We humans have an amazing ability to rapidly interpret and put words into context while we exchange our thoughts and interact with others and the credit goes to the best computer we have ever know : A Human Brain. Over the years Scientists have carried out various research and have found that it involves a huge […]
Modern web applications rely heavily on APIs — the bridges between systems. When building these APIs, following established design principles ensures they remain predictable, reliable, and maintainable over time.This article breaks down three key aspects of high-quality API design: REST, OpenAPI 3.1, Semantic Versioning, and Idempotent Design. REST — The Foundation of Modern APIs REST […]
Are you tired of having a dozen tabs open, struggling to find the one you need, while your browser chews through your computer’s memory? You’re not alone. Tab overload is a common problem for developers, researchers, and just about anyone who spends their day online. We’ve all been there. You start with a handful of […]
A few days ago, while scrolling through LinkedIn, I stumbled upon something interesting. I saw developers excitedly talking about a new Python package manager called uv. At first, I thought, “Do we really need another package manager? Isn’t pip already doing the job?” I have been using it for many years now at my work and it’s the standard.But, people […]
It was a Wednesday afternoon, and the whole city was buzzing with Ganesh Chaturthi vibes. Since it was a holiday, I suddenly found myself with a few free hours. Fresh from the morning’s celebrations, I had that restless energy — the kind that makes you want to tinker and build something. Normally, spinning up a […]
In the previous blog, we explored why decomposing a time series and applying adjustments can simplify patterns and improve forecasting accuracy. In this post, we’ll begin diving into those adjustments—starting with one of the most commonly overlooked yet critical techniques: calendar adjustments. Calendar adjustments are used to remove effects that come from the way the […]
Time series data can exhibit a variety of patterns, and it is often helpful to split a time series into several components. The primary components of a time series are:– Trend – the long-term movement or direction in the data– Seasonality – recurring short-term cycles or patterns– Cycles – longer-term fluctuations not of fixed frequency– […]
So lets first understand what is object detection? Object Detection models are one of the most widely used models among other computer vision tasks. Object detection is a task where we want our model to distinguish the foreground objects from the background and predict the locations and the categories for the objects present in the […]
Transformers have been the de-facto for NLP tasks, various pretrained models are available for translation, text generation, summarization and more. The models can be downloaded and fine tuned in your deep learning framework of choice as it plays nicely with Tensorflow, Pytorch and Jax. Transformers aren’t just for text any more- they can handle a […]
Spatial Transformer The spatial transformer module consists of layers of neural networks that can spatially transform an image. These spatial transformations include cropping, scaling, rotations, and translations etc CNNs perform poorly when the input data contains so much variation. One of the solutions to this is the max-pooling layer. But then again, max-pooling layers do […]
Recently, while exploring computer vision got a chance to train YoloV3 on custom dataset for object detection. We custom trained the YOLO V3 to detect following classes:– hardhat– vest– mask– boots Below is a short video demonstrating how amazingly the model is able to detect these objects. Code for this can be found here.
Divya's Blog 