Deep Learning

Perform low-rank neural network reparameterization and its stable training in a compressed form

Spectral Tensor Train Parameterization of Deep Learning Layers This repository is the official implementation of our AISTATS 2021 paper titled “Spectral Tensor Train Parameterization of Deep Learning Layers” by Anton Obukhov, Maxim Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, and Luc Van Gool [arXiv] [PMLR]. It demonstrates how to perform low-rank neural network reparameterization and its stable training in a compressed form. The code provides all experiments (GAN and Image Classification) from the paper (see configs/aistats21 directory) with […]

Read more
Command-line Tools

An interactive command line text-to-speech tool using Google TTS

cli-tts This is an interactive command line text-to-speech tool using Google TTS. Just type text and the voice will be played. Multi-language is supported. Quick Start macOS $ git clone https://github.com/ReekyStive/cli-tts.git $ cd cli-tts $ brew install ffmpeg # be sure ffmpeg is in PATH $ pip install -r requirements.txt $ python tts.py Windows There’s a package that already included everything: Win32 Release Screenshots Supported Languages Local accent Language code Top-level domain English (Australia) en com.au English (United Kingdom) en […]

Read more
Bot

A Telegram Bot Plays With Words in python

TheWordzBot A Telegram Bot Plays With Words in python. ➠ I Can Turn Text Into Audio ➠ I Can Get Results From Dictionary ➠ I Can Make Google Search For You ➠ I Can Suggest Strong Passwords For You ➠ I Can Encode And Decode text in base64 format ➠ I Can Make Cowsay From Given Text GitHub https://github.com/raveen-2003/TheWordzBot    

Read more
Games

A python-based multi-player online educational game for students to play in a class or club setting

aimmo Using intermediate Python, join your class on a time travelling adventure. Work together to complete challenges and unlock new time periods. It is the year 3000 and the museum is in big trouble! The priceless artifacts are lost and scattered across timelines. Your team’s mission is to travel through time and bring them back into the museum. Quick Start Fork the repo. Take a look at our usage guidelines to see how to get started. GitHub https://github.com/ocadotechnology/aimmo    

Read more
Python

What Can I Do With Python?

Python is a very versatile programming language, with a plethora of uses in a variety of different fields. If you’ve grasped the basics of Python and are itching to build something with the language, then it’s time to figure out what your next step should be. In this article, we offer several different projects, resources, and tutorials that you can use to start building things with Python. What Others Do With Python You’re probably wondering what people are building with […]

Read more
Machine Learning

The glove detects the finger’s positions and translates them into key presses

Vvim – Keyboardless Vim interactions This is done via a hardware glove that the user wears. The glove detects the finger’s positions and translates them into key presses. It’s currently a work in progress. This is done via a hardware glove that the user wears. The glove detects thefinger’s positions and translates them into key presses. It’s currently a workin progress. The glove prototype, with 4 sensors on two fingers Subset of data The stream of data from the 4 […]

Read more
Neural Network

A neural networks using individual node features propagated via GPR

GPRGNN This is the source code for our ICLR2021 paper: Adaptive Universal Generalized PageRank Graph Neural Network. Hidden state feature extraction is performed by a neural networks using individual node features propagated via GPR. Note that both the GPR weights and parameter set of the neural network are learned simultaneously in an end-to-end fashion (as indicated in red). The learnt GPR weights of the GPR-GNN on real world datasets. Cora is homophilic while Texas is heterophilic (Here, H stands for […]

Read more
Documentation

Multiple-level labeling on document images and can generate in multiple languages

SDL: Synthetic Document Layout dataset SDL is the project that synthesizes document images. It facilitates multiple-level labeling on document images and can generate in multiple languages. Sample image Structure of data Quick start python flexible_layout.py –config_file configs/page.yaml Instruction to run data generation Go to instruction Visualization of the result python data_manipulation/visualize.py Vietnamese 300000 images link: Release soon Paper https://arxiv.org/abs/2106.15117 GitHub https://github.com/tson1997/SDL-Document-Image-Generation    

Read more
Transformer

A Unified Vision and Dialog Transformer with BERT

VD-BERT PyTorch Code for the following paper at EMNLP2020:Title: VD-BERT: A Unified Vision and Dialog Transformer with BERT [pdf]Authors: Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, Steven C.H. HoiInstitute: Salesforce Research and CUHKAbstractVisual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in […]

Read more
Network

Dual Self-Attention Network for Multivariate Time Series Forecasting

DSANet This project is the PyTorch implementation of the paper “DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting“, in which we propose a dual self-attention network (DSANet) for multivariate time series forecasting. The network architecture is illustrated in the following figure, and more details about the effect of each component can be found in the paper. Requirements Python 3.5 or above PyTorch 1.1 or above pytorch-lightning How to run You need to prepare the dataset first. Check here. # […]

Read more
1 … 590 591 592 593 594 … 939