部分内容讲的不是很清楚，有些剪切不好，有重复

Very complex Subject

没有翻译 tenserflow也讲得不好

Not enough theory

too theoretical

too many bugs

so hard :(

It was okay. Andrew is obviously very knowledgeable, and there is a wealth of knowledge here. I could go through it a couple more times and still pick up new stuff.

That being said, I've heard him mention he did these videos at like 1 or 2 in the morning after work, and it's very obvious from the videos. He makes so many mistakes that every other lecture (it seems like) has a **CORRECTION** notification next to it. I mean it's great they give this additional correction information, but it would be even better if you just redid the video.

Furthermore, he like stops in the middle of the videos and then repeats the last sentence he said, because he made another mistake. I get it, Andrew is very successful, he's very busy, and I am definitely grateful for the knowledge he's provided in this course. But this makes for a very poor learning experience, because I'm taking notes, and I have to go back and redo them, plus the general angst you get when you're learning something and someone's like "oh wait nope that's not right, forget that." Well for God's sake I already learned it.

Finally, the submission assignments are the most annoying things I have ever come across. They are riddled with errors and misguided information where they literally tell you to use the wrong parameters, and then they never fix it. You have to go into the discussions to find out why your code is wrong, even though you're doing it right.

Then, you'll get everything right on your code for the test cases, and when you go to submit it fails you. And when I say it fails you, it gives you a literally 0 out of like 30 points. And the grader output just says "your submission was incorrect" like no way, I had no idea. Thank you for that very **cough** helpful piece of info.

If you go to the discussions, you find out this is actually a problem with how the grader is built, because if you don't format your code exactly the right way, it fails you, even if your solution is correct. I don't understand why it can be right when you run test cases, but submitting it fails.

Overall, I give it 3 stars before the poor grading, but because of the poor grading performance I have to bring it down to 2. I can't tell you how much time I wasted trying to figure out why my code was wrong just to realize it was right, but they screwed up their implementation.

In conclusion, this reminded me of a college course, where the professor has a ton of knowledge and is in high demand, and doesn't really care whether you get anything out of the course or not. It's sloppy, doesn't seem to be maintained very well, and most of the mentor's responses are literally "did you look at your colleagues similar questions?" Like no I didn't, that's why I'm asking. Why am I paying you so I can spend more time debugging your screw ups? Or maybe I did and I still don't get it because your explanations are ridiculously unclear.

I have one more course in this specialization and I absolutely can't wait for it to get over with so i can move on to more productive (and immersive, since these exercises are just one off "do this then do that" instructions, I still don't know how to set up a Deep Learning project from scratch) ways to learn Deep Learning. If Andrew wasn't so knowledgeable about this topic, I wouldn't even take it because it's that bad. But really you can't get this type of knowledge in such a condensed form anywhere else.

Hi! First of all, I love the specialization and these courses might be the best out there in DL (insane knowledge and Andrew is the best explaining, to be honest). Now, I have to give this 2/5 simply because of Coursera's side this last 7 days.

1. Last thursday, the 'Permission Denied' error -which affected hundreds of users- took over the Jupyter notebooks.

2. On friday, DeepLearning.ai mentors told us that you were aware of the issue and they offered us some 'hacks' or workarounds to actually progress while you solved the error. We were told to wait.

3. On the weekend -not a single official communication on Coursera's side yet (an email or something, the kind of thing a service does when their own product doesn't work, you know)- the mentors told us that you have already solved the issue (?). Of course it was not, and hundreds of users reported it again on the forums. We were told to wait.

4. The workarounds -given to us by the mentors- actually worked for some of the notebooks, but not for all. We were told to wait again.

5. After maybe a whole day inside the forums, we were told again that Coursera has solved the issue and the mentors told us that we needed to refresh the lab. Yeah, that worked... this is monday / tuesday by the way.

6. The issue was apparently solved, but yesterday -after following all instructions- i got a 0/100 grader (?). I contacted support (no solution). Solved by myself. On to the next assignment - Worked. On to the next... dead kernel... I contacted support two times (no solution and i was told to -AGAIN- go to the forums so another person could contact Coursera's support (?). Basically a black hole.

