Self-Supervised

Self-Supervised Learning by Estimating Twin Class Distribution

Codes and pretrained models for TWIST: @article{wang2021self, title={Self-Supervised Learning by Estimating Twin Class Distributions}, author={Wang, Feng and Kong, Tao and Zhang, Rufeng and Liu, Huaping and Li, Hang}, journal={arXiv preprint arXiv:2110.07402}, year={2021} } TWIST is a novel self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Without supervision, we enforce the class distributions of different augmentations to […]

Read more
Camera

Virtual webcam that takes real webcam footage and replaces the background in order to have Virtual Backgrounds in MS Teams for Linux

The Need It’s been good long while since Microsoft first released a Teams version for Linux and yet, one of Teams’ coolest features doesn’t exist in said Linux version: removable backgrounds. As someone who uses Linux for their daily driver, this annoys me. Well, I’m an engineer, so of course, I found a solution. Using OpenCV and a v4l2loopback device (basically a virtual webcam you can write data to), I threw together a Python application that takes your normal webcam […]

Read more
Compiler

A small C compiler written in Python for learning purposes

SmallerC A small C compiler written in Python. Generates x64 Intel-format assembly, which is then assembled and linked by nasm and ld. Features See the tests folder for examples that compile. The function_test.c test is representative of the range of SmallerC. Math Operations: +, -, *, /, %, ++, –, &&, ||, ! Assignment: =, +=, -=, *=, /=, %= Comparison: ==, !=, = int type variables Control structures: if while for break continue Pointers (referencing and dereferencing) Arrays Function […]

Read more
Telegram

A Telegram Userbot to play or streaming Audio and Video songs / files in Telegram Voice Chats

A Telegram Userbot to play or streaming Audio and Video songs / files in Telegram Voice Chats. 1) Installing NodeJS bash curl -fsSL https://deb.nodesource.com/setup_16.x | sudo -E bash – sudo apt-get install -y nodejs 2) Installing FFMPEG and Git bash sudo apt-get install git ffmpeg -y 3) Cloning the Repo bash git clone https://github.com/KennedyProject/Vcmusic-Userbot cd Vcmusic-Userbot 4) Rename `example.env` to `.env` and Fill    

Read more
Developer Tools

Google Developer Student Club I2IT/Clippin n grafting Backend

Presenting you, 🎉 Clippin’ n Grafting 🎉, your very own ecommerce website displaying all your artsy-craftsy stuff. Not only the exposure, but we aim to provide budding artists, budding entrepreneurs and just art enthusiasts a platform to sell, buy and just cruise through the amazing range of artistry that people desire to showcase! This repo focuses on the Django backend part of our Clippin’ n Grafting project Frontend –                     Backend –    

Read more
Network

Network automation Inventory manager

Welcome to Worktory’s documentation! Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts. As the network automation ecosystem grows, several connection plugins and parsers are available, and several times choosing a library or a connection plugin restricts all the devices to the same connection method. Worktory tries to solve that problem giving the developer total flexibility for choosing the connector plugin and parsers for each device, at the same time […]

Read more
Video

Convert lecture videos to slides in one line

About Convert lecture videos to slides in one line. Takes an input of a directory containing your lecture videos and outputs a directory containing .PDF files containing the slides of each lecture. (You can download the videos from Google Drive even if you only have View-Only permissions. Google it) The utility only captures slides when it detects that a slide has changed and does not capture every frame. Thus your pdf will be very close to the actual slides used. […]

Read more
Transformer

AniFormer: Data-driven 3D Animation with Transformer

This is the PyTorch implementation of our BMVC 2021 paper AniFormer: Data-driven 3D Animation with Transformer.Haoyu Chen, Hao Tang, Nicu Sebe, Guoying Zhao. Citation If you use our code or paper, please consider citing: @inproceedings{chen2021AniFormer, title={AniFormer: Data-driven 3D Animation withTransformer}, author={Chen, Haoyu and Tang, Hao and Sebe, Nicu and Zhao, Guoying}, booktitle={BMVC}, year={2021} } Dependencies Requirements: python3.6 numpy pytorch==1.1.0 and above trimesh Dataset preparation Please download DFAUST dataset    

Read more
1 … 510 511 512 513 514 … 1,033