MIMIC-Note-Extract: A Large-Scale Structured Dataset Extracted from MIMIC-IV-Note Discharge Summaries

A high-performance, 100% client-side tool for removing Gemini AI image & video watermarks. Built with pure JavaScript using mathematically precise Reverse Alpha Blending. / 基于 JavaScript 的纯浏览器端 Gem…

Fast and easy focus stacking

SATML 2025 | Differentially Private Active Learning | Official Implementation

This is a segmentation pipeline to automatically, and robustly, segment the whole spine in T2w sagittal images.

Torso Processing ToolBox

VIBESegmentator: Full Torso Segmentation for the NAKO and UK Biobank in Volumetric Interpolated Breath-hold Examination Body Images

Memory mapped numpy arrays of varying shapes

Google Drive public file downloader when curl/wget fails.

Measures and metrics for image2image tasks. PyTorch.

darktable is an open source photography workflow application and raw developer

🗂 Split folders with files (i.e. images) into training, validation and test (dataset) folders

Differentially private training of residual networks with scale normalization

A modular codebase for the benchmarking of popular machine learning design choices in differentially private learning systems. Codebase for the Paper: SmoothNets: Optimizing CNN architecture design…

Source code for HXP CTF 2020 Challenge Find the chicken

This library augments road images to introduce various real world scenarios that pose challenges for training neural networks of Autonomous vehicles. Automold is created to train CNNs in specific w…

Visual Studio Code

Sparse Convolutions for Semantic 3D Instance Segmentation

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Small project to keep track of the status of my series.

Convert models from MatConvNet to PyTorch

Geometry-Aware Learning of Maps for Camera Localization (CVPR2018)

Image-to-Image Translation in PyTorch