InTDS ArchivebyShuyang XiangSuperposition: What Makes it Difficult to Explain Neural NetworkWhen there are more features than model dimensionsDec 29, 20243Dec 29, 20243
InTDS ArchivebyCristian LeoThe Math Behind Multi-Head Attention in TransformersDeep Dive into Multi-Head Attention, the secret element in Transformers and LLMs. Let’s explore its math, and build it from scratch.Jul 16, 20243Jul 16, 20243
Kaushik KoneripalliSatellite Image Data Augmentation using Stable Diffusion for Object detection & segmentation.Introduction:Sep 2, 20231Sep 2, 20231
KaushikladeImage Generation using Generative Adversarial Networks (GANs)Understanding the Generative Adversarial NetworkMar 24, 20211Mar 24, 20211
InTDS ArchivebySébastien GilbertStereo Vision System for 3D TrackingTwo eyes are all you needJan 8, 20235Jan 8, 20235
InTDS ArchivebyRicardo OcampoAutomatic Image Quality Assessment in PythonStep by step guide to code BRISQUE method for automatic image quality assessmentAug 28, 20187Aug 28, 20187
Insight in Plain SightEstimating the Homography Matrix with the Direct Linear Transform (DLT)The Direct Linear Transform (DLT) is an algorithm that solves a homogeneous system. We use it to estimate a homographyApr 6, 2022Apr 6, 2022