Traffic Sign Classification Using Deep Learning in Python/Keras
Offered By: Coursera Project Network via Coursera
Course Description
Overview
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.
Syllabus
- Classify Traffic Signs Using Deep Learning for Self-Driving Cars
- In this hands-on project, we will train deep learning models known as Convolutional Neural Networks (CNNs) to classify 43 traffic sign images. This project could be practically applied to self-driving cars. In this hands-on project we will go through the following tasks: (1) Import libraries and datasets (2) Images visualization (3) Convert images to gray-scale and perform normalization (4) Build deep learning model (5) Compile and train deep learning model (6) Assess trained model performance
Taught by
Ryan Ahmed
Related Courses
Feature EngineeringGoogle Cloud via Coursera TensorFlow on Google Cloud
Google Cloud via Coursera Deep Learning Fundamentals with Keras
IBM via edX Intro to TensorFlow 日本語版
Google Cloud via Coursera Feature Engineering 日本語版
Google Cloud via Coursera