Love is an enigmatic and unifying force. It transforms us from mere pieces into something whole. Just like water is to life — vital and essential — so too is love for our existence. Today, I am privileged to share the basics of cryptography through a captivating tale—a love story between Bob and Alice. In this narrative, just as in real life, their love will not be without challenges. And it's within these hurdles that we can offer insights into how cryptography helps keep communication private and secure. Much like the complexities of love, cryptography is imperfect yet indispensable. This tutorial takes all of us (no prerequisite) together to explore how Bob and Alice use cryptographic methods to protect their most precious secrets from prying eyes. Challenges will arise—eavesdroppers, impostors, even betrayals. And that’s where we step in—to protect their love, one encrypted message at a time. #cryptography ## What is covered in this tutorial - - Symmetric Cryptography - Key Diversification - Asymmetric Cryptography - Certificates - Self-Signed Certificates - Man-in-the-middle attack - Certificate Authorities - PKI

This tutorial explains a training technique that helps in dealing with objects whose center lies on the boundaries of the grid cell in the feature map. This technique falls under the "Bag of Freebies" category as it adds almost zero FLOPS (additional computation) to achieve higher accuracy during test time. Pre-requisite: Bounding Box Prediction https://youtu.be/-nLJyxhl8bY?si=Fv7Bfgxd1I-atZF0 Important links: Paper - https://arxiv.org/abs/2004.10934 Threads with a lot of discussion on this subject: https://github.com/AlexeyAB/darknet/issues/3293 https://github.com/ultralytics/yolov5/issues/528

This tutorial provides an in-depth and visual explanation of the three Bounding Box loss functions. Other than the loss functions you would be able to learn about computing per sample gradients using the new Pytorch API. Resources: Colab notebook https://colab.research.google.com/drive/1GAXn6tbd7rKZ1iuUK1pIom_R9rTH1eVU?usp=sharing Repo with results of training using different loss functions https://github.com/ksachdeva/od-loss-exp DIoU repo with matlab code and author's comment: https://github.com/Zzh-tju/DIoU https://github.com/Zzh-tju/DIoU/issues/22

This tutorial explains the purpose of the neck component in the object detection neural networks. In this video, I explain the architecture that was specified in Feature Pyramid Network paper. Link to the paper [Feature Pyramid Network for object detection] https://arxiv.org/abs/1612.03144 The code snippets and full module implementation can be found in this colab notebook: https://colab.research.google.com/drive/1sSlTMwEoCM7zE2_f7K36BDtFARGxugL2?usp=sharing The torchvision has a more flexible implementation which would take more than 3 feature layers from backbone https://pytorch.org/vision/main/generated/torchvision.ops.FeaturePyramidNetwork.html

This tutorial explains finer details about the bounding box coordinate predictions using visual cues.

This tutorial highlights challenges in object detection training, especially how to associate a predicted box with the ground truth box. It then shows and explains the need for injecting some domain/human knowledge as a starting point for the predicted box.

This tutorial explains how to compute the similarity between 2 bounding boxes using Jaccard Index, commonly known as Intersection over Union in the field of object detection.

This is a continuation of the Detection Head tutorial that explains how to write the code such that you can avoid ugly indexing into the tensors and also have more maintainable and extensible components. It would beneficial to first watch the DetectionHead tutorial Link to the DetectionHead tutorial: https://www.youtube.com/watch?v=U6rpkdVm21E Link to the Google Colab notebook: https://colab.research.google.com/drive/1AQzlSAK5vlNnvmkO1VDXaU8s9gTyRAGU?usp=sharing

This tutorial shows you how to make the detection head(s) that takes features from the backbone or the neck. Link to the Google Colab notebook: https://colab.research.google.com/drive/1KwmWRAsZPBK6G4zQ6JPAbfWEFulVTtRI?usp=sharing

This tutorial introduces to you a fantastic library called einops. Einops provides a consistent API to do reshape, permute, squeeze, unsqueeze and enhances the readabilty of your tensor operations. https://einops.rocks/ Google colab notebook that has examples shown in the tutorial: https://colab.research.google.com/drive/1aWZpF11z28KlgJZRz8-yE0kfdLCcY2d3?usp=sharing

This tutorial explains how to do image pre-processing and data augmentation using Albumentations library. Google Colab notebook: https://colab.research.google.com/drive/1FoQKHuYuuKNyDLJD35-diXW4435DTbJp?usp=sharing

This tutorial goes over various bounding box formats used in Object Detection. Link the Google Colab notebook: https://colab.research.google.com/drive/1GQTmjBuixxo_67WbvwNp2PdCEEsheE9s?usp=sharing

This is an introductory video on object detection which is a computer vision task to localize and identify objects in images. Notes - * I have intentionally not talked about 2-stage detectors. * There will be follow-up tutorials that dedicated to individual concepts

A visual explanation of why, what, and how of softmax function. Also as a bonus is explained the notion of temperature.

In this tutorial, the need & mechanics behind Grouped Convolution is explained with visual cues. Then the understanding is validated by looking at the weights generated by the PyTorch Conv layer and by performing the operations manually using NumPy. Google colab notebook: https://colab.research.google.com/drive/1AUrTK622287NaKHij0YqOCvcdi6gVxhc?usp=sharing Playlist: https://www.youtube.com/watch?v=6SizUUfY3Qo&list=PLivJwLo9VCUItCi3hVjN6cpbmHuY_BQJK #groupconvolution #deeplearning #cnn