Deep Learning

Vision Transformers for Dense Prediction This repository contains code and models for our paper: Vision Transformers for Dense Prediction René Ranftl,

参赛作品名 【隔空取人】【AI创造营】【mixlab】 An AR+ML prototype 作品简介 手机对准某人，确认要“收集”的他/她，然后对准电脑桌面对某个位置，即可把他/她贴到电脑桌面上！～～～ 使用方式 1 需要安装nodejs、python的开发环境，还有electron 2 启动服务

WILDS is a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, from tumor identification to wildlife monitoring to poverty mapping.

Yolov5 real time smoke detection system

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency(ECCV 2020, unfinish)

This version of famous StyleGAN2 is intended mostly for fellow artists and students, who rarely look at scientific metrics, but rather need a working tool.

A collection of code snippets for my PyTorch Lightning projects

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

A curated list of Causality in Computer Vision

A Julia library for efficient tensor computations and tensor network calculations

Polaris is a system based on facial recognition with a futuristic GUI design, Can easily find people informations stored in a database using their pictures .

This tool should help discover different patterns based on similarity measures in historical (financial) data

This repository provides a robustness evaluation on Face Recognition by using various adversarial attacks. These evaluations are conducted under diverse adversarial settings

ZCls is a classification model benchmark code base

LEAP is a general purpose Evolutionary Computation package that combines readable and easy-to-use syntax for search and optimization algorithms with powerful distribution and visualization features.

A repository to compare many popular NAS algorithms seamlessly across three popular benchmarks (NASBench 101, 201, and 301). You can implement your own NAS algorithm, and then easily compare it with eleven algorithms across three

A collection of multimodal datasets, and visual features for VQA and captionning in pytorch. Just run "pip install multimodal"

The official repository for TransReID: Transformer-based Object Re-Identification achieves state-of-the-art performances on object re-ID, including person re-ID and vehicle re-ID.

SymReg is a Symbolic Regression library aimed to be easy to use and fast. You can use it to find expressions trying to explain a given output from giv

Solarwinds Vulnerablity Info Repository with all the Solarwinds Vulnerability information I've been tracking and using for communications, review, and

ZenML.io • docs.ZenML.io • Quickstart • Join Slack What is ZenML? ZenML is an extensible, open-source MLOps framework for using production-ready Machi

2020: A Year Full of Amazing AI papers- A Review A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link

Brainstorm Brainstorm is a collaborative, open-source application dedicated to the analysis of brain recordings: MEG, EEG, fNIRS, ECoG, depth electrod

image-statistics-matching Preface This repository contains a Python implementation of Feature Distribution Matching and Histogram Matching methods pub

Continuous Reforestation Make tree planting a part of your daily workflow. 🌳 A GitHub Action for planting trees within your development workflow usin

OpticSim.jl Documentation Build Status OpticSim.jl is a Julia package for geometric optics (ray tracing) simulation and optimization of complex optica

초성 해석기 개요 한국어 초성만으로 이루어진 문장을 입력하면, 완성된 문장을 예측하는 초성 해석기입니다. 초성: ㄴㄴ ㄴㄹ ㅈㅇㅎ 예측 문장: 나는 너를 좋아해 모델 모델은 SKT-AI에서 공개한 Ko-BART를 이용합니다. 데이터 문장 단위로 이루어진 아무 코퍼스나

Rotary Transformer Rotary Transformer，简称RoFormer，是我们自研的语言模型之一，主要是为Transformer结构设计了新的旋转式位置编码（Rotary Position Embedding，RoPE）。RoPE具有良好的理论性质，且是目前唯一一种可以应用

Simple pure function representations of popular time series packages.

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (PyTorch)

A tiny multiprocess data loader in ~100 lines,