Sound Bytes Part 1: The ABCs of Sound and DigitizationDiving into the world of sound and how Deep Learning enhances our audio experienceOct 31, 2023Oct 31, 2023
The Future is Self-Supervised: An Introduction to DINOv2Self-supervised learning is a type of machine learning where systems are trained to predict or solve tasks using only a raw dataset…Jun 27, 2023Jun 27, 2023
Unveiling U-Net++: A Hands-On Guide on Image SegmentationImagine looking at an image and being able to decipher distinct regions, each representing a unique object or area of interest.Apr 28, 2023Apr 28, 2023
Going Deep: An Introduction to Depth Estimation with Fully Convolutional Residual NetworksHave you ever looked at a two-dimensional image and wished you could know the depth of the objects in the scene?Feb 27, 2023A response icon1Feb 27, 2023A response icon1
From Sound to Sight: Using Vision Transformers for Audio ClassificationLearn how to classify music genres using a custom Vision TransformerJan 3, 2023A response icon2Jan 3, 2023A response icon2
Maximizing Model Performance with Knowledge Distillation in PyTorchBoost your model’s accuracy and save on resources with knowledge distillation in PyTorchDec 8, 2022Dec 8, 2022
Model Compression: an Introduction to Teacher-Student Knowledge DistillationThere’s often the misconception that bigger and bigger models are always necessarily better. For instance, GPT-3 is trained on 570 GB of…Oct 28, 2022A response icon1Oct 28, 2022A response icon1
Multi-Task Deep Learning with PytorchAn introduction to multi-tasking for Neural NetworksSep 26, 2022Sep 26, 2022
ViT — VisionTransformer, a Pytorch implementationThe Attention is all you need’s paper revolutionized the world of Natural Language Processing and Transformer-based architecture became…Aug 19, 2022Aug 19, 2022
DropBlock: A Better Dropout for CNN’sA simple and effective regularization technique implemented in PytorchAug 8, 2022Aug 8, 2022
