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
629 évaluations
132 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.

PD
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.

Filtrer par :

126 - 137 sur 137 Avis pour Custom Models, Layers, and Loss Functions with TensorFlow

par Ignacio L

9 avr. 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.

par Alexander O

13 juin 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.

par David J

25 nov. 2021

In general, the entire course is well organized and boiled down to the most vital topics, so that the instructors could've given them in a given time. But, one thing that bothered me was the quiz. It's hard for me to tell that all quizzes were helpful for some of them were quite tricky to pick one answer or it was too specific or out of focus, in my opinion.

par mohit d

10 sept. 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

par David R

3 mai 2021

some good stuff, but too short and pretty easy

par JackT T

17 janv. 2021

Very nice course!

par Ian S

11 sept. 2021

​good course

par José L

15 avr. 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.

par Artem M

23 juil. 2021

Just an overview straigt from tensorflow documentation without any practical use cases or anything that has more value than completely free youtube tutorials

par Federico C

3 nov. 2021

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

par Ann A

5 janv. 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

par Varun S

30 déc. 2020

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