Why Data Augmentation Is Key for Vision, Language, and Audio AI
Explore data augmentation techniques that improve accuracy, robustness, and generalization in vision, language, and audio models.
DiffBIR: High Quality Blind Image Restoration with Generative Diffusion Prior
In this tutorial, we walkthrough the DiffBIR technique for blind image resoration. This Stable Diffusion based technique shows much promise, so follow along this tutorial to launch DiffBIR!
Instant Hair Transformation: HairFastGAN Revolutionizes Realistic and Rapid Hairstyle Changes
Experiment with new hairstyle and haircolor, with HairFastGAN. A novel approach to transfer a hairstyle from a reference image to another for virtual hair try-on.
Attention Mechanisms in Computer Vision: CBAM
This post covers an in-depth analysis of the convolution block attention module (CBAM).
Pooling In Convolutional Neural Networks
Explore the whys and the hows behind the process of pooling in CNN architectures, and compare 2 common techniques: max and average pooling.
Panoptic Segmentation: Unifying Semantic and Instance Segmentation
In this article learn about Panoptic segmentation, an advanced technique offers detailed image analysis, making it crucial for applications in autonomous driving, medical imaging, and more.
How to train and use a custom YOLOv7 model
We examine YOLOv7 & its features, learn how to prepare custom datasets for the model, and then build a YOLOv7 demo from scratch using NBA footage.
Training YOLOv8 on Custom Data
This blog post explores YOLOv8, comparing its architectural changes to YOLOv5. We’ll also demonstrate the new model’s Python API functionality by testing its detection capabilities on a Basketball dataset.
LeNet-5 from Scratch with PyTorch A Beginner’s Guide
A complete walkthrough to build LeNet-5 from scratch using PyTorch. Perfect for beginners exploring deep learning and CNNs.
Writing VGG from Scratch in PyTorch
We explore writing VGG from Scratch in PyTorch. Learn how to create, train, and evaluate a VGG neural network for CIFAR-100 image classification.