Chevron Left
返回到 AI Capstone Project with Deep Learning

学生对 IBM 提供的 AI Capstone Project with Deep Learning 的评价和反馈

311 个评分
57 条评论


In this capstone, learners will apply their deep learning knowledge and expertise to a real world challenge. They will use a library of their choice to develop and test a deep learning model. They will load and pre-process data for a real problem, build the model and validate it. Learners will then present a project report to demonstrate the validity of their model and their proficiency in the field of Deep Learning. Learning Outcomes: • determine what kind of deep learning method to use in which situation • know how to build a deep learning model to solve a real problem • master the process of creating a deep learning pipeline • apply knowledge of deep learning to improve models using real data • demonstrate ability to present and communicate outcomes of deep learning projects...


Jul 30, 2020

The capstone of the project was really good it helped me to understand the deep learning concepts clearly for providing the solution.

May 22, 2020

A very nice project based course to get hands on experience with deep learning\n\nand transfer learning.


26 - AI Capstone Project with Deep Learning 的 50 个评论(共 56 个)


Sep 23, 2020

awesome course

创建者 Julien V

Jun 3, 2020

Great course !

创建者 Christos

Feb 25, 2020



Jul 25, 2020

Noce project

创建者 Yuanlong S

Feb 16, 2021

good course

创建者 Aditya M P

Dec 11, 2020

Good Course


Oct 18, 2020

Good Course

创建者 Carlos F C d S e S

Mar 26, 2020

Thank you!

创建者 Alvaro B

Apr 6, 2020


创建者 Claudia S

May 17, 2020

For the Keras part, it would be desirable if "clean" zip files were provided for week 2 to week 4 exercises, since they contain the MacOSX folder (which I think it is not required for the exercises). Also for Keras, it might be helpful if any other example could be found, since I do not think that using models which take that many hours (35 hours in Cognitive AI site / 8 hours in Google Colab) contribute in any way to the learning process. Or at least adjust them to use one epoch, like the Pytorch exercises

创建者 Meenal I

Jul 16, 2020

The course was good, but the only reason I gave it a 4* is because try as I might, the model fitting kept running out of memory on the provided system. I had to create an account on AWS to get my model to run. Maybe a consideration would be to try an alternate dataset that may fit in memory. I spent over 5 days trying it on IBM till before I had to move. to AWS. It was a great set of courses. Could have been a little more challenging as well.

创建者 Julien P

Jun 19, 2020

It's a great course to guide you through the full process of training a deep neural net. However, one needs to use external resources to train the model efficiently (Google Colab for example). The resources provided by IBM are not powerful enough to train the model in a reasonable amount of time (no GPU).

创建者 Theodore G

Jan 28, 2021

Great course content! One thing that can be improved is the Skills Network portal. It's incredibly difficult to train any of the pre-trained models there.

创建者 Mikhail P

Feb 13, 2021

The Keras part of the course is more attractive just because its final assignment is much better structured than that of PyTorch.

创建者 Daniel J B O

May 26, 2020

I like the flexibility to pick our framework for the project i wish the kers one were a little bit more challenging

创建者 Ruchika V

Dec 3, 2020

I have completed this course but did not get the badge for it. Is there any way to access it?

创建者 Thar H S

Mar 27, 2020

Thank a lot for creating this course. It really useful and practical for me.

创建者 Emanuel N

Mar 1, 2021

Buen curso, implementando todo lo que se vio en la especializacion

创建者 charles l

Feb 24, 2020

This course was riddled with operational flaws regarding the image data, and how it operated in the IBM framework. At one point I was not able to run the labs with either PyTorch or Keras versions, and eventually just downloaded the notebooks and ran them in Google Colab to complete the specialization.

创建者 Yinias

Feb 6, 2020

The data from the course is not well prepared, some invalid pictures in the data. And also sometimes the IBM platform can not run the training well, loss connection and need several hours of time for training the model...

创建者 Alexis b

Mar 24, 2020

This is a good enough project if it is your first Pytorch implementation. However, the program is unevenly difficult, with very few information for week3 assignment, and almost copy/paste assignment for week4.


Mar 5, 2021

Not enough instructions as I wasted many hours without going to Google Colab. Please change it to AI review of project rather than peer review as most times there is insufficient submissions.

创建者 Reinaldo L N

Feb 4, 2020

The docker environment by IBM is horrible. I just got to finish my course running all the notebooks locally (except for those at the Watson environment)

创建者 Lee Y Y

Feb 9, 2020

Not well-prepared materials in Keras, especially in Week 3 (model-training) which took more than 3 hours to training and even not successfully.

创建者 Jakub P

May 31, 2020

The content of the course is very interesting and highly informative, however there is a critical flaw in this course (at least for the keras library side of things), the problem is that IBM Cognitive Labs, the intended environment for the assignments, is incapable of running the later labs (week 3 + final) and will crash after 30+ minutes of waiting, this being due to the instructors having us use a relatively large database of images (~250 mb). Jupyter Notebooks on IBM Cognitive Lab struggles to just unzip the dataset (which is downloaded as a zip), not to even mention fitting the models to the data, which I found to be impossible to do with IBM Cognitive labs (for both week 3 and the final assignment). Ultimately I ended up having set up a jupyter lab environment on my own laptop, the problem is even then it took about 14 hours to fit the data to the models (in total, both week 3 and final assignment).

TL;DR the instructors have us using a pointlessly large dataset images which serves more to test our patience than our ability to create deep learning models.