Great course for kickoff into the world of CNN's. Gives a nice overview of existing architectures and certain applications of CNN's as well as giving some solid background in how they work internally.
I really enjoyed this course, it would be awesome to see al least one training example using GPU (maybe in Google Colab since not everyone owns one) so we could train the deepest networks from scratch
創建者 Edgar A G A•
The course is amazing and the topics are quite interesting. I think the explanation about the YOLO algorithm could be slightly better (I have to check out some external resources to catch the idea). Some programming assignments were hard to accomplish due to a lack of clarity about how to use TF. Nevertheless, all the topics covered along the course were really interesting. Thank you!
創建者 Pedro T B•
Amazing course, with careful explanations and intuitions for every algorithm. Beyond explaining greatly what are Convolutional Neural Networks, the course uses recent research papers to go through high level algorithms for face recognition and presented really nice applications such as Neural Style Transfer. I'd like to really thank the instructors for delivering this amazing course.
創建者 Victor A M B•
Es un curso que te enseña los fundamentos, técnicas y variaciones de las CovNets (Redes Neuronales con Convoluciones). Este curso es bastante bueno para introducirse en el mundo del análisis de imágenes y otros campos que utilicen datos no estructurados. Muy recomendado el curso, pero vean primeros los otros cursos de esta especialización para que pueden entender mejor los conceptos.
創建者 Jason J D•
Another wonderful course in this specialization. The course covers many important topics in the field of Deep Learning such as CNN architecture and models, ResNets, Object Detection, Face Recognition, Neural Style Transfer and even a tutorial on the popular DL library Keras. The programming exercises and fun to complete and the course content is top-notch as always from Prof. Andrew.
創建者 Pablo G G•
Awesome CNNs course! I don't know why so many bad reviews, the grader doesn't fail if you follow the instructions (grade your assigment when you are asked!...tensorflow can only run one session so if you try to overwrite your model session with the teacher example session, grader will fail...tensorflow fault not this course) Would have love some GAN Week 5 Neural Style Generation :D
創建者 Sriram V•
Programming exercises need to made really with right structure as the YOLO one was very poor. Problems are very easy and makes this course very simple. We need to incorporate right amount of programming along with concepts, make it tough and train us also really well in the ideas. Concepts are absolutely fine, it takes the slow pace to make us understand deeper ideas and intuitions.
創建者 Nelson F A•
Excellent course with many hands on examples and filled with important resources on CNN architectures and other best practices. There are many optional reading material that I'm sure to come back too. The only thing missing was a little more insight on backpropagation on CNNs, although an example of it is given in a coding example. This is a course I will be coming back to for sure!
創建者 Ashutosh K•
The best part about the course is the focus on understanding the basics. It takes time and effort to learn and follow through the lectures but once you understand the basics clearly, everything else becomes so much easy to understand. Not like some of the courses out there which push you into advanced coding from day 1 and then move backwards to basics, this course is so much better
創建者 Tamim-Ul-Haq M•
Really amazing and in-depth course. There is no better course than this to uncover the secrets of Deep Learning in the field of Computer Vision and how to easily utilize, improve and develop these systems. I am truly impressed by the content and by the knowledge I have gained and I doubt any university or other course can match up to Andrew's level of knowledge and teaching method.
創建者 Samuel Y•
This course was awesome -- albeit pretty hard. I understood most of the concepts when learning them, but it was easy to forget a lot of the implementational details and such. Dr. Ng does such a good job, nevertheless, both presenting the material (which is straight out of cutting-edge papers) and also offering tips for actual implementation. I plan to make an app after this course.
創建者 Quentin G•
Cours très intéressant et d'un niveau bien supérieur aux 3 modules précédents. J'ai vraiment du réfléchir sur de nombreux exercices de programmation pour arriver à mes fins. Merci beaucoup !
Very interesting courses. The difficulty level is very higher than the 3 previous courses. I really had to think everything twice on the programming assignments before submitting. Thanks a lot !
