Image Classification with PyTorch

Focused View

Janani Ravi

3:04:49

158 View

1. Course Overview

1. Course Overview.mp4

01:50

2. Preprocessing Images to Use in Machine Learning Models

01. Version Check.mp4

00:16

02. Module Overview.mp4

01:09

03. Prerequisites and Course Outline.mp4

01:37

04. Single Channel and Multichannel Images.mp4

04:45

05. Preprocessing Images to Train Robust Models.mp4

05:32

06. Setting up a Deep Learning VM.mp4

04:38

07. Image Preprocessing - Resizing and Rescaling Images.mp4

06:35

08. Cropping and Denoising Images.mp4

04:38

09. Standardizing Images in PyTorch.mp4

04:50

10. ZCA Whitening to Decorrelate Features.mp4

02:52

11. Image Transformations Using PyTorch Libraries.mp4

03:09

12. Normalizing Images Using Mean and Standard Deviation.mp4

05:47

13. Module Summary.mp4

01:22

3. Understanding the Drawbacks of Using Deep Neural Networks with Images

1. Module Overview.mp4

01:29

2. Deep Neural Networks to Work with Images.mp4

06:06

3. Loading and Processing MNIST Images.mp4

06:43

4. Setting up a Fully Connected Neural Network for Image Classification.mp4

02:56

5. Training a Fully Connected Image Classification Model.mp4

05:06

6. Module Summary.mp4

01:19

4. Introducing Convolutional Neural Networks

1. Module Overview.mp4

01:16

2. Local Receptive Fields.mp4

02:18

3. Understanding Convolution.mp4

03:58

4. Convolutional Layers.mp4

06:50

5. Pooling Layers.mp4

03:28

6. Typical CNN Architecture.mp4

03:25

7. Applying Convolutional and Pooling Layers.mp4

07:48

8. Module Summary.mp4

01:20

5. Building Convolutional Neural Networks for Image Classification

01. Module Overview.mp4

01:16

02. Zero Padding and Stride Size.mp4

03:58

03. Batch Normalization.mp4

04:49

04. Activation Functions.mp4

02:04

05. Feature Map Size Calculations.mp4

02:12

06. Preparing and Exploring Image Data.mp4

04:01

07. Setting up a Convolutional Neural Network.mp4

05:49

08. Training a CNN.mp4

04:38

09. Hyperparameter Tuning.mp4

04:12

10. Module Summary.mp4

01:27

6. Optimizing Image Classification with Hyperparameter Tuning

1. Module Overview.mp4

01:05

2. Preparing the CIFAR-10 Dataset.mp4

03:31

3. Setting up the CNN.mp4

03:32

4. Training the CNN.mp4

04:25

5. Choosing Different Activation Functions.mp4

02:43

6. Choosing Pooling Layers.mp4

02:38

7. Choosing Convolution Kernel Sizes.mp4

02:31

8. Additional Convolution Layers and Different Kernel Size.mp4

03:57

9. Module Summary.mp4

01:12

7. Performing Image Classification with Pre-trained Models

1. Module Overview.mp4

01:12

2. Transfer Learning.mp4

05:08

3. Using the Resnet-18 Pretrained Model.mp4

05:45

4. The Train Function to Find the Best Model Weights.mp4

04:25

5. Predictions Using Pretrained Models.mp4

02:37

6. Cleaning up Resources.mp4

01:04

7. Summary and Further Study.mp4

01:36

Description

This course covers the parts of building enterprise-grade image classification systems like image pre-processing, picking between CNNs and DNNs, calculating output dimensions of CNNs, and leveraging pre-trained models using PyTorch transfer learning.

What You'll Learn?

Perhaps the most ground-breaking advances in machine learnings have come from applying machine learning to classification problems. In this course, Image Classification with PyTorch, you will gain the ability to design and implement image classifications using PyTorch, which is fast emerging as a popular choice for building deep learning models owing to its flexibility, ease-of-use and built-in support for optimized hardware such as GPUs. First, you will learn how images can be represented as 4-D tensors and then pre-processed to get the best out of ML algorithms. Next, you will discover how to implement image classification using Dense Neural Networks; you will then understand and overcome the associated pitfalls using Convolutional Neural Networks (CNNs). Finally, you will round out the course by understanding and using the most powerful and popular CNN architectures such as VGG, AlexNet, DenseNet and so on, and leveraging PyTorch’s support for transfer learning. When you’re finished with this course, you will have the skills and knowledge to design and implement efficient and powerful image classification solutions using a range of neural network architectures in PyTorch.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Python

Janani Ravi

Instructor's Courses

Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework. After spending years working in tech in the Bay Area, New York, and Singapore at companies such as Microsoft, Google, and Flipkart, Janani finally decided to combine her love for technology with her passion for teaching. She is now the co-founder of Loonycorn, a content studio focused on providing high-quality content for technical skill development. Loonycorn is working on developing an engine (patent filed) to automate animations for presentations and educational content.

Pluralsight

View courses Pluralsight

Pluralsight, LLC is an American privately held online education company that offers a variety of video training courses for software developers, IT administrators, and creative professionals through its website. Founded in 2004 by Aaron Skonnard, Keith Brown, Fritz Onion, and Bill Williams, the company has its headquarters in Farmington, Utah. As of July 2018, it uses more than 1,400 subject-matter experts as authors, and offers more than 7,000 courses in its catalog. Since first moving its courses online in 2007, the company has expanded, developing a full enterprise platform, and adding skills assessment modules.