Good intro course, but google colab assignments need to be improved. And submitting a jupyter notebook was much more easier, why would I want to login to my google account to be a part of this course?
Great course to get started with building Convolutional Neural Networks in Keras for building Image Classifiers. This is probably the best way to get beginners into Deep Learning for Computer Vision.
创建者 Arkady T•
It take some time to change the code and run examples from this course with TensorFlow 2.0 locally on my computer. Today TF 2.0 is state of the art and required in practice. Please rewrite code for TensorFlow 2.0
创建者 Kumar N S•
More or less the course takes on Tensorflow's implementation of Keras rather than Tensorflow native env. It also only focuses on computer vision domain. Kind of misleading course title.
创建者 yuan j•
Learn a lot of tensorflow basics, which is good. However, the course is very short and easy to complete, and I cannot apply the neural network learned in this course to actual work
创建者 Guillaume G•
Ce cours balaye les fonctions de bases de la librairie d'abstraction Keras et permet de construire rapidement des réseaux de neurones complexes.
创建者 Rudresh M•
When each layer visualization was taught, I didnt get that part nor in the program. Else its a great starter course
创建者 Lu A•
It's relatively simple course if you've already finished Andrew Ng's deep learning specialization
创建者 Bhabani D•
Great introductory course to learn the application of TensorFlow with Keras.
Great course, but can be completed shortly instead of many weeks session
创建者 Hakesh K•
Amazing way of putting all the stuff together
创建者 Muthiah A•
Useful start for practitioner.
创建者 Rushikesh W•
Good practice for coding on tf
创建者 Henrik R•
The course is ok-ish, as are all the other courses in the specialization. This review is for all the courses in the specialization. I have a general shallow overview of DL but wanted to learn about TensorFlow and about Keras. For this it provides a good overview. You could learn it from tutorials too but at least I benefit from taking a course, as it motivates me to finish. But, the material is very shallow and it is a shame that there are close to no graded exercises. The quizzes are super easy. And there is no capstone project. If I didn't know the basics before I probably wouldn't have understood anything. If you know a bit of DL beforehand you can easily take one course per day. The fact that earning the certificates unfortunately degrades the value of it. If you finish in a month (and therefore only pay for a month) I think it is worth the price, even if what you learn is not that deep.
创建者 thomas y•
I get that this is a separate course from Ng's deep learning course, but I found the lack of theory (or even recommendations of best practices) disturbing. Additionally, I thought the videos were way too short and would have appreciated it if they had gone into detail into each Keras method used, the parameters for it, etc. For example, on the last assignment we were supposed to use a callback on accuracy to end training, but nowhere in the videos did it mention how fit_generator() handles callbacks as opposed to how they were handled with fit().
Lastly, and most importantly, this course was advertised to be a course on Tensorflow. However, this is not the case. This is a course on Keras; Tensorflow's API. If you came here looking for how to implement a DL algorithm from scratch in TF, this is not the course for you (or me apparently).
创建者 Ivan N•
I think this is a great way to introduce NN to people that have never seen one.
But there was very little depth in this course. I finished the 4 weeks in an afternoon. The external references were at times way too advanced, while the exercise code was way too simple. That being said, the Jupyter notebooks were a great material and helped me start with NN really quickly. The MNIST dataset is brilliant and hank you for showing how to do it.
The reason why I gave 3 stars is because the MOOCs aI have done in the past were much more extensive and gave plenty of theoretical background. Some people might think that the lack of theory lowers the entry bar for students, but in my book that's a tutorial not a course.
Save yourself the $40 price tag and buy a book on the topic, there are plenty out there.
创建者 Alon L•
Material is very well explained and very relevant but the course is short in comparison to other deeplearning.ai courses before and could be richer both in content and in exercises (which are also not graded)
创建者 Rui P•
Instructors, please take a look at the discussion forum and answer some questions. It would save students a lot of time. The content of the course was overall awesome though.
创建者 Xiangzhen Z•
Each video is a bit too short. And the assingment can't be smoothly finished and submitted due to environment issue. The creator should try to improve the user experience.
创建者 Volodymyr L•
A very basic course, but it doesn't give you any fundamentals - just gives you a chance to recall keras API better. You'll be much better off doing cs231n, which is free!
创建者 Aniket C•
The notebooks do not provide enough information about what block implements what. A simple comment that implement custom callback here would have made things lot easier.
创建者 Ranjan D•
The course was good enough on the high-level perspective but was expecting pure TensorFlow based implementation of the models instead of using the Keras high-level API.
创建者 Roger G A•
The course was very basic but interesting. However, there were some issues when submitting the assignments. And the virtual lab uses tensorflow 1.x instead of 2.x
创建者 Baurjan S•
It's very introductory and the knowledge may not stick. I think it is more beneficial to take a full deep learning course with TF as an add-on to the course.
创建者 Desiré D W•
Great content, excellent explanations.
But I couldn't run the notebooks without running into kernel issues, the programming assignments were a real hassle.
创建者 Philip D•
Decent enough but much too abbreviated and lacking the depth I expected from a deeplearning.ai course after taking their deep learning specialization.
创建者 Harmanpreet S•
Could have been a more elaborated course. This course mostly talks about how Keras functionality has been adopted by high-level APIs in Tensorflow.