Mixup GeneratorAn implementation of "mixup: Beyond Empirical Risk Minimization"
SoltStreaming over lightweight data transformations
ZerothKaldi-based Korean ASR (한국어 음성인식) open-source project
Syndata GenerationCode used to generate synthetic scenes and bounding box annotations for object detection. This was used to generate data used in the Cut, Paste and Learn paper
ScaperA library for soundscape synthesis and augmentation
Tensorflow Mnist CnnMNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
TsaugA Python package for time series augmentation
MudaA library for augmenting annotated audio data
Stylealign[ICCV 2019]Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Transition
Torch AudiomentationsFast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
EvoskeletonOfficial project website for the CVPR 2020 paper (Oral Presentation) "Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data"
Copy Paste AugCopy-paste augmentation for segmentation and detection tasks
TorchsampleHigh-Level Training, Data Augmentation, and Utilities for Pytorch
Ghost Free Shadow Removal[AAAI 2020] Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
SemsegpipelineA simpler way of reading and augmenting image segmentation data into TensorFlow
Aaltd18Data augmentation using synthetic data for time series classification with deep residual networks
All Conv KerasAll Convolutional Network: (https://arxiv.org/abs/1412.6806#) implementation in Keras
What I Have ReadPaper Lists, Notes and Slides, Focus on NLP. For summarization, please refer to https://github.com/xcfcode/Summarization-Papers
Fcn trainThe code includes all the file that you need in the training stage for FCN
Cutmixa Ready-to-use PyTorch Extension of Unofficial CutMix Implementations with more improved performance.
TextattackTextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP
Wb color augmenterWB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Pose Adv AugCode for "Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation" (CVPR 2018)
GrandSource code and dataset of the NeurIPS 2020 paper "Graph Random Neural Network for Semi-Supervised Learning on Graphs"
DdaDifferentiable Data Augmentation Library
DoccreatorDIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation
DipsNAACL 2019: Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation
Nlp xiaojiang自然语言处理(nlp),小姜机器人(闲聊检索式chatbot),BERT句向量-相似度(Sentence Similarity),XLNET句向量-相似度(text xlnet embedding),文本分类(Text classification), 实体提取(ner,bert+bilstm+crf),数据增强(text augment, data enhance),同义句同义词生成,句子主干提取(mainpart),中文汉语短文本相似度,文本特征工程,keras-http-service调用
All Classifiers 2019A collection of computer vision projects for Acute Lymphoblastic Leukemia classification/early detection.
Eda nlpData augmentation for NLP, presented at EMNLP 2019
Data Augmentation ReviewList of useful data augmentation resources. You will find here some not common techniques, libraries, links to github repos, papers and others.
TorchioMedical image preprocessing and augmentation toolkit for deep learning
InltkNatural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
Yolo Tf2yolo(all versions) implementation in keras and tensorflow 2.4
Eda nlp for chineseAn implement of the paper of EDA for Chinese corpus.中文语料的EDA数据增强工具。NLP数据增强。论文阅读笔记。
PaddleclasA treasure chest for image classification powered by PaddlePaddle
Random ErasingRandom Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST
SnorkelA system for quickly generating training data with weak supervision
PbaEfficient Learning of Augmentation Policy Schedules
AudiomentationsA Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Nlpcda一键中文数据增强包 ; NLP数据增强、bert数据增强、EDA:pip install nlpcda
DeepconvsepDeep Convolutional Neural Networks for Musical Source Separation
SpecaugmentA Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
MixupImplementation of the mixup training method
DeltapyDeltaPy - Tabular Data Augmentation (by @firmai)
DaliA GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.