Chevron Left
Back to Convolutional Neural Networks in TensorFlow

Learner Reviews & Feedback for Convolutional Neural Networks in TensorFlow by DeepLearning.AI

4.7
stars
8,024 ratings

About the Course

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This course is part of the upcoming Machine Learning in Tensorflow Specialization and will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In Course 2 of the deeplearning.ai TensorFlow Specialization, you will learn advanced techniques to improve the computer vision model you built in Course 1. You will explore how to work with real-world images in different shapes and sizes, visualize the journey of an image through convolutions to understand how a computer “sees” information, plot loss and accuracy, and explore strategies to prevent overfitting, including augmentation and dropout. Finally, Course 2 will introduce you to transfer learning and how learned features can be extracted from models. The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization....

Top reviews

JM

Sep 11, 2019

great introductory stuff, great way to keep in touch with tensorflow's new tools, and the instructor is absolutely phenomenal. love the enthusiasm and the interactions with andrew are a joy to watch.

RB

Mar 14, 2020

Nice experience taking this course. Precise and to the point introduction of topics and a really nice head start into practical aspects of Computer Vision and using the amazing tensorflow framework..

Filter by:

826 - 850 of 1,245 Reviews for Convolutional Neural Networks in TensorFlow

By Zain A

Mar 19, 2023

noice

By Sarath S

Sep 16, 2021

great

By Ben B

May 6, 2020

Great

By Wira A S

May 3, 2020

great

By Dini P U

Nov 2, 2023

good

By SRIKANTH K

Jun 28, 2022

good

By Muhammad N

Aug 10, 2021

nice

By Ken T

Aug 8, 2021

good

By Suci A S

Jun 19, 2021

good

By Alivia Z

Apr 25, 2021

wowo

By Roberto

Apr 16, 2021

good

By Ahmad H N

Mar 26, 2021

Good

By Indah D S

Mar 19, 2021

cool

By tg l

Jan 17, 2021

good

By Johnnie W

Sep 22, 2020

good

By RAGHUVEER S D

Jul 25, 2020

good

By Rifat R

Jun 7, 2020

Good

By PANG M Q

May 29, 2020

good

By Amit K

May 13, 2020

Good

By Nho N

Mar 17, 2020

good

By zhenzhen w

Nov 18, 2019

nice

By Jurassic

Sep 6, 2019

good

By Ming G

Aug 20, 2019

gj

By Islam U

Jan 24, 2021

The course definitely teaches interesting techniques (Dropout, Transfer Learning) and tools (use of ImageDataGenerator). What i think would be an improment point is further tips on how to actually achieve a state of art (or really high quality) models. For example for full Cats and Dogs dataset from Kaggle, there was an optional ungraded work that asked to achieve over 99.9% accuracy on both training/validated datasets. It would be great if some tips on how to achieve this would be given. Maybe some discussion of network architectures that can achieve this, as this subject is not always covered, while it plays probably a dominant role whether you make it or break it. Otherwise, i liked the course and thanks for wonderfull explanations.

P.s. week 4 final graded task is structured suboptimally, so maybe it can be reviewed, as many people struggling with many sorts of errors.

By Uriel S

Mar 6, 2023

The course itself was good, but the assignments were worse than in the first course. You are basically forced to either use google colab during some of the tests and during some of the practices. I dislike this, specially because my machine can train the models faster, without using colab's resources which i might need for something else. I also find it a bit annoying considering that in the previous course they provided a virtual env you could use.

Additionally some of the assignments weren't quite solvable with the content shown during the course. It wouldn't be a big deal, but since training the model was done on colab when you had to try new things, for example to reach a higher accuracy, it was slow and time consuming specially with big datasets.