The course was amazing, but the thing i don't get it is the 'sparse_categorical_crossentropy' must be use in the last exercise notebook. In the video(s) ,Laurence introduced only 'categorical_crossentropy', hope somebody could upgrade the notebook to suitable the lessons. Tks.

'

Really good course, but recommend doing deeplerning specialization first before doing this one or doing them together. Because Andrew Ng explains really well how convolutions work, and without this background info, it will be difficult to understand the concepts in this course.

Really impressed by the work of the team. It is designed specially for the beginner to advance their career and be expert the emerging AI field. With the help of high quality videos and project based assignment one become expert hoe to deal and tackle real world problems.

What an amazing set of courses. Full practical and to point. No time wastage. Believe me if are interested in any course and DeepLearning.ai has it then blindly just enrolled in it as they have the best courses in the coursera platform. Thank you Laurence and Andrew Ng.

It was easy to follow up all the lesson because of the way the course has been structured. I even tried in other places to learn tensorflow but i was not able to continue after few days. but this structured course was the best. I am confident about the knowledge i got.

Excellent. I learned after a couple of years working with neural networks new topics and implementations. I think it would be a good idea to include also here an exercise that gets graded at the end such that we take our time and can try out if we can make things work.

The week 1 is a bit casual but where as the remaining one's are just awesome learnt a lot like how to implement a model without overfiting and learnt how to implement transfer learning and multi-class classification problem, really worthy taking up this course....!!!

I recently completed a Convolutional Neural Networks course in TensorFlow, and it exceeded my expectations in every way. The course provided a comprehensive and hands-on learning experience that significantly enhanced my understanding of CNNs and their applications.

This course is for beginners and intermediate, If you know the detail of the model layer then don't take this course. The instructor only tells the code who to add Conv, pool max layers in TensorFlow do not explain the depth of convolution and pooling layers.

This was a really great course for me to dive into practising the implementation of machine learning for image datasets. The instructor is really nice. I thoroughly enjoyed the course and will be taking more courses on applied machine learning from Laurence.

The course was nicely built on the advanced topics of multi-class classification, data-augmentation, and transfer learning in Convolutional Neural Networks. Special congratulations to the instructor and his team for coming up with such a nice course.

The course was excellent. Other than the (typical by now) Coursera code-submission issues, the course really covers a broader range of CV applications & TF capabilities than I've seen with the "get it working and move on" workflow at the day job.

Thank you very much for this course, it helped me understand data augumentation and transfer learning. I am very inspired seeing computer graphic generated training data. It would be great having a separate course/workshop covering this topic.

This is very well structured course for geeks who want to start learning machine leaning and implement different neural networks are hiking the technology world.

I personally appreciate the course material and instructor for the immense work.

Thank you for teaching me this outstanding course I learned a lot about Convolutional Neural Networks. The programming assignment were also at the right difficulty not too hard and not too easy. The quizzes were easy but really awesome.

Thanks

An excellent learning platform during Covd-19 pandemic. I appreciate the effort of the Coursera team who provide us such an amazing learning environment. This course really helps me to improve my practical knowledge of CNN.

Thanks Coursera.

This lectures are givin a very nice advices for practical implementation of ConvNets. combining it with prof.Andrew Ng's lecture exercises in this course will allow you much more practi implementation of knowledge you have acquired before.

The course in general is pretty good, only the last test seems to me that is incorrect, since there are 24 different classes, but doesn't approve it when you set it with these 24. It requires from you to put 26 when to me seems illogical.

I found the course really interesting and I learned a lot. The thing I liked the most about this course is the minimal helping nature of the evaluative notebooks, deep learning specialisation's notebooks practically spoon-fed the answers.

The practical aspect of this course is addicting. I can't stop myself from wanted to try the next technique. maybe because i have seen most of these before but i going had made it clear what i was doing wrong in some of my "failed kaggle"

I enjoy the lectures. The professor has a good speaking and teaching style which keeps me interested. Lots of concrete math examples which make it easier to understand. Very good slides which are well formulated and easy to understand

Excellent course, in particular, all explanations to work with the Image Augmentation libraries, I enjoined the transfer learning part, highly recommended for anyone looking to improve their knowledge of Convolutional Neural Networks

This course is really really challengging until I have to repeat 16 times . But because i try, try and try i can finish this course.However is late, but i want to do for study and learning more to the Data Science and Data Analyst.

It is a great course to learn about Convolutional Neural Networks, exploring how to use them with large datasets, Augmentation, Dropouts, Regularization and Transfer learning, and coding during binary or multi-class classification.

Deeplearning.AI allows me to explore more about CNN. Using CNN and Tensorflow, I can build a model in just few lines of code. This library really helps me to overcome the problems in Machine Learning, especially in Computer Vision.