Chevron Left
Back to Traffic Sign Classification Using Deep Learning in Python/Keras

Learner Reviews & Feedback for Traffic Sign Classification Using Deep Learning in Python/Keras by Coursera Project Network

4.6
stars
375 ratings

About the Course

In this 1-hour long project-based course, you will be able to: - Understand the theory and intuition behind Convolutional Neural Networks (CNNs). - Import Key libraries, dataset and visualize images. - Perform image normalization and convert from color-scaled to gray-scaled images. - Build a Convolutional Neural Network using Keras with Tensorflow 2.0 as a backend. - Compile and fit Deep Learning model to training data. - Assess the performance of trained CNN and ensure its generalization using various KPIs. - Improve network performance using regularization techniques such as dropout....

Top reviews

NB

Jun 20, 2020

Very nice course, everything was explained perfectly.

Can also add about testing the trained model using external data, like if we want to give an input and perform prediction then how it is done.

FF

May 21, 2020

Instructor was efficient in delivering the knowledge and I understood it very well. The exercises were also great. Overall, my aim for taking this course had been accomplished.

Filter by:

51 - 55 of 55 Reviews for Traffic Sign Classification Using Deep Learning in Python/Keras

By G S

•

Jun 3, 2020

Resources might have been provided as the could desktop was not function properly and there was no proper response from instructor for messages

By Gurpreet S N

•

Jun 1, 2020

I feel few more details can be added to the course especially while explaining CNN

By Aritra S

•

May 31, 2020

The external tool is not good. It is very slow and not user-friendly.

By KUNAL S

•

Aug 26, 2020

There is no support on the discussion forums and the dataset is also wrong. Poorly designed and its all spoon fed. There is no use of wasting time on this. It is a useless course because you will not learn anything from it.

By raghu r m

•

May 10, 2020

not completely explaining the methods being used.