Part 6: Multi-label Classification with Binary Cross Entropy | Lesson: Binary Cross Entropy Loss

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 6, we’ll focus on multi-label classification for real-world imagery. Build a model that identifies multiple environmental labels from Amazon satellite images, applying binary cross-entropy for training and analyzing predictions 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 Check out the calendar for upcoming computer vision events: https://voxel51.com/computer-vision-events/ #computervision #ai #artificialintelligence #machinevision #machinelearning #datascience #opensource Contents of this video -- 00:00 - Intro 00:08 - Learning Goals and Overview 00:54 - Understanding Cross Entropy Loss 01:28 - Interpreting the Cross Entropy Formula 02:19 - Softmax and Single Label Classification 03:28 - Neural Network Outputs and Logits 04:14 - Distributing Probabilities Across Classes 04:51 - Binary Cross Entropy Explained 05:38 - Multilabel vs Binary Classification 07:07 - Sigmoid Activation for Binary Tasks 07:46 - PyTorch Approaches for Binary Classification 08:17 - Multilabel Classification with Independent Outputs 09:06 - Implementing Multilabel Classification in PyTorch 10:00 - Kaggle Practice: Satellite Image Classification 10:36 - Summary and Best Practices --