Chevron Left
Siamese Network with Triplet Loss in Keras に戻る

Coursera Project Network による Siamese Network with Triplet Loss in Keras の受講者のレビューおよびフィードバック



In this 2-hour long project-based course, you will learn how to implement a Triplet Loss function, create a Siamese Network, and train the network with the Triplet Loss function. With this training process, the network will learn to produce Embedding of different classes from a given dataset in a way that Embedding of examples from different classes will start to move away from each other in the vector space. 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, Keras, Neural Networks. 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....




I like the way we got involved into practice by setting goals which are a bit challenging yet we want to achieve successfully.



worth enrolling!! checkout in detail about this project even after completion


Siamese Network with Triplet Loss in Keras: 1 - 19 / 19 レビュー

by Isra P


Incomplete course, the prediction is very important not only training!

by Joerg A


Very well instructed, I learned both a new technology and something for good python programming habits. Explanations come to the point and still are deep. Test are not stupid simple questions, but still easy to answer. And I got the impression the instructor even knows about the pain with Rhyme (and seems to do something about it !)

by Abhishek P G


I like the way we got involved into practice by setting goals which are a bit challenging yet we want to achieve successfully.

by Luis A G L


It is useful as you learn exactly what you expect to learn, with just the right amount of theory.

by Nittala V B


worth enrolling!! checkout in detail about this project even after completion

by Fabian L


it's so great for two hours, is just a preview, but is good

by Angshuman S


Nice crisp and knowledgeable course



Very Helpful !

by Doss D


Thank you

by Sourav D



by Santiago G



by sarithanakkala



by Qasim K


Great introductory course. Would have given 5 if the dataset was a little more complex and a real-world use case was covered.

by Siddhesh S


This course has nice content, but the usage is difficult. Ever after having fast internet, the videos and the environment were so slow, making it almost impossible to be used.

by Sri C


Not at all enough to start with a face recognition kind of use cases. The intro was cool with the explanation of using siamese network for FR kind of use-cases. But lost its cool when explaining it with mnist dataset. There's already a lot of stuff available in market and on net regarding mnist. It would have been nice if the instructor had explained some other use case too, for better understanding. The network was too small to understand the complexities of siamese network.

by Simon S R


One of the few courses with an instructor actually present in the forum. However, this project needs both, more hands-on exercise and a deeper dive into the theory.

by Jorge G


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.

by Yannik U


S​afe your money and have a look on this website, it is exactly the same code:

by Molin D


Good, but not recommend.