JunkyByte

easy_ViTPose

Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

deepcharuco

Unofficial pytorch implementation of the model proposed in Deep ChArUco: Dark ChArUco Marker Pose Estimation CVPR2019 https://arxiv.org/abs/1812.03247 for ChArUco board localization.

vispipe

Build Pipelines using a visual interface and run them in pure python

iris

Iris is a simple utility written completely in python which allows to sync folders between local and remote ssh (sftp) server

fast-charuco

Fast inference of deepcharuco model using onnx and improved inference setup

jupyter-autopy

ACDT

Tangent Based Manifold Approximation with locally linear models, implementation https://linkinghub.elsevier.com/retrieve/pii/S0165168414001522

DiffusionCraft

the name was chosen by chatgpt. This does not have anything to do with minecraft (yet)

E-HDQN

An implementation of a Hierarchical dqn driven by curiosity modules

python-gridwindow

A mini python library that provides grid visualization of multiple images/videos in a single opencv window.

Track-Anything-Mobile

(This Fork adds MobileSAM support) Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

alphabot

A bot based on alphago style supervised / rl training using Monte Carlo https://lightningbot.tk/

arduino-bajour

A personal project for my brother, a bajour that turns on when there's a movement, powered with Arduino

BangleApps_jb

Bangle.js App Loader (and Apps)

bookmarket

mini python script to selfhost your bookmarks (browser/device agnostic)

DRLPlayground

A deep reinforcement learning playground with Unity running the game physics, and Python handling the reinforcement learning algorithms.

Cloud-Basic-2023

Slides, exercises and resources for the 2023-2024 course on "Cloud-Computing Module 1" under the "Scientific and Data-Intensive Computing" Master Program at University of Trieste

co-tracker

CoTracker is a model for tracking any point (pixel) on a video.

final_hpc_and_cloud

GA-ICM-CONSENSUS

HER_DQN

Hindsight Experience Replay + Double Dueling DQN with BitSwap custom environment pytorch test implementation

Personalize-SAM

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

picon

Run your code in python interactive console from the command line

robcam-calibration

sam-pt

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

simppl

package for writing simple command-line pipelines, and organized command-line tools

telegram_wakeonlan_bot

WOL bot Simple telegram bot to wake up computers on your net

videopose

3D pose estimation for wild videos， embed 2d keypoints detector like hrnet alphapose and openpose

ViTPose_pytorch

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite