Penn Health Institute > Development > Data Science > Object Detection on Custom Dataset With Keras Using Python

3.9 out of 5

13 reviews on Udemy

Object Detection on Custom Dataset With Keras Using Python

Deep Learning-Based Object Detection for Computer Vision with Keras and TensorFlow in Google Colab Platform : Hands-on

Instructor:

Karthik K

1,028 students enrolled

English

Understand the fundamentals of Vision Transformer (ViT)

Build and train a deep learning network using Keras with Tensorflow as a backend using Google Colab

Assess the performance of trained model

Learn to use the trained model to predict the object of a new image data set

Welcome to the “Object Detection on Custom Dataset with Keras using Python” course. In this course, you will learn how to create a Vision Transformer in Keras with a TensorFlow backend from scratch, and you will learn to train the deep learning model to solve object detection problems. Please note that you don’t need a high-powered workstation to learn this course. We will be carrying out the entire project in the Google Colab environment, which is free. You only need an internet connection and a free Gmail account to complete this course. This is a practical course, we will focus on Python programming, and you will understand every part of the program very well. By the end of this course, you will be able to build and train the deep learning network using Keras with TensorFlow as a backend. You will also be able to visualise data and use the model to make predictions on new data. This object detection course is practical and directly applicable to many industries. You can add this project to your portfolio of projects which is essential for your following job interview. This course is designed most straightforwardly to utilise your time wisely. Happy learning.

How much does a Deep Learning Engineer make? (Source: salary(dot)com)

The average Deep Learning Engineer’s salary is $143,793 as of August 29, 2022, but the salary range typically falls between $124,179 and $165,138.

Fundamentals

Introduction

Artificial Intelligence

Machine Learning

Deep Learning

Object Detection

How object detection is done?

Vision Transformer Architecture

Building, Evaluating and Predicting Object Detection Model

Download Dataset

What is inside leopards_images folder?

What is inside leopards_annotation folder?

What is the .h5 file?

Object Detection Python Code

Enabling GPU in Google Colab

Is GPU connected to Colab notebook?

Connect Google Colab with Google Drive

Download TensorFlow Addons

Check the Number of Images in the Dataset

Preparing the Dataset

Visualizing a Sample Image in the Dataset

Building Multilayer-Perceptron (MLP) Network

Building the Patch Creation Layer

Displaying Patches for an Input Image

Building the Patch Encoding Layer

Building Vision Transformer

Compiling and Displaying Model

Training the Model

Evaluating : Intersection over Union / Jaccard Index

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!

3.9