創建者 Rex F•
i can't believe i learned so much, can read complex equations and translate them .. it's like a condensed math specialty mixed with learning real-world utilities and tools .. hey, i know from this course how to quickly and (almost) effortlessly prototype recurrent and other deep networks, how cool is that? because of this course i also became a contributor to Keras! yay for me :)
創建者 Roman V•
I have become a great fun of deeplearning.ai and Andrew Ng. Thanks a lot of great high quality materials. Going through the specialization I'm falling in love with Deep Learning. I believe historically, deep learning, and especially ConvNets related papers are usually pretty hard to comprehend by simply reading them. This course made it so much more simpler, it is unbelievable.
創建者 Jamie K•
Lots of new concepts in this course. I liked the literature review sections and the fact that Andrew starts to show you when it makes sense to pull someone else's model down and use that rather than building something from scratch. The programming exercises were also pretty good - I had to think in a number of places though they are still a little too structured for my liking.
創建者 Najeeb K•
A great course providing in-depth theoretical understanding of Convolutional Neural Networks and state of the art model architectures for various Computer Vision tasks. I have been doing Machine Learning from past one and a half years but the course content still gave me wealth of knowledge in a structured format that I yearned for so long. Thanks Prof Andrew and the team! :)
創建者 Antony A•
best course in world or unvierse to understand the basics and complex details of convolutional neural network .i would give an oscar for this course . I was so woried about the complex diagrams that i saw in internet about CNN but this course made it look very easy i was totally suprised how complex details were explained in simple manner .I would recommend this to everone .
創建者 Manjit P•
This course covers lot more material and it is more application oriented compared to last three courses. I had to spend lot more time and effort for this one. Also, there are some bugs during submission of the assignments. There is enough discussion about those but I hope Coursera takes care of those in the near future. Nevertheless, I always enjoy Prof. Ng's lucid lectures.
創建者 Utkarsh M•
This course was something different. Earlier when I started The Deep Learning Specialization, I was not interested in any particular application of Deep Learning, but this course gave developed interest in CNNs, so much so I'm seriously considering and planning to pursue my master's in Data Science. I wanna thank Andrew Ng for such great lectures, he has truly inspired me.
創建者 Yash M B•
This course has given me everything that one can expect to learn from the field of Image processing models like CNNs, Deep Convolutional Models like Inception, VGG-16, VGG-19, ResNets, etc. Other topics were also learned that included me applying these concepts into real-world applications like the neural style transfer as well as the object detection and face recognition.
The teaching style of Dr Ng is excellent as usual. He is able to take a complex topic and make it easy to understand. I found this course more challenging than the others in this specialization. It does require a bit of tenacity in order to finish the assignments. This is usual when coding. So don't give up and be sure to search the discussion forum when you hit a barrier.
I am really appreciating this specialization. The only thing that I would change is maybe focusing less on the matricial operations required e.g. in the loss function computation, and more on how to use Keras/TF at a higher level; at the moment, it would still take me a lot of time figuring out how to build a nn from scratch, or use an existing one, with these frameworks.
創建者 Erman N•
This course is amazing. I strongly recommend everyone willing to build a career in machine learning to start here. I was really skeptical at the beginning. As a Ph.D. student in the computer vision field, I was looking for a course that can simply explain the science behind most AI courses. Now, I can say Andrew nail it, the course was far beyond my expectations. Thanks
創建者 Esteban C•
Very good in-depth coverage of conv NN.
Just one little thing, week 4 Notebook assignments:
In style transfer code is not well explained how the train is actually working. In this case the input is set as a Variable instead of a Placeholder and this aspect is not mentioned or explained
In face recognition I still don't know how triple loss function is used during training
創建者 WALEED E•
This course was the best I have ever taken. It gave me a big boost to carry my PhD research in robot vision with confidence of understanding what is happening all over the network and comprehension of one of the pioneer papers published in discussed in classes. Coding directly after finishing each week was the best to go to practice and apply all this knowledge gained.
創建者 Ayush K•
Quite lucid and good introduction to CNN for beginners to intermediate level. I specially liked the links and discussions about different papers along the course that Andrew recommends to read. For some who has just hear about CNN, but knows about basic NN, this is a really good course to learn main things super fast and then proceed into their own personal topics.