Part 9 - Model Optimization | Lesson: Data Augmentation & Regularization
Join us for the "Practical Computer Vision with PyTorch and FiftyOne" workshop series. This is a 12-part, hands-on series that teaches you how to work with images, build and train models, and explore tasks like image classification, segmentation, object detection, and image generation. Each session combines straightforward explanations with practical coding in PyTorch and FiftyOne, allowing you to learn core skills in computer vision and apply them to real-world tasks.
In Part 9, we’ll introduce optimization strategies including data augmentation, dropout, batch normalization, and transfer learning. Implement an augmented network using a fruits dataset with models like VGG-16 and ResNet18, and analyze the results with FiftyOne.
These are hands-on maker workshops that make use of GitHub Codespaces, Kaggle notebooks, and Google Colab environments, so no local installation is required (though you are welcome to work locally if preferred!)
Learn more about FiftyOne: https://github.com/voxel51/fiftyone
GitHub Repo: https://github.com/andandandand/pract...
Check out the calendar for upcoming computer vision events: https://voxel51.com/computer-vision-e...
#computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #opensource
00:00 - Intro
00:06 - What is Data Augmentation?
00:24 - Learning Goals and Transform Types
00:48 - Label Preservation in Augmented Images
01:56 - Generalization Through Random Transformations
03:01 - Regularization Effects with Augmentation
03:45 - Affine Transformations Overview
04:59 - Rotation Transformation Explained
06:03 - Translation Transformation
07:09 - Scaling and Its Effects
08:49 - Shear Transformation
09:35 - Flipping and Combined Transforms
10:54 - Random Crop vs Random Resize Crop
11:49 - Risks of Careless Augmentation
13:00 - Validation Set Augmentation Warning
13:45 - Avoiding Data Leakage Between Splits
15:08 - Summary and Best Practices