overview of the TensorFlow API but does get a little boring after a while. Would be nice to have some discussion of how to design models using the lecture content.
AJ
Excellent course with thorough practical exercises and most of all I love Kevin Webster teaching style.. Definitely a go to course for anyone who has some basic Deep Learning knowlegde.
HA
Excellent Course .. One of the best for practicing Tensorflow . Great content and well designed assignments ... GTA did a good job though sometimes the accent is not very clear
HC
Amazing course, one of the best so far. The course discusses the Tensorflow 2 framework in a very detailed and practical way. Thanks for the opportunity!
Showing: 20 of 188
This class is excelent for beginers to learn tf2. this class mainly talked about practice ,and it is useful to build basic deeplearning models
Decent quality content, but course doesn't seem to really be supported anymore, and it isn't noted anywhere. I just found out when I couldn't submit the final project (was able to submit everything else). This should be noted in big red letters somewhere or something in case people are looking for a certificate.
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!
Course is very well designed and very well for learning tensorflow higher level api's. Peer graded assignment was very frustrating as it will take so much time to reflect that you are passed or not. Happy Learning!!
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.
The course is really well-organized. The videos are relatively short but very clear and concise. Programming assignments are right on spot. If you already have basic knowledge of deep learning and want to get more practical experience with Tensorflow 2, this s absolutely a good resource.
Very nice introduction to tensorflow 2.0 with focus on keras. I already knew keras from tensorflow 1 so this was very useful. Still I thought this course was a little too basic for me to get a certificate. I used it as preparation for the other course ('customizing your models with tensorflow 2'). Doing this course quickly at least gives me a good background to do the second one.
There were some small errors in the course. It looks like tensorflow has adapted their APIs so that in the model checkpointing you specify the number of batches and not the number of samples. Also, there is a current bug in tensorflow 2.2.0 (and 2.3.0), that specifying {batch} in the path of the checkpoint no longer works. Also, there is another bug in tensorflow 2.3.0 that has apparently broken saving and loading of complete models using model.save() and load_model().
Going to do the second course now with the aim to get the certificate.
I think it is an absolutely incredible course for anyone who wants to make the jumpy from TF 1.x to TF 2 (or has the knowledge of Deep Learning ideas and is looking to learn the TF 2 framework to apply them). The content is planned out perfectly for learners, the tutorials and assignment introduce and understand important ideas from the tensorflow 2 framework.
Finally, the most amazing thing about this course is the Capstone project. It just strikes the perfect balance on the difficulty scale. It will keep you engaged but at the same time it will not be very difficult either. The content in the course is geared towards preparing the learner to be able to do the project with ease and it does serve as a culmination of the skills used learnt in the course.
This is a truly outstanding course that teaches you the basics of Tensorflow 2 using the Keras API. (There is a more advanced course if you want to deep dive into Tensorflow2)
One minor quirk is that instructors almost never answer questions on the forum. Nonetheless, it is worth the money spent if you plan to start designing Neural Networks with Tensorflow 2 framework.
The Capstone project is really satisfying since it gives you a lot of flexibility on how you can to complete it.
This is such an amazing course. It's very simple but accomplishes what it's supposed to accomplish. I've taken the andrew NG course for deep learning so I know the theory and this finally made me understand what I've been writing and allowed me to express some of what I think in terms of code instead of only having the theoretical model. and even more stuff that the other course didn't cover in terms of tensorflow
A good course for beginners in TF, though familiarity with deep learning is assumed. The course is up to date with TF2 API, so I had no issues implementing the excercises. The peer-reviewed project is open-ended and gives a lot of freedom to build the appropriate network architecture. The instructors are clear and overall production quality is really high.
Excellent course with thorough practical exercises and most of all I love Kevin Webster teaching style.. Definitely a go to course for anyone who has some basic Deep Learning knowlegde.
A beautifully structured course. It does require a fair bit of preliminary knowledge in DL, but once you have that, the practical implementation in this course is on point.
A great course for those who already have some knowledge of deep learning. Concepts are explained in very well way.
Well designed course, with the final Capstone project covering all the aspects involved in a MLP.
Very good course but the final peer graded review takes alot of time
Excellent course with videos and assignment.
First of all, this course is not a deep learning course but a TensorFlow2 course, so prior knowledge of deep learning is required. For example, if you don't understand what CNN (Convolutional Neural Network) is, it's recommended to take a dedicated deep learning course, such as OpenAI's, before starting this course. With that in mind, the content of this course is excellent. You will become proficient in executing what you imagine using TensorFlow2. However, there are some drawbacks. Almost every module consists of the following components: 1. Videos where the instructor explains concepts while showing code. 2. Videos where the TA (Teaching Assistant) explains concepts while coding. 3. JupyterNotebook exercises. 1 and 2 are quite redundant. Moreover, video 2 involves typing out code from scratch instead of explaining pre-written code, which makes the videos unnecessarily long. Typing out code while watching the video was quite painful. In addition, the lab's automatic grading tool was a bit unstable. Particularly, during the second week's auto-grading, it would fail when the lab was working correctly, and pass when errors occurred while coding as per the instructions on the lab. Additionally, there were issues with the peer review assignment, as attempting to generate a PDF as instructed resulted in a server-side error, preventing the output. I downloaded the Jupyter project and struggled to generate a PDF from my local JupyterLab.
The course material is fine but the peer review thing must really be get rid of. I don't wanna see the discussion forum filled with people begging for reviews.
Something seemed off with the course, there was a quiz that covered information I'd never seen in the videos. They breezed right through very important foundational concepts, assuming you already knew about them.