Stars
VBTI-development / onedl-mmrotate
Forked from open-mmlab/mmrotateOneDL Lab Rotated Object Detection Toolbox and Benchmark
Architected a distributed notebook execution environment simulating Kaggle Kernels. Utilized the Kubernetes K8s API for dynamic pod orchestration and WebSockets for real-time streaming of code exec…
Python implementation of TurboQuant (arXiv 2504.19874). Data-oblivious, near-optimal 1–4 bit vector quantization for streaming KV-caches and databases.
A macOS menu bar app that helps protect your eyes using the 20-20-20 rule - every 20 minutes, look at something 20 feet away for 20 seconds.
graphzero: High performance C++ backed python library for graphs
Resources for deep learning with satellite & aerial imagery
A method to optimize the current SAR ship detection pipeline using the DEtection TRansformer (DETR) model.
Project on the implementation of deep-learning models for ship detection on SAR images.
A high-throughput and memory-efficient inference and serving engine for LLMs
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Script collection for use with Scriptable App as IOS Widget
Unified multimodal backend for AI data apps
Testcontainers is a Python library that providing a friendly API to run Docker container. It is designed to create runtime environment to use during your automatic tests.
Access Google Colab compute from your local VSCode
Run Segment Anything Model 2 on a live video stream
dnth / DEIMKit
Forked from Intellindust-AI-Lab/DEIMDEIMKit is a Python package that provides a wrapper for DEIM: DETR with Improved Matching for Fast Convergence. Check out the original repo for more details.
(Google Play Store App) Pipeline to convert real-life chess boards into 2D digital format (FEN) from images and live camera feeds. The system has two versions: a real-time pipeline using OAK-D Lite…
[VISAPP 2024] Official implementation of "End-to-End Chess Recognition".
Image Background Removal Toolkit - Open Source and API Models
Rembg is a tool to remove images background
FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
OpenTofu lets you declaratively manage your cloud infrastructure.
The OpenTF Manifesto expresses concern over HashiCorp's switch of the Terraform license from open-source to the Business Source License (BSL) and calls for the tool's return to a truly open-source …
Flexible Python configuration system. The last one you will ever need.
The simplest, fastest repository for training/finetuning small-sized VLMs.