7. I've spent two hours now trying to submit my last assignment of Convolutional NN (yeah, dead kernel)

8. These past 6 days have been a waste of time, straight up. 6 days copying and pasting in an external text editor, 6 days with our attention on the blogs because, you know, 0 transparency on Coursera's side (yeah, its crazy to me that no official message was released).

Honestly, I was thinking of dropping out of the specialization if i couldn't submit the assignment today. Very disappointed with Coursera's communication and support

I found it very easy to go through the assignments and the quizzes were great, but I do have 2 complaints: -- I didn't get quiz feedbacks (they seem to be disabled), so, this is a huge let down and I wasn't able to completely grasp the concepts. -- For example the Gram matrix I had to accept it was true when they said "if the filters are quite similar then the dot product will be high". Show this please? #mastery #selfcontained. -- Another example, on the programming assignment, on Neural Style transfer, it is POORLY explained how the framework works when it comes to setting a_G and a_C. Then it is said "this will be covered (explained) in the "model" function, which wasn't. -- I have printed most of the mentioned papers and I am starting to read them, I loved the fact you recommended papers on this lesson, and the rest of the programming assignments were great, especially when you would provide "Hint" to go to the docs and lookup the method, etc.

I feel this is by far the weakest of the first 4 courses in the series. The information is really valuable and the homework offers almost no opportunities to actually explore CNN architectures. The homework is more about implementing a few parts of a dictated network where all of the critical information is provided. The only exercises are in more vector manipulation and knowledge of frameworks that are never talked about in the actual course material. I'd love real framework material and real opportunities to practice using them, but the limited exposure here does not cut it.

Basically, I listened to the videos talk about CNNs, answered quiz questions about minor foot notes in the lectures, and then messed with vectors again. Oh, and the video editing was pretty choppy in this course compared to the others. Disappointed.

The material covered in the course is very good but the instructors really need to go back over the course materials (particularly the homeworks) and clean them up. Many of the links to the TensorFlow documents are out of date and link to missing information. These aren't necessarily updated in the forums either, which do not seem to have much of a TA presence anymore. It would be nice if the lectures & slides could be updated to incorporate the errata in the syllabus but I understand that could be a lot of work. However, it seems like it would be better to present the errata before the lectures in the syllabus. Admittedly its a small complaint but it seems like an easy fix and the fact that it hasn't been done says something about the amount of care put into maintaining the course.

Course is great, but there were several bug in the homework, including misleading tests.

In one, getting the right value (triplet loss) results in a failing grade, getting the wrong values (using help from the forum) get you to pass the test. In another test, there were corrupted files; one has to add a print statement in a helper function, learn what file is corrupted, rename it, reload the exercise, and voila, it works.

Clearly, graders should survey the forum more closely to address these issues. Hopefully it will be addressed soon, and these comments will become moot.

That aside, the quality of the videos and the insight provided by Andrew Ng are second to none, thanks for the outstanding instruction

Felt compelled to review this particular course to voice my dissatisfaction. The course, as it stands right now, is rather poor in quality. The lectures contain several errors that are lazily corrected. Sections of video are incorrectly spliced together that chops up the flow. The programming assignments drop sharply drop in quality from the previous courses; they're pretty close to "type the stuff we tell you to type" at this point. Even at that, there's several errors in those assignments that require digging into the forums because the course instructors seem to lack quality control.

I quite enjoyed this specialization in courses 1-3, but this course has left quite a bad taste in my mouth.

While the content of the course is thought provoking and up to date, the overall quality is quite low. Videos are of moderate quality with very poor audio editing, and the programming exercises suffer from poor auto-graders. Regarding programming assignments, I spend most of my time trying to get just right combination of function calls despite getting exaclty the right answer in my tests. Typically this comes down to using just right numpy or tensorflow function, despite either one giving the same results. Overall, I wouldn't recommend taking this course for credit but rather simply extracting the relevant lessons and recommended readings.

