-
MBS Survey Software Ltd
- London, United Kingdom
- https://kirans.me
- https://orcid.org/0000-0003-3739-5985
- in/kiranshahi
- https://stackoverflow.com/users/5740382/kiran-shahi
Highlights
Lists (11)
Sort Name ascending (A-Z)
- All languages
- API Blueprint
- Assembly
- Astro
- C
- C#
- C++
- CSS
- Crystal
- Cuda
- Cython
- D
- Dart
- Dhall
- Dockerfile
- Elixir
- F#
- Go
- HTML
- Haskell
- Inno Setup
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MATLAB
- MDX
- Markdown
- OCaml
- PHP
- PostScript
- PowerShell
- Prolog
- Pug
- Python
- R
- Racket
- Rich Text Format
- Ruby
- Rust
- SCSS
- Shell
- Swift
- TeX
- TypeScript
- V
- Vala
- Vim Script
- Vue
- Wikitext
- Zig
Starred repositories
Repository containing all necessary codes to get started on the SoccerNet Tracking challenge. This repository also contains benchmark methods to get started.
How much can 150 flowers tell you? Nested cross-validation, significance tests and error analysis on the Iris dataset
3D U-Net (MONAI) that segments T1 brain MRI into 44 FreeSurfer structures on OASIS-3, compares a full and a reduced label set, and checks volume agreement with FreeSurfer.
Predicting brain age from T1 MRI with a 3D CNN, with bias correction and scanner analysis (IXI dataset)
How a CNN works, step by step: one MRI image through convolution, ReLU, pooling and softmax, built from scratch in NumPy
How a Vision Transformer works, step by step: one MRI image through patches, self-attention and [CLS], re-built in NumPy
How self-supervised learning works: a masked autoencoder finds brain lesions with zero labels and beats training from scratch with few labels
How semi-supervised learning works: FixMatch on brain-MRI-style scans, why it fails on subtle lesions, and how to fix it
Heart disease prediction using UCI dataset
Does a COVID-19 chest X-ray classifier look at the lungs? A DenseNet121 scores 0.994 AUC, but still reaches 0.983 with the central lung region hidden, and file metadata alone reaches 0.989. A short…
Hands-on Jupyter notebooks teaching MRI reconstruction: from k-space and the Fourier transform to compressed sensing and deep learning. Runs in Google Colab with simulated data.
Image processing algorithms implemented in Python and NumPy and checked against OpenCV
Eight hands-on Jupyter lessons that build classic neural networks from scratch in NumPy: perceptrons, backpropagation, Hebbian learning, BAM and fuzzy sets.
Convert images to CSV files of pixel values and back, for grayscale and colour images. Lossless round trip.
Colouring label images and FreeSurfer brain segmentations with custom colour maps and lookup tables
Label-free and label-efficient performance monitoring of breast-ultrasound classifiers across five public datasets from five countries.
Measure the volume of every labelled structure in a 3D segmentation, with names from a FreeSurfer lookup table.
In-domain masked-volume self-supervised pretraining for label-efficient whole-brain MRI parcellation. 3D U-Net on OASIS-3, tested with 10, 25, 50 and 104 labeled scans under 5-fold cross-validation…
Angular & Tailwind CSS Admin Dashboard Starter Kit, Free and Open Source
Free, open-source admin dashboard template crafted with Angular and Tailwind CSS. Includes essential UI components, elements, and pre-built pages to create a sleek, modern admin panel and dashboard…
Free Tailwind CSS v4 components for your next project, designed to enhance your web development with the latest features and styles 🚀
Elevate your AI research writing, no more tedious polishing ✨
Light your way in Deep Learning with Torch 🔦
A paper list of some recent Transformer-based CV works.
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
PDFsharp and MigraDoc Foundation for .NET 6 and .NET Framework
The "Simple HTML to PDF" project is a lightweight library and NuGet package for .NET that enables easy conversion of HTML content to PDF documents using the wkhtmltopdf command-line tool, making it…