167 Open source projects that are alternatives of or similar to augraphy

Reference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single …

Reference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Lev…

MTSS-GAN: Multivariate Time Series Simulation with Generative Adversarial Networks (by @firmai)

A system for quickly generating training data with weak supervision

Evaluate real and synthetic datasets with each other

The Declarative Data Generator

Programming assignments and quizzes from all courses within the GANs specialization offered by deeplearning.ai

Natural Language Data Augmentation Tool for Conversational Systems

This repository contains the collection of UCI (real-life) datasets and Synthetic (artificial) datasets (with cluster labels and MATLAB files) ready to use with clustering algorithms.

Library for data augmentation

Bulk Stash is a docker rclone service to sync, or copy, files between different storage services. For example, you can copy files either to or from a remote storage services like Amazon S3 to Google Cloud Storage, or locally from your laptop to a remote storage.

Awesome Graph Self-Supervised Learning

Repository to identify Lego bricks automatically only using images

Simplified ETL process in Hadoop using Apache Spark. Has complete ETL pipeline for datalake. SparkSession extensions, DataFrame validation, Column extensions, SQL functions, and DataFrame transformations

Code for paper "Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery", Ren et al., CVPR'18

Light-weight Single Person Pose Estimator

IBM Synthetic Data Generator for Itemsets and Sequences

Collection of casual conversations that can be used with the Rasa Stack

Supervised Classification of bird species 🐦 in high resolution images, especially for, Himalayan birds, having diverse species with fairly low amount of labelled data

Synthetic data for computer vision. An open source toolkit using Blender and Python.

Saisoku is a Python module that helps you build complex pipelines of batch file/directory transfer/sync jobs.

This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

our code for paper 'PointCutMix: Regularization Strategy for Point Cloud Classification'

A curated list of papers, code and resources pertaining to few-shot image generation.

Implemenation of UNets for Lung Segmentation

An extended TSP (Time Stretched Pulse). CAPRICEP substantially replaces FVN. CAPRICEP enables interactive and real-time measurement of the linear time-invariant, the non-linear time-invariant, and random and time varying responses simultaneously.

KitanaQA: Adversarial training and data augmentation for neural question-answering models

3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks

The Gretel Python Client allows you to interact with the Gretel REST API.

Codes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling", ICRA 2022

Real estate dagster pipeline

VisDA2020: 4th Visual Domain Adaptation Challenge in ECCV'20

COVID-19 Coughs files for training AI models

Differentiable elastic deformations for N-dimensional images (Python, SciPy, NumPy, TensorFlow, PyTorch).

Data pipeline project

Multiclass image classification using Convolutional Neural Network

[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator (RAL+ICRA'21)

Pipeline module for parallel real-time data processing for machine learning models development and production purposes.

Image rotation and cropping out the black borders in TensorFlow

Library and CLI for randomly generating medical data like you might get out of an Electronic Health Records (EHR) system

Rivery CLI

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

Configuration and definitions of Airflow for OpenTrials

Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)

Source code and data for ACL 2019 Long Paper ``Semantic Parsing with Dual Learning".

TKDE 22. CCCL: Contrastive Cascade Graph Learning.

Synthetic Data Generation for mixed-type, multivariate time series.

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

A time series signal analysis and classification framework

Benchmarking synthetic data generation methods.

[Medical Image Analysis] Adversarial Data Augmentation with Chained Transformations (AdvChain)

Audio degradation toolbox in python, with a command-line tool. It is useful to apply controlled degradations to audio: e.g. data augmentation, evaluation in noisy conditions, etc.

Tensor2tensor experiment with SpecAugment

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

A generalizable application framework for segmentation, regression, and classification using PyTorch

AAAI'21: Data Augmentation for Graph Neural Networks

A Node.js and JavaScript synchronous data pipeline processing, data sharing and stream processing library. Actionable & Transformable Pipeline data processing.

JobAnalytics system consumes data from multiple sources and provides valuable information to both job hunters and recruiters.

Korean Easy Data Augmentation