Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

Abstract Despite their failure to solve the compositional SCAN dataset, seq2seq architectures still achieve astonishing success on more practical tasks. This observation pushes us to question the usefulness of SCAN-style compositional generalization in realistic NLP tasks. In this work, we study the benefit that such compositionality brings about to several machine translation tasks. We present several focused modifications of Transformer that greatly improve generalization capabilities on SCAN and select one that remains on par with a vanilla Transformer on a […]

Read more

Deep learning models for remote sensing applications

Setting up a python environment Follow the instruction in https://docs.conda.io/projects/conda/en/latest/user-guide/install/linux.html for downloading and installing Miniconda Open a terminal in the code directory Create an environment using the .yml file: conda env create -f deepsatmodels_env.yml Activate the environment: source activate deepsatmodels Install required version of torch: conda install pytorch torchvision torchaudio cudatoolkit=10.1 -c pytorch-nightly Datasets MTLCC dataset (Germany) Download the dataset (.tfrecords) The data for Germany can be downloaded from: https://github.com/TUM-LMF/MTLCC clone the repository in a separate directory: git clone https://github.com/TUM-LMF/MTLCC […]

Read more

Discord Token Finder with python

Find half of your target’s token with just their ID. Install 🔧 pip install -r requeriments.txt Usage 💻 Go to Discord Settings Advanced Enable Developer Mode When you right click on an user, the final option is “Copy ID”, click it and input it into Ttawi Notes 📝 If you see a bug, please open an issue. ☕    

Read more

Repositório contendo scripts Python que realizam a consulta de CPF e CNPJ diretamente no site da Receita Federal

Repositório contendo scripts Python que realizam a consulta de CPF e CNPJ diretamente no site da Receita Federal. Requerimentos Python 3.x instalado; Driver do navegador que será utilizado. Clique aqui para mais informações; Caminho do driver baixado adicionado ao PATH. Instalação Na pasta do repositório, execute o comando: pip install -r requirements.txt Alterações necessárias Para a execução, é necessário adaptar o código para o navegador que será utilizado. Por padrão o código utiliza o navegador Microsoft Edge. Modificar se necessário: […]

Read more

Developer guide for Hivecoin project

Developer guide for Hivecoin project. Install Content are writen in reStructuredText (RST) and rendered with Sphinx. Much of the content displayed on the is converted from Markdown toreStructuredText (RST) and renderedwith Sphinx. Render the documentation locally To render the documentation locally you first need to install Sphinx and therequired theme modules, e.g. by running pip install -r requirements.txt This should be done from the root of this repo. Then you can execute Sphinx by calling This will generate HTML from […]

Read more

SSD-based Object Detection in PyTorch

서강대학교 현대모비스 SW 프로그램에서 진행한 인공지능 프로젝트입니다. Jetson nano를 이용해 pre-trained network를 fine tuning시켜 차량 및 신호등 인식을 구현하였습니다. https://www.youtube.com/watch?v=jYsIBuAgdao This repo implements SSD (Single Shot MultiBox Detector) in PyTorch for object detection, using MobileNet backbones. It also has out-of-box support for retraining on Google Open Images dataset. For documentation, please refer to Object Detection portion of the Hello AI World tutorial:Re-training SSD-Mobilenet Thanks to @qfgaohao for the upstream implementation from: https://github.com/qfgaohao/pytorch-ssd GitHub View Github    

Read more

AWS EC2 S3 Automated With python

This programme is a Python3 script that utilizes Boto3 to automate the process of creating an AWS EC2 instance with an Apache web server installed on it and a S3 bucket configured for static web hosting. This script is designed for use in a Linux based operating system. This script only requires one other file to run successfully; the pre-built index.html page included in this repository. Upon completetion, the script will have launched the Apache web sebver, which will be […]

Read more

Plazmix API wrapper for Python

An optimised, easy to use Plazmix API wrapper written in Python Features: Async and sync wrappers Using ujson instead of json for performance Regular updates Completely covers the Plazmix API Users Modes Online Metrics Moderator alerts News …and other more! Installing Important: Python 3.9 or higher is required To install the library you can just run the following command: Linux: # Linux/MacOS pip3 install plazmixapi Windows: python -m pip install plazmixapi OR pip install plazmixapi    

Read more
1 496 497 498 499 500 1,076