Chevron Left
Вернуться к Deploy Models with TensorFlow Serving and Flask

Отзывы учащихся о курсе Deploy Models with TensorFlow Serving and Flask от партнера Coursera Project Network

4.5
звезд
Оценки: 191

О курсе

In this 2-hour long project-based course, you will learn how to deploy TensorFlow models using TensorFlow Serving and Docker, and you will create a simple web application with Flask which will serve as an interface to get predictions from the served TensorFlow model. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your Internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with (e.g. Python, Jupyter, and Tensorflow) pre-installed. Prerequisites: In order to be successful in this project, you should be familiar with Python, TensorFlow, Flask, and HTML. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....

Лучшие рецензии

MS

14 сент. 2020 г.

This course helped me a lot, I was confused and looked up a lot of articles on deploying deep learning models with tensorflow but this one helped by a great margin.

MB

10 дек. 2020 г.

Excellent! I will rate this as the best rhyme project that I have done so far. The instructor does an excellent job in explaining all the parts.

Фильтр по:

26–37 из 37 отзывов о курсе Deploy Models with TensorFlow Serving and Flask

автор: p s

23 июня 2020 г.

Nice

автор: Vajinepalli s s

16 июня 2020 г.

nice

автор: M M A

23 июля 2020 г.

Ok

автор: Joerg H

15 апр. 2020 г.

Fine demonstration of the TensorFlow Serving Tool. I Since I have experience with Flask and Docker it was easy for me to follow. I particularly liked the application of the Bootstrap library, which I didn't use yet. As a potential for improvement I would like to propose more coverage of TensorFlow Service itself (I guess it is also possible build and train new models - but maybe this is beyond the scope of a short project...) By this course I feel inspired to use TensorFlow Serving and learned how to set a defined model in short time.

автор: José C G M

29 мая 2020 г.

The virtual machine could be properly configured so as not to waste time on problems that arise. Also, I found the Rhyme platform with bugs

автор: JAVIER A T L

27 июня 2020 г.

Time given for the virtual desktop is not enought if you actually type and try everything he does.

автор: Guillaume S

11 апр. 2020 г.

More oriented toward using flask than on TensorFlow Serving but well done.

автор: Jorge G

25 февр. 2021 г.

I do not recommend taking this type of course, take one and pass it, however after a few days I have tried to review the material, and my surprise is that it asks me to pay again to be able to review the material. Of course coursera gives me a small discount for having already paid it previously. It is very easy to download the videos and difficult to get hold of the material, but with ingenuity it is possible. Then I recommend uploading them to YouTube and keeping them private for when they want to consult (they avoid legal problems and can share with friends), then they can request a refund.

автор: Akiva K S

16 дек. 2021 г.

Without Jupiter Netbook it's rather hard to follow. If you leave session chances are that Rhyme will close docker without informing you.

автор: Rishabh R

2 июля 2020 г.

not as expected

автор: David B

2 авг. 2021 г.

I​ am afriad this presentation really doent work as a format. I got half way through and the model simply wouldnt run, then had to go back through an hours coding - re watching to see where I made a typo. I found it eventually (a combination of not being able to code as fast as the tutor was talking, and the fact that he said one thing, then went back to change it later - and I missed the silent change.

A​nywhay then the corrected code wouldnt run because it seemed to still be running the wrong code, and I ran out of time and patience - it isnt a two hour course - at leadt not for me.

I​ think the format needs seriulsy rethinking - the explanations and instructions are confusing, and delivered too quickly - it became an exercise in 'monkey see - monket do" with no real understanding of images, servers, ports, forwards, and a host of chained other stuff - it really needed a slide, or a picture to explain the complex chain of 'somethings' we were suppose to set up.

I​ would have better understood, and had more success I suspect with a longer, better explianed, and more well supported course like most of the ones I have found on Coursera - and that is my suggestion to the authors and instructors.

автор: Jean M

15 мая 2020 г.

The course is too basic. The course doesn't even train the model. It would be much better to prepare everything from model creation to deploy and serve. The browser-based tool used to code is horrible.