Dive into the world of Convolutional Neural Networks (CNNs) with this comprehensive 35-minute video tutorial. Explore the fundamental concepts behind CNNs, their significance in computer vision, and their practical implementation using Python and PyTorch. Learn about image preprocessing techniques, essential CNN components including pooling layers, and the architecture of notable networks like LeNet, AlexNet, VGGNet, and ResNet. Follow along with hands-on demonstrations to build, train, and use CNNs for image classification tasks. Gain insights into normalizing images for CNN input, creating efficient data loading pipelines, and setting up training parameters. By the end of this tutorial, acquire the skills to implement and leverage CNNs for various computer vision applications.
Overview
Syllabus
Intro
What Makes a Convolutional Neural Network
Image preprocessing for CNNs
Common components of a CNN
Components: pooling layers
Building the CNN with PyTorch
Notable CNNs
Implementation of CNNs
Image Preprocessing for CNNs
How to normalize images for CNN input
Image preprocessing pipeline with pytorch
Pytorch data loading pipeline for CNNs
Building the CNN with PyTorch
CNN training parameters
CNN training loop
Using PyTorch CNN for inference
Taught by
James Briggs
