Learner Reviews & Feedback for TensorFlow for AI: Applying Image Convolution by Coursera Project Network
About the Course
This guided project course is part of the "Tensorflow for AI" series, and this series presents material that builds on the first course of DeepLearning.AI TensorFlow Developer Professional Certificate, which will help learners reinforce their skills and build more projects with Tensorflow.
In this 1.5-hour long project-based course, you will discover convolutions, apply filters to images, apply pooling layers, and try out the convolution and pooling techniques on real images to learn about how convolutions work. At the end of the project, you will get a bonus deep learning project implemented with Tensorflow. By the end of this project, you will have learned how convolutions work and how to create convolutional layers to prepare for your own deep learning projects using convolutional neural networks.
This class is for learners who want to use Python for building convolutional neural networks with TensorFlow, and for learners who are currently taking a basic deep learning course or have already finished a deep learning course and are searching for a knowledge-based course about convolutions in images with TensorFlow. Also, this project provides learners with needed knowledge about building convolutional neural networks and improves their skills in applying filters to images which helps them in fulfilling their career goals by adding this project to their portfolios....
1 - 5 of 5 Reviews for TensorFlow for AI: Applying Image Convolution
By Diego F B H
Oct 27, 2020
The way to explain convolutional operations is right and well demonstrated with visual results that are pretty comprehensible for any one person.
By Ed H C
Dec 7, 2020
I love this training but I need to review again and again I think to understand it fully.
By Rohit P
Dec 30, 2020
By Christos G
Dec 9, 2020
A very nice explanation of convolutional and pooling operations accompanied by visual results that are comprehensible and easily understandable.