Semantic

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

News & Updates (24/08/2021) Release the demo to perform fine-grained semantic alignments using the pretrained ROSITA model. (15/08/2021) Release the basic framework for ROSITA, including the pretrained base ROSITA model, as well as the scripts to run the fine-tuning and evaluation on three downstream tasks (i.e., VQA, REC, ITR) over six datasets. Introduction This repository contains source code necessary to reproduce the results presented in our ACM MM paper ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration, […]

Read more
Django

Drop-in replacement of Django admin comes with lots of goodies, fully extensible with plugin support

GitHub – sshwsfc/xadmin: Drop-in replacement of Django admin comes with lots of goodies, fully extensible with plugin support, pretty UI based on Twitter Bootstrap. Drop-in replacement of Django admin comes with lots of goodies, fully extensible with plugin support, pretty UI based on Twitter Bootstrap. – GitHub – sshwsfc/xadmin: Drop-in replacement of Django …    

Read more
Machine Learning

TLDR: Twin Learning for Dimensionality Reduction

TLDR (Twin Learning for Dimensionality Reduction) is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses. Inspired by manifold learning, TLDR uses nearest neighbors as a way to build pairs from a training set and a redundancy reduction loss to learn an encoder that produces representations invariant across such pairs. Similar to other neighborhood embeddings, TLDR effectively and unsupervisedly learns low-dimensional spaces where local neighborhoods of the input space […]

Read more
AWS

AWS SQS event redrive Lambda With Python

This repository contains one simple AWS Lambda function in Python to redrive AWS SQS events from source queue to destination queue. This script can be triggered periodically via cloudwatch as well if source queue contains too many events and you dont want to redrive them altogether. batch_size can be passed as input which will move only X events in one execution cycle. Default batch size is 10 if no value is passed. This script ensures that if same event is […]

Read more
Discord

A collection of discord tools using python

A collection of discord tools i’ve made. Basically every discord related project i’ve worked on can be found here, i’ll try and update/upload new projects to this repository as much as i can. Firstly, install discum by typing the following command into your console/terminal : python -m pip install –user –upgrade git+https://github.com/Merubokkusu/Discord-S.C.U.M.git#egg=discum If that doesn’t work, i recommend reading the discum installation guide here : https://github.com/Merubokkusu/Discord-S.C.U.M Secondly install all the other requirements by inputting the following command into your console/terminal […]

Read more
Deep Learning

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

Code for the paper TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks by Yu Li, Min Li, Qiuxia Lai, Yannan Liu, and Qiang Xu. If you use this code, or development from it, please cite our paper: @article{yu2021testrank, title={TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks}, author={Yu Li, Min Li, Qiuxia Lai, Yannan Liu, and Qiang Xu}, journal={NeurIPS}, year={2021} } 1. Setup Install dependencies conda env create -f environment.yml Please    

Read more
Images

IICNet: A Generic Framework for Reversible Image Conversion

Official PyTorch Implementation for IICNet: A Generic Framework for Reversible Image Conversion (ICCV2021). Demo Video | Supplements Introduction Reversible image conversion (RIC) aims to build a reversible transformation between specific visual content (e.g., short videos) and an embedding image, where the original content can be restored from the embedding when necessary. This work develops Invertible Image Conversion Net (IICNet) as a generic solution to various RIC tasks due to its strong capacity and task-independent design. Unlike previous encoder-decoder based methods, […]

Read more
Authentication

Python SDK for accessing the Hanko Authentication API

This package is maintained by Hanko. Introduction This SDK provides an API client that lets you communicate with theHanko Authentication APIto easily integrate FIDO®-based authentication into your web application written inPython. Documentation Installation Pip Building a wheel py -m build pip install dist/hanko_sdk-X.X.X-py3-none-any.whl Usage Prerequisites In order to utilize the client provided by the SDK you need an API URL as well as API credentials in the form of anAPI key ID and an API secret. View our getting   […]

Read more
Document

Documentation for the lottie file format

This repository contains both human-readable and machine-readable documentation about the Lottie format The documentation is available online at https://lottiefiles.github.io/lottie-docs/ License CC-BY 4.0 Setting Up This project uses mkdocs to generate the HTML pages from the documentation,and pip to install dependencies. It’s recommended you install dependencies on some kind of virtual environment. Once you have your environment, you can run pip install requirements.txt or make install_dependencies Building the Docs You can use To build the static HTML. During development, you might […]

Read more
1 … 422 423 424 425 426 … 940