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
1,055 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.

PD

Jan 14, 2021

Wow! What a course it is! Amazing. Thanks to DeepLearningAi and Laurence for this course. But the mentors should be more active in the discussion forum. Not everyone is not comfortable with slack.

Filter by:

201 - 221 of 221 Reviews for Custom Models, Layers, and Loss Functions with TensorFlow

By Chamika G

•

Aug 13, 2021

Best

By Ignacio L

•

Apr 9, 2021

GREAT ONE. You will be getting better in some things thanks to this course, like object encapsulation , remembering fowar and back prop etc. I still want more freedom trying to use this tools in a challenging way. Like Kaggle does. Its too much info to get it right and know one is worth using. I woudnt change what there is, but I would add a final lab with a more open ended result.

By Alexander O (

•

Jun 13, 2021

The course is great for Tensorflow beginners. Unfortunately it provides only a superficial description of custom layers, covering only simplest one-line computations. Models covered in the course labs do not support summary() methods. I would like to know from the course how one would create full-fledged Tensorflow/Keras models that support all standard methods.

By Amit H

•

Oct 16, 2022

A good course to refresh the DL concepts in Tensorflow language. It is still a basic course so don't expect novel ML material from it. But it's good to understand TF code that you many encounter and convert PyTorch code into TF. Combined with other advanced DL theory, we can write TF code which creates complicated models.

By mohit d

•

Sep 10, 2021

One of the best course on custom Models and layers . As we all know importing a layer is an easier task it just includes a line but making our own models and layers is something which I always wanted to learn and I would like to say this course completely justified it

By Yuqi W

•

Apr 24, 2022

The course is overall very good and helpful to help me build my custom Model

Learn a lot of new concepts

But there are also lots of grading error

And I personally found # Your Code start Here# is annoying as I had to delete them first before I can code

By afsane h

•

May 6, 2023

Very good course which enables you to implement custom model structures, and custom training. I'll recommend the course if you are a researcher, student, or developer in need for trying modeling beyond already existing models, and keras api

By Thierry K

•

May 9, 2022

A little bit too easy. It's too bad that the coding assigments are so easy and don't need any deep thinking...

Nevertheless it's a good course and the instructor explains very well !

By Antonio C R

•

Dec 25, 2022

Concise and simple, but I would liked to see more depth and more exploration. It touches only the bare ground and it is a really short course.

By Nakshatra G

•

Mar 30, 2022

A little tedious course but overall a great one. I think after going through code some more times the concepts will seem fairly easy.

By Baburam C

•

Jun 9, 2023

excellent and comprehensive course with enough examples to understand the concepts

By David R

•

May 3, 2021

some good stuff, but too short and pretty easy

By Danial Z

•

Oct 12, 2023

Some material links were inaccessible

By Jacky T

•

Jan 17, 2021

Very nice course!

By Deleted A

•

Sep 11, 2021

good course

By Xứng B

•

May 1, 2023

good

By José L

•

Apr 15, 2021

The content is very clearly presented, but is very easy. Also miss a real-world challenging application exercise. All in all, too short, too easy for an "intermediate" level course.

By 周昊轩

•

Apr 20, 2024

For the last graded assignment, just keep the first and last layer. Otherwise, there will be a time off error

By Federico C

•

Nov 3, 2021

An interesting perspective, but the assignements modalities are a bit too easy.

By Ann A

•

Jan 5, 2021

Simple course. A very simple course. Too simple course. There are very few practical works and they are too simple. There is almost no description of the features of the application of certain techniques. I am disappointed

By Varun S

•

Dec 30, 2020

Libraries are not explained properly, looks like its just code walkthrough,