Chevron Left
Back to Custom Models, Layers, and Loss Functions with TensorFlow

Learner Reviews & Feedback for Custom Models, Layers, and Loss Functions with TensorFlow by DeepLearning.AI

4.9
stars
975 ratings

About the Course

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....

Top reviews

NP

Feb 3, 2021

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.

MS

Nov 24, 2020

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.

Filter by:

51 - 75 of 211 Reviews for Custom Models, Layers, and Loss Functions with TensorFlow

By Andrea G

•

Sep 3, 2021

The lessons and examples are clear and entertaining. The overall content is interesting. The only flaws are the extremely detailed instructions and large code chunks provided in the practical tests. These help to concentrate on the topic, but tests result a little straightforward.

By Abd-elrahman S

•

Feb 1, 2022

overall great course if you have solid foundation in tensorflow ,Don't be fooled by the easy assignments in week 1 ,because from there the course gets into object oriented programming with customization of a lot of things and you will encounter building the complex architectures

By Zaky A R

•

Jan 31, 2021

Excellent introduction to customizing your neural network. its an eye opener for people who wants to have more customizable layers, loss function, callbacks and even the architecture itself. Also the instructor themself are amazing. I really recommend the course! definitely 5/5

By Florian C

•

Aug 4, 2021

Excellent course! Thank you to the instructors and everyone which contributed to it!

The theory is very well explained and I also had the opportunity to practice meaningful hands-on coding. It gives a boost to anyone wanting to work with more complex machine learning models.

By Mohamed M

•

Jan 14, 2021

Great course with a well structured plan and flow between topics. I really enjoyed the way the programming assignments were delivered. Completing this course has made me eager to apply my new knowledge of the TensorFlow 2 Functional API to my data science pipelines!

By Ozan G

•

Feb 15, 2021

If you are going to be doing research with Tensorflow, you will most likely need this course. Functional API and custom layers, loss functions and models are essential for going above and beyond training MNIST classifiers and building something novel.

By Pranjal J

•

Dec 23, 2021

The Course provides easy understanding to explore tensorflow layers and APIs to create complex models. The Custom Loss and Custom Callback features along with model subclassing will help students to build powerful models very efficiently.

By Ayobami A

•

May 26, 2022

Great course with great contents. This course gave me a deep understanding of how things work under the hood in Tensorflow. I'll recommend this course for anyone trying to build deep learning models from scratch in TensorFlow

By giuseppe i

•

Jan 16, 2023

Great course, precise and concise. I love the way and the clearness, Laurence Moroney explains things (I found the short videos formulas to be very effective). I will definitively follow his other courses. Thanks Laurence!

By Петр В

•

Feb 12, 2021

Lots of very valuable TensorFlow materials to launch an advanced project and have more control over the models, layers, loss functions and callbacks. Exactly what you need to improve your skills in a short period of time.

By Boels M

•

Apr 15, 2021

Very well explained and structured course. You will learn to write advanced and object-oriented programming code using the latest TensorFlow techniques for building flexible neural networks architectures.

By Nileshchandra P

•

Feb 4, 2021

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.

By Andrii S

•

Nov 6, 2022

Great explanation of functional API and using classes to make complex models like residual or with repeatable parts. And a lot of other things which lead you to a better understanding of NNs, CNNs.

By Ferran P G

•

Nov 11, 2022

Very interesting and well-explained course. Laurence is an amazing instructor and makes everything easier to understand and master. I definitely will be recommending this course to my colleagues!

By Diego A F S

•

Mar 30, 2021

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.

By Magda

•

Aug 10, 2021

This course consists of good explanations and coding exercises. followed by not overly demanding practical assignments. It is informative and opens the world of Tensorflow models customization.

By Muhammad N S

•

Aug 23, 2023

Very interesting course! Here, I learned a lot of new things related to TensorFlow. The explanation of the material is easy to understand, and the exercises are also quite challenging.

By Alireza M

•

Jul 30, 2022

It was a very useful course. Now I can build deep learning models with my desired architecture. I am also able to understand the implementation method of famous models like VGG-16.

By Jonas K

•

Feb 3, 2021

It would be very nice if you were able to go from one fullscreen video to the next.

As it is right now it requires 3 clicks to just resume, that could easily be done with one click.

By Sadaf

•

Feb 14, 2022

1. Course labs are well designed

2. Material covers real world problems

3. Course is well designed

4. Instructors are very good in the subject

5. Teaching method is good

By quyet t

•

Aug 30, 2021

extremely detailed course on how to use API functions, I found that the weeks in which week 1 is the most difficult with homework the following weeks they are too simple

By Specialist i F

•

Oct 14, 2022

Amazing course. I had done the deep learning specialization before this to understand principles, so this course helped me implement those principles in tensorflow

By Stephen N

•

Apr 1, 2021

For a newbie in tensorflow, this course gave me the tool to custom the model. Compared to the previous specification "Tensorflow Developer", it is much more better

By Luigi S

•

Apr 11, 2021

It was a very good course, very clearly explained. The rhythm was not so high and I enjoyed the chance to go step by step going in deep in important concepts.

By Ajay K V N

•

May 23, 2023

Really very useful course for students who are aspiring of becoming ML/DL engineer. Instructor explanation is awesome and provides us good helpful resources