Bringing a machine learning model into the real world involves a lot more than just modeling. This Specialization will teach you how to navigate various deployment scenarios and use data more effectively to train your model.
This second course teaches you how to run your machine learning models in mobile applications. You’ll learn how to prepare models for a lower-powered, battery-operated devices, then execute models on both Android and iOS platforms. Finally, you’ll explore how to deploy on embedded systems using TensorFlow on Raspberry Pi and microcontrollers. This Specialization builds upon our TensorFlow in Practice Specialization. If you are new to TensorFlow, we recommend that you take the TensorFlow in Practice Specialization first. To develop a deeper, foundational understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.
AC
The course was a good one from the instructor. Could have made it more interesting. But anyways a good starter course for anyone.
BS
Really informative course on tf lite for beginners like me, it has given serious thoughts about the EDGEML field and opportunities , thanks coursera and deeplearning.ai for this kind of courses.
RS
Just one recommendation, may be an exercise on a NLP Model deployment (Text or audio) could have been added rather than all 3 examples of computer vision
FL
Same as the previous course of this specialization:The assignments are not very challenging. But the exercises are really cool!!
SK
Laurence is a good teacher. His explanations are clear and to the point. This is a one of the best sources to learn how to deploy ML models on devices
TE
Well delivered and very interesting course. The code examples and walkthroughs are amazing and help to get you trying this stuff yourself quickly.
JC
One of the most useful and exciting courses I've ever done! Especially for the information available in the last (4th) week. Very interesting material and full of practical potential!
AA
Was a great course.Had some hands on experience on codes using Gcollabs.Additionally helped me complete my project of deploying ML on android.
JU
Good introduction into getting TensorFlow models up and running on different platforms from microcontrollers, raspberry PI through to IOS and Android
AM
Very well presented and structured course format. It really provides strong introductory foundations for a journey in Deep Learning AI.
PS
I am glad I did this course to learn about exciting options to run Tensorflow on a variety of devices. I am thinking about Raspberry Pi and iOS devices in particular
ME
Great course to teach a non-technical, non-cse person, with all basics to implement and use the AI models with all android, iOS and Raspberry devices.
显示：20/111
The topic is very interesting but the way the course is delivered is a bit disappointing. I really loved the TensorFlow in Practice specialization and the first course of the TensorFlow Data and Deployment delivered by M. Moroney. This course is not at all at their level. In addition, I'd prefer to have hands-on mandatory assignments than mere quizzes
Just one recommendation, may be an exercise on a NLP Model deployment (Text or audio) could have been added rather than all 3 examples of computer vision
This course is good as overview - theoretical. You go through all the important topics - principles of tensorflow lite, android deployment, apple deployment, microcontrolers deployment. But unfortunately all you need is to watch. No exercises you would really need to do in order to complete the course. I mean, it is explained well but i would not call it 'course' rather 'presentation'. I dont feel i gained real competence. At least i know the theory and what are the possibilities.
There is just too much within this course and I think it should be splitted at least within Embedded applications and Mobile applications: rarely is a person interested in both fields. The quantity of the contents makes the course dispersive and topics almost uncorrelated. After succeeding in the course you do not feel you acquired any new skill but you just discovered that Tensorflow Lite exists. However I do not think one will be able to use this in practice after this course.
Please take care of the walk-through of this and the previous course: the quality of those videos is so bad that the code in it is unreadable. External slides (with text content that can be copied and pasted) would be a strong plus of this course as well as for the others.
excellent course with practical examples on using TensorFlow Lite on Raspberry, Android and iOS
A great course to learn how to implement any Deep Learning models on edge devices.
Amazing introduction course to Tensorflow models deployment on different devices.
great!!!exactly what i want for my undergrad thesis application
exceptionally brilliant work
Awesome. I learned a lot
While I like the approach to cover multiple platforms and consequently the need of availability of them to course participants, it's a pity that hand-on practice now is optional and not part of the assignments. An option maybe would be that participants choose one platform (e.g. iOS, Android, Raspbian) and than follow the course a bit more deeply and hands-on on that particular platform.
This course is an excellent introduction to TFlite and how Tensorflow can be deployed on mobile and edge device like raspberry pi. From all the Tensorflow specialization so far I found it the most difficult as it requires advanced knowledge on app development, even though not mandatory to validate the course. It shows well however the value and use case of bringing tensorflow to those device. I think that one of the greatest difficulty with TFlite is that we are switching to "3rd party" ecosystem, that requires important effort to convert interfaces of the different worlds, aka tensorflow "python" ecosystem to Android/IOS ecosystems. This is anyway great material that bring incredible value to path the way for inferencing at the edge.
Muy buen curso, las semana 2 y 3 se me hicieron más difíciles porque están orientadas a Android e iOS, de los cuales no tengo experiencia. Pero están muy bien explicadas. ¡Lo disfruté!
Very good course, weeks 2 and 3 were more difficult for me because they are oriented to Android and iOS, of which I have no experience. But they are very well explained. Enjoy it!
It was a great introductin to diff application fo TF models and how to deploy them acctually I enjoyed the first course more as I had already done some web development. so ya it's a useful course if you have completed TF in practise and basics of deep and machine learning this is a great way to start deploying your model using just single Tech TF.
I love the learning, before enrolling the course I wish to learn about how the models actually deploy in production but by this course I will get to learn many things with ML model deployment on Mobile devices as well as on low power devices such as Raspberry Pi and wish to learn on Micro controller as well
really good for developers simple and basic, it's also hard for a machine learning engineer to get 100% of these codes, but as for teams working on a project it takes a less effort to create a great product with this course, also loved how you didn't force us to code in other languages .
A really interesting course by deeplearning.ai. Although I would say that the course was very introductory and easy, I cannot neglect the fact that it taught me a lot of stuff on how to deploy "small" models on devices. Surely a great place to start with deploying models on devices! :)
The course material was well-organized and the hands-on assignments were challenging but achievable. I especially appreciated the real-world examples provided throughout the course, which helped me to better understand how to apply the concepts in practice.
Though I am not into app development, this course gave me useful insight into how to get things done in the real world. The most useful part was the fourth week for me. Just the things I anticipated. A really great course for ML enthusiasts.
One of the best courses I've taken. I've always worked on projects using Tensorflow models on a desktop or a laptop. This course opened new possibilities for me, and I'm now eager to develop AI applications on my smartphone and Raspberry Pi.