The lectures are quite interesting, but the course should be at least twice as long to cover the CNNs with enough depth for a practical application. For the assignments, the Grader and the Notebook worked terrible compared to all the courses I took on Coursera so far. There were many discrepancies between the Notebook and the Grader- code matching the expected output in the Notebook would fail in the Grader etc. Starting about two days before the assignment deadlines, loading models into the Notebook would take 30-40 minutes, and crash most of the time, with unreadable error messages. Files got corrupted, sessions ran for hours...

As with other courses from Andrew, the lectures were great - easy to follow, clear explanations, great insights, lots of practical advice. The main reason for the lower than average rating is related to all the issues with doing the programming assignments. There seemed to be a larger than usual number of errors in the notebooks and one in particular (Week 4) had a problem with the grader that persisted for several weeks (if not still ongoing). In addition, several of the assignments didn't seem to really help in understanding the algorithms for CNN but instead concentrated on the minutae of the frameworks like tensorflow.

This course presents some important state-of-the-art in convnets and teaches you everything you need to get your feet wet in that area. As always, Andrew is a great teacher. However, the programming assignments are a mess. Sometimes they are trivial, sometimes you feel completely lost. That wouldn't be a problem, if it were not for multiple bugs in the grader. So, after solving the task correctly, you find out that the grader expects an incorrect value and you have to figure out what mistake the developer might have made. Without the forum and very helpful other students, there is almost no chance of completion.

Frustrating and annoying pitfalls in the assignements: most of the time you lose time on trivial syntactical issues on python / tensor flow, rather than concentrating on the model itself.

Beside that the Kernel stabiliyt is gettin worse and worse in these courses as the weight of the models increase: the kernel breaks too frequently and you don't have any other way to restart it from the beginning, losing all the modification.

It takes ages to reach the end for trivial issues, not related to the subject of the course

It is impossible to accomplish the grades without digging in the forums

Material explained very well, but course material was very poor. To really understand the material one has to basically rewrite all the class notes themselves. Maybe this is a great way to learn, but it can take a lot more time than advertised. The jupyter notebooks are well done, and a great source for future reference. But the main problem is that only the notebooks can be downloaded. All datasets and pictures do not download using the provided coursera instructions. I called coursera, but the problem could not be solved. This was very disappointing and extremely frustrating.

Assignment for Week 3 is just a load of BS. Complete mess with no structured attempt to explain relations between suggested data-structures and built-in functions that use them. Whole fairly nice course is completely ruined by this one mindless pile of 'fill in random line of code to get the result' approach.

On the top of that - a final cherry on the pie was complete mess with Week 4 assignment on face recognition. Multiple bugs in the assignment code and grading, broken db's for the notebook and complete lack of support from Coursera. A shame. Weak and shame.

This course is an interesting review about techniques of image recognition based on neural networks. Unfortunately, it is not possible to achieve a deep understanding of these techniques during the time the course lasts. The practical activities are just filling lines in programs following the provided instructions and, sometimes, it is even possible to do it without understanding the rest of the code. The frequent disconnections between the notebook and the server slowed me down a lot and even made me lose all my work and start from scratch several times.

The first couple weeks laid a good foundation for understanding CNNs, but I did not understand the point of diving so deep in to Computer Vision, especially having a lengthy programming assignment devoted to an algorithm as complex and relatively niche as YOLO. There are several different architectures/applications of Deep Neural Nets conspicuously absent from this entire sequence, most notably GANs and AutoEncoders. I felt a good deal of frustration when implementing the programming assignments in the latter half of this course

Overall it's a very comprehensive course with a broad set of topics which I found insightfull. However, the programming assignments, in particular the Happy House, was done in a rush due to errors in the models and code provided. Part of the assignment couldn't be tested just for the lack of access to the model and evaluated its results after its grading. The forums were also crowded with many threads talking about similar issues. Hope you can improve this section in order to create a more solid course.

Very buggy, videos having problems (like repeating phrase), many errors in notebooks so that you spend more time trying to understand why grader doesn't work than on actual exercises...

The explications are either too simple or too sketched, so that you never really understand where difficulties are. The programming exercises are hard on the programming part and too easy on the math part, essentially what it is difficult is using tensorflow and keras with little or no explications.