Image Classification with PyTorch

سرفصل های دوره

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.

1. Course Overview

1. Course Overview

2. Preprocessing Images to Use in Machine Learning Models

01. Version Check

02. Module Overview

03. Prerequisites and Course Outline

04. Single Channel and Multichannel Images

05. Preprocessing Images to Train Robust Models

06. Setting up a Deep Learning VM

07. Image Preprocessing - Resizing and Rescaling Images

08. Cropping and Denoising Images

09. Standardizing Images in PyTorch

10. ZCA Whitening to Decorrelate Features

11. Image Transformations Using PyTorch Libraries

12. Normalizing Images Using Mean and Standard Deviation

13. Module Summary

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

1. Module Overview

2. Deep Neural Networks to Work with Images

3. Loading and Processing MNIST Images

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

5. Training a Fully Connected Image Classification Model

6. Module Summary

4. Introducing Convolutional Neural Networks

1. Module Overview

2. Local Receptive Fields

3. Understanding Convolution

4. Convolutional Layers

5. Pooling Layers

6. Typical CNN Architecture

7. Applying Convolutional and Pooling Layers

8. Module Summary

5. Building Convolutional Neural Networks for Image Classification

01. Module Overview

02. Zero Padding and Stride Size

03. Batch Normalization

04. Activation Functions

05. Feature Map Size Calculations

06. Preparing and Exploring Image Data

07. Setting up a Convolutional Neural Network

08. Training a CNN

09. Hyperparameter Tuning

10. Module Summary

6. Optimizing Image Classification with Hyperparameter Tuning

1. Module Overview

2. Preparing the CIFAR-10 Dataset

3. Setting up the CNN

4. Training the CNN

5. Choosing Different Activation Functions

6. Choosing Pooling Layers

7. Choosing Convolution Kernel Sizes

8. Additional Convolution Layers and Different Kernel Size

9. Module Summary

7. Performing Image Classification with Pre-trained Models

1. Module Overview

2. Transfer Learning

3. Using the Resnet-18 Pretrained Model

4. The Train Function to Find the Best Model Weights

5. Predictions Using Pretrained Models

6. Cleaning up Resources

7. Summary and Further Study

439,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: PluralSight