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
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.
by Selina N•
It's an exciting course. I find very interesting to learn object detection, facial expression and face recognition. The concept of neural style transfer is easy to understand and funny to generate image to absorb the style from another image. The explanation is useful. One improvement is some assignments only import the trained models with extra source code. It would be better for students to build by themselves to go through the whole model development step by step.
by Mike G•
Some of the concepts in this course were at times hard to grasp. I'm still fuzzy around filtering and pooling concepts so will need to revisit. Andrew's lighthearted nature and good humor though; added levity to this otherwise fairly complex subject. My takeaway is that I have much more to learn about the subject. This class however has been a fantastic launchpad to an entirely new domain for me. I already bought some literature to dive deeper.
Thank you guys :)
by ABIR E•
Just wonderful! and especially unique! : we could never find such a deep and detailed course on computer vision and its applications.Terrific! (just for fun: before I always say : I need to go deeper (I have a gap to fill in computer vision), but now that's it: I went deeper than any "Inception..."(those who are going to take the course will understand the joke I just used (suspense: it concerns "Leonardo DiCaprio" ...), go take the course, without hesitation!
by Rahul K•
Very intricately explained course! Prof. Andrew has gone the extra mile here, making sure that the basics of CNNs have been imbibed thoroughly. Kudos to the programming assignments - They're undoubtedly the toughest of all the former deeplearning.ai courses. Use the discussion forums to help get subtle hints. I now feel that I can read CNN-related papers and even work on CNN applications. Plus, you learn how to implement Neural Style Transfer (DeepDream) here!
CNN is a tough topic to fully demonstrate. From my perspective, the lecturer simply offer an intuitive introduction and pick up some notable variant like ResNet, and illustrate the main ideas through delicately chosen case studies. That's somewhat "clever", I think. Maybe that's not appropriate, but I mean that it's friendly to a fresh learner but far from detailed and enlightening for an advanced learner. Anyway, I get to dive deeper into this field myself.
As in every class taught by him, Professor Andrew Ng makes Deep Learning concepts and applications accessible. His clear explanations during the videos lead from learning the foundations to implementing modern-architecture Convolutional Neural Networks. He provides additional information about whether certain techniques are currently utilized in research and production which bring an important relevancy to the material. Thank you for offering this course.
by CHEW L W B•
Great intro to CNNs, how they work, how to use them and the types of problems they are good at solving. I'm glad Prof Andrew Ng touched on more advanced topics such as image detection, localisation and face verification/detection and how CNNs can be applied to such use-cases. The programming problems were challenging but not overwhelming, as long as one is willing to spend some time to understand the concepts presented and explained in the lectures.
Great course! Gives a great boost in understanding of deep learning usage while solving computer vision tasks. Different ConvNet architectures, their application, state of the art algorithms are explained in detail. Sometimes there were issues while solving programming assingments, specially at the last week, but I truly appreciate deeplearning.ai work that gives everyone the ability to learn about this things very effectively. So 5 for this course.
by TANVEER M•
The course gives the basic understanding of convolutional neural network in a lucid manner.Every concept is very nicely explained. I was having some confusion with yolo algorithm which got cleared.Also Neural Style transfer and Face verification using Siamese network were the two which I haven't heard before were very interesting. The assignments are awesome where how yolo and neural style transfer works made my concepts clear to a lot of extent.
by Anshul M•
Great introduction into some of the recent and cutting edge work in the field of computer vision. The course's mathematical focus is good to understand the mechanics behind the use cases at the same time I liked the intuition about the steps in the process were shared from time to time for better context. Would have loved to get hands dirty on training models or tuning hyper-parameters - but understand it would need additional resources GPU etc.
by Amit B•
Excellent Course. It has given me an immense insight into CNN and its practical applications. I have become that much more knowledgeable thanks to this course and its contents. Sincerely appreciate the concerted efforts of the team to lucidly explain the nuances of various concepts and at the same time provide ample opportunities to the trainees on hone their skills on practical aspects of implementing the algorithms. Kudos of all stake-holders.
by Matthew J C•
Another fantastic course from Dr. Ng. In addition to object classification/recognition (which class does the object belong to?) this course should get you started with object detection (where in the picture is/are this object/s?). This course does not cover single or multiple instance semantic segmentation. Take this course (much of the coding is from scratch) & then go look at examples from your favorite API (Keras, TensorFlow, PyTorch, etc).
