PietroVitiello

the-algorithm

Source code for Twitter's Recommendation Algorithm

llama3

The official Meta Llama 3 GitHub site

yfinance

Download market data from Yahoo! Finance's API

Open3D

Open3D: A Modern Library for 3D Data Processing

ImageBind

ImageBind One Embedding Space to Bind Them All

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

HEBO

Bayesian optimisation & Reinforcement Learning library developped by Huawei Noah's Ark Lab

awesome-hand-pose-estimation

Awesome work on hand pose estimation/tracking

BlenderProc

A procedural Blender pipeline for photorealistic training image generation

LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

koila

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

lang-segment-anything

SAM with text prompt

dora

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.

vision-based-robotic-grasping

Related papers and codes for vision-based robotic grasping

ObjectPoseEstimationSummary

Resources (papers, datasets, rendering methods) in the domain of object pose estimation.

dino-vit-features

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".

pytorch-lamb

Implementation of https://arxiv.org/abs/1904.00962

create-tsi

Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.

ndf_robot

Implementation of the method proposed in the paper "Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation"

ml-aspanformer

nope

[CVPR 2024] PyTorch implementation of NOPE: Novel Object Pose Estimation from a Single Image

UnseenObjectClustering

Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation

owlvit_segment_anything

Combining OwlViT with Segment Anything - Open-vocabulary Detection and Segmentation (Text-conditioned, and Image-conditioned)

assemblyhands-toolkit

AssemblyHands Toolkit is a Python package that provides data loader, visualization, and evaluation tools for the AssemblyHands dataset (CVPR 2023).

language-models-trajectory-generators

iga

Code for paper: "Few-Shot In-Context Imitation Learning via Implicit Graph Alignment"

Cuda_cuDNN_LinuxInstall

How to install Cuda and cuDNN on Ubuntu 20.04

ai-assistant