Chevron Left
Custom Models, Layers, and Loss Functions with TensorFlow に戻る による Custom Models, Layers, and Loss Functions with TensorFlow の受講者のレビューおよびフィードバック



In this course, you will: • Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network. • Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data. • Build off of existing standard layers to create custom layers for your models, customize a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions. • Build off of existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models....




It is advanced TF specialization and the way contents are presented in the course are very systematically. Definitely recommended for developers already familiar with TF and wanted to explore further.



I was looking for a course about this specific topics. Previous NN courses were cool, but I think they kep short on making more complex Architechtures, which is perfectly addressed in this course.


Custom Models, Layers, and Loss Functions with TensorFlow: 1 - 25 / 156 レビュー

by Irina G


The course is basically a presentation of semi-digested Keras tutorials, sometimes outdated. No depth and no real-world experience were communicated. The notebooks are mediocre, lazy and minimalistic, here-they-work-here-they-don't. You will not use them for your portfolio. I wouldn't call this course "advanced", it's rather a shallow overview of advanced techniques.

by Sieds M


Very nice course, learned a lot! Thanks

Some recommendations:

In my opinion, the course is not the number of hours that were given for it. I'm not a super experienced Deep Learning practitioner but spent around half of the time that was given

Secondly, the microphone of Lawrence should be checked, in the far background, there are some 'crunchy noises' which can be a bit annoying.

by Daniel E


This course presented such timely and vitially important innovations in deep learning, that it is difficult to express. While some of the material, was challenging, only illustrated the vast contributions of highly technical ideas that have come out of the development community. I am grateful to have taken part and benefitted from this course.

by Quazi R


The course is very helpful for building sophisticated models, and also provides in-depth understanding of model architecture. And as usual, Laurence Moroney did a marvelous job in teaching such a complicated topic in a fun and exciting way.

by Vishnu D P


If you want to lead a happy and peaceful life keep learning. Deeplearning.AI courses are so beautifully structured and explained that I sometimes feel this should never end. Learning from the deeplearning.AI course gives me immense pleasure.

by S S


Loved it!!! What I like is understanding the concepts and how it ties together without getting needlessly stuck in some Python heavy exercise. The knowledge acquired will help me to mess around and have fun with Tensorflow2.

by Bernard F


Excellent introduction to the subject of custom layers in Tensorflow .

Shows much more flexible methods for coding Tensorflow models in a way that previously might have required a switch to PyTorch to achieve

by Moustafa S


Really great course, it teaches you all about the TF API and how to customize it for your needs, i thought only pytorch can make that as it's really pythonic, but i am a nieve noob what can i say.

by Eric L


This course was fantastic! After learning about the functional API, I found tensorflow/keras are far more flexible than I had realized and am much more excited about the possibilities.



Such an awesome course. The examples given are just to the point. Can't thank enough Coursera for providing such a lovely platform and Laurence, what an amazing instructor.

by Jay R


The course makes some of the more advanced functionality in Tensorflow really accessible, and I think anyone serious about Tensorflow needs to take this course.

by sameer s


Great course to get hands dirty with functional api, custom loss functions, custom layers, custom models, and custom callbacks! Thank laurence moroney sir :)

by Santiago I C


Good to get deeper into some custom tensorflow techniques. I would also recommend the book by Aurelien Geron which has a nice chapter about this also.

by Cristian S


Very happy with the course. The examples are clear to learn how to really take advantage of the flexibility provided by tensor flow and Keras.

by Maryam F


It is an amazing course, great introduction of advance technique, specially functional APIs. Thanks again Laurence Moroney and Eddy Shyu.

by Bhavesh W


Outstanding as always. Big Fan of Lawrence and andrew, both have changed my life. Thank you so much

by Kaan B


Everything is very well explained, although programming exercises could have been more challenging.

by Ram K K


To the point, crystal clear, very good course. Please make a pytorch version of this course.

by Julio C M B


Excellent course with great material. The videos explain everything needed to start coding.

by Minn B B


Yes, we do need this course right after the previous specialization to master TensorFlow.

by Isuru S A


Great Content. You need some prior experience of TensorFlow to do his course.

by Daniel D


One of the most useful and enjoyable course that I have ever finished

by Lam T


Great course to learn how to use Tensorflow to build flexible model

by Abdelrahman A


Very good instructor and very good topics.

by Orson T M


good course , thank you !!