Avis et commentaires pour l'étudiant pour Image Understanding with TensorFlow on GCP par Google Cloud

Several quicklabs issues

TPU quicklabs does not work. Always getting access error. I added manually the rights, but then I have an error about import apache-beam.

AutoML Vision quicklabs needs to mention to enable per object ACL or you cannot set the ACL.

Datalab is very very slow to start, very painful.

Most labs don't work or are pointless

Subscribing to this course only gives you option to run assignments on Qwik labs, and they're very poor for these kinds of assignments. You won't get any feedback on assignments anyway since there is no grader.

If you want to check out the material it's better to just clone training-data-analyst from github and do these assignments on GCP free tier.

Great Course!

Really interesting labs in this course!.Thank you!

It was One of the great course having labs which was really fun

G

r

e

a

t

e

C

o

u

r

s

e

.

Excelent in every aspect. contents, coding, pacing. awesome

Great learning on Image ML models...

思路很清晰，每一个课程讲解的都很明白，本觉得课程内容有些少，对于很多概念讲解的很浅显，但是想一下和门课主要是讲TensorFlow的，也就不这么苛刻了，老师语速适中，不十分推荐新手，尤其是英语不是特别棒的新手观看，少许有一些图像相关的了解看起来会快一些，还有就是觉得实验方面不是很好，主要还是感觉这种形式的实验其实自己在电脑上就可以做了，没必要很复杂的在GoogleCloud上费时间，希望改进一下Lab吧

Was worried this would be just another CNN course but it was so much more. Showing out to use existing models etc. The details on CNN is a little lite but that can be found elsewhere. What was really good was the batch normalization and using pre-trained models but just changing the dense layers to provide classification,

A very good course, with cutting edge research about Deep Learning, Go google :-) !

Good

this Courser teach a ongoing technique in GCP, and the world

The AUTOML is fascinated technique for learning

An excellent course. Clear, concise and comprehensive.

Very good course on CNNs. The labs were cool. Thank you!

Thumbs Up!

Good

Amazing course! Definitely recommend the course for learning Google's way to handle images! ;)

The code in the labs needs updating.

Good material

You should improve the explanation of Transfer Learning from prebuilt models like ResNet. The conceptual side is not clear.

The course provides an excellent overview of Image Understanding with TF and the utilization of all the capabilities of GCP to build productionable image systems.

Good Practical Experience with the concepts what that I learned . Good for recommending my friends.

Highly recommended