Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Deep Learning for Image Classification in Python with CNN
Rating: 4.0 out of 5(25 ratings)
1,095 students
Created byKarthik Karunakaran, Ph.D.
Last updated 12/2022
English

What you'll learn

  • Understand the fundamentals of Convolutional Neural Networks (CNNs)
  • Build and train a CNN using Keras with Tensorflow as a backend using Google Colab
  • Assess the performance of trained CNN
  • Learn to use the trained model to predict the class of a new set of image data

Course content

2 sections • 35 lectures • 1h 5m total length

  • Introduction1:54
  • Artificial Intelligence2:05
  • Machine Learning1:03
  • Deep Learning2:47

    Deep learning emerged as a powerful subset of machine learning, expanding neural networks with multiple hidden layers to improve image classification and sequence data tasks through convolutional and recurrent networks.

  • Artificial Neural Networks (Conventional / Traditional)2:30
  • Backward Propagation of Errors0:45
  • Gradient Descent1:22
  • Stochastic Gradient Descent0:50
  • Convolutional Neural Networks (CNN)0:53
  • Input Layer, Convolutional Layer1:15

    Receive images with the input layer (32x32x1 grayscale or 224x224x3 color) and apply convolution with kernels to extract features via elementwise multiplication and summation, performing sharpening, blurring, and edge detection.

  • Pooling Layer, Activation Function Layer1:38
  • Fully Connected Layers / Dense Layer, Dropout Layer0:58
  • Image Classification and its Applications1:37
  • How image classification is done?0:58
  • Transfer Learning3:02
  • Architecture of ResNet (Residual Networks)2:03

Requirements

  • Basic knowledge of Python Programming

Description

Welcome to the "Deep Learning for Image Classification in Python with CNN" course. In this course, you will learn how to create a Convolutional Neural Network (CNN) in Keras with a TensorFlow backend from scratch, and you will learn to train CNNs to solve custom Image Classification 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 convolutional neural 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 image classification 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 utilize your time wisely.

Happy learning.


How much does an Image Processing Engineer make in the USA? (Source: Talent)

The average image processing engineer salary in the USA is $125,550 per year or $64.38 per hour. Entry-level positions start at $102,500 per year, while most experienced workers make up to $174,160 per year.

Who this course is for:

  • Beginners starting out to the field of Deep Learning
  • Industry professionals and aspiring data scientists
  • People who want to know how to write their image classification code

Report abuse