Chevron Left
Retour à Custom Models, Layers, and Loss Functions with TensorFlow

Avis et commentaires pour d'étudiants pour Custom Models, Layers, and Loss Functions with TensorFlow par deeplearning.ai

4.9
étoiles
634 évaluations
133 avis

À propos du cours

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....

Meilleurs avis

PK
3 févr. 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
24 nov. 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.

Filtrer par :

51 - 75 sur 137 Avis pour Custom Models, Layers, and Loss Functions with TensorFlow

par Boels M

15 avr. 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.

par Nileshchandra P

4 févr. 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.

par Diego A F S

30 mars 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.

par Pramit D

14 janv. 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.

par Magda

10 août 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.

par Jonas K

3 févr. 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.

par quyet t

30 août 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

par Stephen N

1 avr. 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

par Luigi S

11 avr. 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.

par Akhil M

20 janv. 2021

Best code explanations. Any beginner in TensorFlow/deep learning can follow this course. Bits and bytes of TensorFlow Functional API have explained.

par Diego O S

20 mars 2021

The course is exceptional but I'll rather see more exercises for the students, just like common mathematics books have exercises at the end of it.

par Merlin S

7 juil. 2021

T​his doesn't feel to advanced, but its a nicely prepared course. I would like to have found this when I was getting into Tensorflow 2.

par Thomas N

6 juin 2021

Very useful content, labs help to understand concepts and I have started using stuff I learned about custom models in my work.

par Tung N

21 mars 2021

The instructors did e great job of explaining tensorflow advanced concepts as well as making the assignments simple to follow

par yarusx

25 janv. 2021

This is the first course in the Tensorflow series which brings something more than basics from open-source tutorials.

par Fahmi J

2 févr. 2021

Awesome courses, expanding the horizon of using TensorFlow for creating model, customizing, etc... Great!

par Himasha J

13 oct. 2021

Great course learned many new concepts on modeling , loss functions , model class . Highly recommended .

par Alysson M

2 juil. 2021

Amazing course. The knowledge I gained from completing it will be crucial for my next research projects!

par Manjunath S

21 mai 2021

Excellent Course! A good add on for people who have completed TensorFlow in Practice Specialisation.

par Nikolay S

28 févr. 2021

This course was fantastic! Laurence and DeepLearning.ai team did great job. Definitely recommended.

par Akshay K

28 déc. 2021

T​he courses are really helpful in understanding the basics of how to build custom things with TF.

par Shiva S B

29 juin 2021

very useful to implement our custom networks. Thanks for clear explanation and tangible examples

par Gonzalo G

19 févr. 2021

Excelent information really interesting and helpful for developing my projects with Tensorflow!

par Abdelrhman y a m

9 oct. 2021

f​antastic Course Teach you How u can use TensorFlow and Keras with Professional way so thanks

par Nancy S

31 déc. 2021

This course is super concise and useful. I've never thought Tensorflow can be such flexible!