by Hermes R S A•
There is a dedication, from the professor and the team, to teach you the most recent developments, without skipping important introductory level concepts. Having a grasp on the Imagenet winning architectures was really rewarding. The only down side was the YOLO algorithm assignment, because the notebook was a little confusing and disorganized, but you ca get the key ideas from it. All in all, it was my favorite course on this specialization.
by JOSHY J•
This is the best course for those who are serious about Deep Learning and computer vision. Some of the features of the course are Well Arranged, Simple, give a deep understanding of the mechanism, etc. We will learn Image processing, Image detection, Object detection, Face recognition and face detection through this course. Weekly assignments in the course give hand-o experience with the popular deep learning frameworks and neural networks.
by Shuai X•
Prior courses are almost all covered in the Stanford Machine Learning Course, which is free. If you don't want to waste time going through what the Stanford Machine Learning Course can offer, then this is the point to start to subscribe. Though it estimates 4 weeks of learning is needed, you can probably finish this course in a week. Assignments on CovNets and ResNets written in Tensorflow and Keras are mostly very good and very useful.
by Ashutosh P•
This is a really comprehensive course by professor Andrew Ng. He dove down to even the smallest details, you'll realize this when you listen to the lectures carefully. Make notes of each lecture as it's a long course and there are lots of terminologies in which you could easily lose yourself, stranded somewhere in between lectures having no clue what he's talking about. All-in-all, it's easily one of the best courses I've done on CNNs.
by Azer D•
Course was so helpful to understand concepts of conv nets. Also i like that Prof. Ng prepared the course with related successful papers of conv net world.One thing that i'm not happy is Coursera's Jupyter Notebook hub which I usually have problem with user authentication. Because of that I saved notebooks to my local machine, worked locally, and after completing it pasted my answers to notebook. I hope problems will be fixed soon.
by Jon M•
Fun and yet challenging. More challenging than some of the earlier courses because there's more advanced concepts. Without the pre-written code some of the assignments could have taken a novice ages to figure out, but the assignments are written with the goal of only really focusing our attention on the new stuff that was discussed in the lectures rather than forcing students to figure out the details from scratch. Loved it!
by JP L•
Extremely well done. Great balance between hand holding/help from the forums and effort in learning. I certainly appreciate the fact that after the course, you are ready to run in the real world working on AI endeavors. They also use all the most recent and up-to-date tools en development environments like Python notebooks, Keras and Tensorflow which makes you immediately proficient working in AI projects. Kudos to the team !
by Souvik S B•
This is an excellent course and so far gives best understanding of convoluitonal Network and how it works. But the grading issues needs to be resolved. One thing I specially like about andrew NG courses is how it explains the basics and how algorithms are written from scratch for better understanding. Would be good if we could do the same for YOLO and Facenet.However the assignments are well designed for good understanding.
The course is very interesting but we will have to practice after all that and go through the github codes in detail!
I found the professor Andrew is very clear in his explanations, especially in his desire to visualize what there is behind this complex models.
On the other hand I found the part on the Yolo model a little less well explained especially with regard to the anchor boxes. But I'm going to dig deeper into this.
Probably the best course in the specialization and the best course online on ConvNets!
Very engaging and interesting assignments, which cover advanced topics in an approachable manner. teaches current technologies (Keras, TensorFlow). The course goes into some of the math but doesn't get bogged down in it. The course includes recent developments in ConvNets such as the YOLO algorithm, Neural style transfer, and FaceNet.
by Vipul S•
There are lot of things are happening in computer vision field and this course helped me in understanding the concept like convolution and their use in computer vision field. Practical advice like using existing open-source implementation or existing network architecture are really helpful.
Overall this course equipped me to understand the CNN and it's practical application in computer vision field.
by Praphul S•
Some exercises very interesting, especially the last week. Why transpose was required made me reflect on the first course's content that dimensions matching will be a very useful technique to debug. Some highlights were the need for the convolution and how it reduces the complexity. The pace of the videos was good and details were very well explained (along with references which encourages to explore more on interest).
by Tao Z•
Andrew and his teaching assistants made difficult course easy to understand. This is not trivial at all. The exams not only tested students' knowledge but also provide hands on experience on real models, which should be very handy when students want to implement their own AI solutions by themselves later on. Andrew is certainly an excellent teacher and an outstanding AI ambassador, besides being a pioneer in the field!