The course itsel is a very good introduction how to use Tensorflow models in browser. It will suit well for people with basic JS and ML knowledge. The assignments and projects are quite fun. However there are things to improve:

1) A few questions in quiz are syntax-related and boring. It is absolutelly not fun trying to find difference in bracket or comma

2) Most of the assignments are very similar to the examples, a lot of them could be solved with mere copy-paste without real understanding

3) Final project crashes on Windows if number of samples are > 50. Very frustrating, especially when you collected almost all the samples

In this course you'll learn how to train and deploy ML model straight in JavaScript, instead of Pythhon e.g. This is helpful for when you want to avoid back-end calls to Python e.g. when building web applications. For small applications, this is great. You also learn how to train the model in Python, and then import it in JS making inferences.

Format is perfect: short videos, assignments are a handfull, especially the last one. The code you'll get is a great reference for later on.

Do note: Javascript is pretty much prerequisite.

Exercises in this course are on the monkey level.

When I took this course, I was already familiar with deep learning in Python, but this course helps me a lot to grab the concepts of javascript and using javascript to train the models on the webserver and also helped in the making of some cool project and more cool project ideas. Much Appreciated. Can't wait to do the rest of the courses.

Awesome - elegant in its complex simplicity. Clear explanations, logical curriculum structure, nice and knowledgeable code examples. A must-complete course indeed!

A lot of explanation of obvious things. Also, excercises are low quality, with Week 3 and 4 quite hard to pass because of technical issues. Week 3 - need specific versions of the libraries, which are not provided, without which "the model is invalid". Week 4 - quite hard to collect training samples for the model to reach required accuracy, since the app crashes after ~200 examples and wipes them out - you have to start again.

Excellent Course, I have fun !!! implementing the projects, I also enjoy the format with the labs where you need to apply some modifications to what was taught to get an entirely new project, It demonstrates the capabilities of tensorflow and modularized code. Thanks to everyone that worked on this Course, now to the next one.

A great course to learn how to leverage python tensorflow/keras API with Javascript. Also very nice to be able to build a real Web App, in addition of the typical Data Science process. This is handy to showcase the value of Data Science and Deep Learning for real life scenario.

The lecture content is clear, the quizz are not very interesting, and the assignments mostly are copy paste of the exercises, so not much challenge there.

I give 5 starts because despite all that the example applications are really cool!!

The intent to teach DL application in the browser is well scoped. I would suggest more background reading including fundamentals and articles outlining state of the art (challenges and approaches - successful and not), and then additional reference material surrounding related areas such as execution on the edge device. But nothing should excuse coursera or the teachers from technical difficulty experienced by many (dozens of students) with grading. Who is at fault? You wasted my time. And you let dozens of students collide head-on without warning into this problem. You should, at the very least admit to your failure and more importantly compensate me one full course at no charge. Without compensation, i see no reason to trust you. Equally important, Coursera is an off-line teach ing system. I make mistakes. I get so little feedback, your system blocks my learning. There is incredible value in learning what not to do. Again, you need to fix this across all courses - and this goes for all such platforms. Thank you, there is some value in taking a course - we all want more

Not for the impatient.

3rd and 4th week assignments are quite problematic:

3rd week is heavily dependent on python and libraries versions in user's environment and the course does not point which combination is the one which will be graded correctly. Took me 3 long debugging sessions to finally find the right one.

4th week involves taking had photos to get some gesture recognition. I've spent over an hour with constantly crashing web browser and different cameras to get it right.

Although the skills that can be learned in this course can be really useful, the unnecessary hardships prevent me from recommending it to anyone.

Very insightful and helpful course for front end web developers who want to get started with deep learning through TensorFlow. Quizzes and assignments are up to to the mark as well. Can learn a lot through this course. Also pretty good for people who want to learn about transfer learning. That is what grabbed my attention to the course in the first place itself.

After spending more than a year learning Machine Learning and Deep Learning, now i'm finally able to deploy my models in very simple and efficient way, which will help me tackle my next professional challenge, which is deploying my internship models using Tensorflow.js !

The course was neat and clear in terms of details on Tensorflow JS. A bit more details on what are the practical area where this is used at the moment could have been useful. But of course, we can find it on our own. :)

No doubt, the team of Deeplearning.AI is building best learning resources. We would love to get more and more resources for easy way learning from DeepLearning.AI Team.

Thanks to all.

I have worked with tensorflow for some time, but I didn't know it is this straight forward to deploy on browser.Very good explanation with examples of different deployment options

I thoroughly enjoyed this course and also the programming assignments. It would have been better if the machine requirement for the final assignment was already informed in advance. My humble laptop was not able to execute it and was giving memory error. Fortunately I could borrow a friend's laptop with Nvidia graphic card and could finally finish it. Got to learn a lot! Thanks for developing this course.

update the course, why do even we need to use the past version of tensorflow, while the newest one can still running for the assignment

it is very exhausting to pass the tests due to hardware and software prblems, though the programming is very easy

So many technical issues!

90% of the time I dealt with technical issues such as make the web server run my code.

The course itself was very short and easy.

The course content is very good but the instructions on how to install Tensorflow 2.0 and Tensorflow.js in python 3 are not clear.

The assignment system was sooo frustrating and wasting my time. Please fix it..

A very well structured course with many concepts clearly described and elaborated. Laurence explains the topics very well and is one of the best instructors to share complex concepts in an easy to understand way.

Room for Improvements: The grading mechanisms for weekly exercises can be confusing and difficult to understand why a submission failed. Seems a lot of TensorflowJS and TensorFlow version specific dependencies. Be careful!

I have been waiting for a course like this! Great course, IF you have background in both machine learning and javascript/Web Development. I am training to be a Data Science Application Developer which combines my education as a data scientist and my experience as a web developer. This is the BEST course I have taken on Coursera! And to see Andrew Ng voicing his support for TensorFlow.js is just AWESOME!

I was really struggling how to implement my model in a web interface and this course made it so easy. I came to know about TensorFlow Javascript library which can easily convert the model for use in javascript and we can use our models in a web browser. Thank You for making this course easy and fun. All credits to DeepLearning.AI team.