Dive into a comprehensive 2.5-hour tutorial on two-dimensional convolution and convolutional neural networks. Learn the fundamentals of convolution operations, explore the Softmax neural network layer, and understand batch normalization. Build a 2D convolutional neural network from scratch, starting with the basics and progressing through a step-by-step implementation using the MNIST digits dataset. Gain insights into model architecture, pre-trained model results, and analyze examples of successes and failures. Discover the advantages of using Cottonwood framework, set up training code, add and connect layers, and implement training and testing loops. Explore loss history visualization, text summaries, and learn how to collect and render examples. Conclude with a Cottonwood code tour and a handy cheatsheet for quick reference.
Overview
Syllabus
How Convolution Works.
The Softmax neural network layer.
Batch normalization.
Build a 2D convolutional neural network, part 1: Getting started.
Build a 2D convolutional neural network, part 2: Overview.
Build a 2D convolutional neural network, part 3: MNIST digits.
Build a 2D convolutional neural network, part 4: Model overview.
Build a 2D convolutional neural network, part 5: Pre-trained model results.
Build a 2D convolutional neural network, part 6: Examples of successes and failures.
Build a 2D convolutional neural network, part 7: Why Cottonwood?.
Build a 2D convolutional neural network, part 8: Training code setup.
Build a 2D convolutional neural network, part 9: Adding layers.
Build a 2D convolutional neural network, part 10: Connecting layers.
Build a 2D convolutional neural network, part 11: The training loop.
Build a 2D convolutional neural network, part 12: Testing loop.
Build a 2D convolutional neural network, part 13: Loss history and text summary.
Build a 2D convolutional neural network, part 14: Collecting examples.
Build a 2D convolutional neural network, part 15: Rendering examples.
Build a 2D convolutional neural network, part 16: Cottonwood code tour.
Build a 2D convolutional neural network, part 17: Cottonwood cheatsheet.
Taught by
Brandon Rohrer
Related Courses
-
Deep Learning with Python and PyTorch.
-
Hot Dog or Not Hot Dog – Convolutional Neural Network Course for Beginners
-
Deep Learning with PyTorch : Image Segmentation
-
PyTorch for Deep Learning & Machine Learning – Full Course
-
TensorFlow for Computer Vision - Full Tutorial for Beginners
-
Object Localization with TensorFlow
