Efficient Track Anything

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

A concise but complete full-attention transformer with a set of promising experimental features from various papers

VisualTorch aims to help visualize Torch-based neural network architectures.

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Segment Anything in Medical Images

ZenML 🙏: The bridge between ML and Ops. https://zenml.io.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Uses Harris Hawk and Whale Nature Inspired Algorithm to Train the weights of Neural Network.

Code release for CVPR'24 submission 'OmniGlue'

this is a demo

Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, ResNet features.

Modern Control