Neural Network

Learning to Tile with Self-Supervised Graph Neural Network

TilinGNN TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020) About The goal of our research problem is illustrated below: given a tile set (a) and a 2D region to be filled (b), we aim to produce a tiling (c) that maximally covers the interior of the given region without overlap or hole between the tile instances. Dependencies: This project is implemented in Python 3.7. You need to install the following packages to run our program. Pytorch (tested […]

Read more
Network

Riggable 3D Face Reconstruction via In-Network Optimization

INORig Source code for CVPR 2021 paper “Riggable 3D Face Reconstruction via In-Network Optimization”. Installation (1) Create an Anaconda environment. conda env create -f env.yaml conda activate INORig (2) Clone the repository and install dependencies. git clone https://github.com/zqbai-jeremy/INORig.git cd INORig pip install -r requirements_pip.txt (3) Setup 3DMM mkdir external cd external git clone https://github.com/zqbai-jeremy/face3d.git cd face3d Setup face3d as in YadiraF/face3d. Download “Exp_Pca.bin” from Guo et al. (in “CoarseData” link of their repository)and copy to “/external/face3d/examples/Data/BFM/Out/”. Download “std_exp.txt” from Deng […]

Read more
Machine Learning

Spatially-invariant Style-codes Controlled Makeup Transfer in python

SCGAN Implementation of CVPR 2021 paper “Spatially-invariant Style-codes Controlled Makeup Transfer” Prepare The pre-trained model is avaiable at https://drive.google.com/file/d/1t1Hbgqqzc_rV5v3gF7HuJ-xiuEVNb8sh/view?usp=sharing. vgg_conv.pth:https://drive.google.com/file/d/1JNrSVZrK4TfC7pFG-r7AOmGvBXF2VFOt/view?usp=sharing Put the G.pth and VGG weights in “./checkpoints” and “./” respectively. Environments:python=3.8, pytorch=1.6.0, Ubuntu=20.04.1 LTS Train Put the train-list of makeup images in “./MT-Dataset/makeup.txt” and the train-list of non-makeup images in “./MT-Dataset/non-makeup.txt” Use the “./scripts/handle_parsing.py” to convert the origin MT-Dataset’s seg labels Use python sc.py –phase train to train Test 1.Global Makeup Transfer python sc.py –phase test 2.Part-specific Makeup Transfer […]

Read more
Natural Language Processing

Bi-encoder based entity linker for japanese with python

jel: Japanese Entity Linker jel – Japanese Entity Linker – is Bi-encoder based entity linker for japanese. Currently, link and question methods are supported. el.link This returnes named entity and its candidate ones from Wikipedia titles. from jel import EntityLinker el = EntityLinker() el.link(‘今日は東京都のマックにアップルを買いに行き、スティーブジョブスとドナルドに会い、堀田区に引っ越した。’) >> [ { “text”: “東京都”, “label”: “GPE”, “span”: [ 3, 6 ], “predicted_normalized_entities”: [ [ “東京都庁”, 0.1084 ], [ “東京”, 0.0633 ], [ “国家地方警察東京都本部”, 0.0604 ], [ “東京都”, 0.0598 ], … ] }, { “text”: “アップル”, […]

Read more
Deep Learning

Website which uses Deep Learning to generate horror stories

Creepypasta – Text Generator Website which uses Deep Learning to generate horror stories. There are two parts to the project. One is the Deep Learning model which generates the text. The other is the website which uses the model to generate text. I have used Deep Learning model to generate text. It is a Neural Network which uses Recurrent Neural Network to generate text. I have hosted a model on Algorithmia and used it’s API to generate text. Built With […]

Read more
Simulation

An open-source computational electrodynamics Python simulator

PyCharge PyCharge is an open-source computational electrodynamics Python simulator that can calculate the electromagnetic fields and potentials generated by moving point charges and can self-consistently simulate dipoles modeled as Lorentz oscillators. PyCharge was designed to be accessible for a wide range of use cases: it can be used as a pedagogical tool for undergraduate and graduate-level EM theory courses to provide an intuitive understanding of the EM waves generated by moving point charges, and can also be used by researchers […]

Read more
Music player

A curses based mpd client with basic functionality and album art

Miniplayer A curses based mpd client with basic functionality and album art. After installation, the player can be opened from the terminal with miniplayer. Installation This package can be installed by: Cloning this repository to your computer and running python setup.py install Through PyPi with pip install miniplayer By installing the miniplayer-git package with your AUR package manager of choice. Configuration The config file is located at ~/.config/miniplayer/config. The example configuration file, config.example, has all the default values. You will […]

Read more
Discord

An enhanced audio player for discord

Discodo Discodo is an enhanced audio player for discord. Features Standalone Audio Node Youtube Related Video Autoplay Crossfade and Audio effects Synced Youtube Video Subtitle Documentation More information can be found here. Installation Discodo requires Python 3.7 or higher python -m pip install –upgrade discodo On Linux environments, more dependencies are required. Execution Audio Node Server Additional options can be seen with the –help flag python -m discodo Client libraries GitHub https://github.com/kijk2869/discodo    

Read more
Monitoring

A small project that allows internet speed monitoring using Grafana and Speedtest

Speedtest monitor for Grafana A small project that allows internet speed monitoring using Grafana, InfluxDB 2 and Speedtest. Requirements Docker and Docker compose. Python 3.+ (3.9.5 is recommended) Virtualenv pip install virtualenv Setup With Docker Make sure Docker and Docker-compose are installed before running the following commnad $ docker-compose build $ docker-compose up For development First make sure InfluxDB is up and running $ docker-compose up influxdb Once that is done you may setup your development environment. Make sure Python […]

Read more
Robot

Pypot: A Python lib for Dynamixel motors control

Pypot Pypot is a library developed in the Inria FLOWERS team to make it easy and fast to control custom robots based on dynamixel motors. This framework provides different levels of abstraction corresponding to different types of use. More precisely, you can use pypot to: directly control robotis motors (both protocol v1 and v2 are supported) through a USB2serial device, define the structure of your particular robot and control it through high-level commands, define primitives and easily combine them to […]

Read more
1 … 545 546 547 548 549 … 927