audio degraderAudio 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.
Stars: ✭ 40 (-90.57%)
Learning-From-RulesImplementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)
Stars: ✭ 46 (-89.15%)
fastai sparse3D 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
Stars: ✭ 46 (-89.15%)
GaNDLFA generalizable application framework for segmentation, regression, and classification using PyTorch
Stars: ✭ 77 (-81.84%)
pytorch-ricapPyTorch implementation of RICAP (Random Image Cropping And Patching)
Stars: ✭ 40 (-90.57%)
CAPRICEPAn 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.
Stars: ✭ 23 (-94.58%)
semantic-parsing-dualSource code and data for ACL 2019 Long Paper ``Semantic Parsing with Dual Learning".
Stars: ✭ 17 (-95.99%)
DataAugmentationTFImplementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.
Stars: ✭ 35 (-91.75%)
text2textText2Text: Cross-lingual natural language processing and generation toolkit
Stars: ✭ 188 (-55.66%)
DrqDrQ: Data regularized Q
Stars: ✭ 268 (-36.79%)
manifold mixupTensorflow implementation of the Manifold Mixup machine learning research paper
Stars: ✭ 24 (-94.34%)
MobilePoseLight-weight Single Person Pose Estimator
Stars: ✭ 588 (+38.68%)
DeltapyDeltaPy - Tabular Data Augmentation (by @firmai)
Stars: ✭ 344 (-18.87%)
PointCutMixour code for paper 'PointCutMix: Regularization Strategy for Point Cloud Classification'
Stars: ✭ 42 (-90.09%)
webdatasetA high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Stars: ✭ 816 (+92.45%)
specAugmentTensor2tensor experiment with SpecAugment
Stars: ✭ 46 (-89.15%)
thelperTraining framework & tools for PyTorch-based machine learning projects.
Stars: ✭ 14 (-96.7%)
mrnetBuilding an ACL tear detector to spot knee injuries from MRIs with PyTorch (MRNet)
Stars: ✭ 98 (-76.89%)
elasticdeformDifferentiable elastic deformations for N-dimensional images (Python, SciPy, NumPy, TensorFlow, PyTorch).
Stars: ✭ 134 (-68.4%)
KoEDAKorean Easy Data Augmentation
Stars: ✭ 62 (-85.38%)
Mixup GeneratorAn implementation of "mixup: Beyond Empirical Risk Minimization"
Stars: ✭ 250 (-41.04%)
all-classifiers-2019A collection of computer vision projects for Acute Lymphoblastic Leukemia classification/early detection.
Stars: ✭ 24 (-94.34%)
DabData Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ
Stars: ✭ 294 (-30.66%)
volumentationsAugmentation package for 3d data based on albumentaitons
Stars: ✭ 26 (-93.87%)
UnetsImplemenation of UNets for Lung Segmentation
Stars: ✭ 18 (-95.75%)
Amazon Forest Computer VisionAmazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Stars: ✭ 346 (-18.4%)
GAugAAAI'21: Data Augmentation for Graph Neural Networks
Stars: ✭ 139 (-67.22%)
KitanaQAKitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (-86.32%)
Torchsat🔥TorchSat 🌏 is an open-source deep learning framework for satellite imagery analysis based on PyTorch.
Stars: ✭ 261 (-38.44%)
coursera-gan-specializationProgramming assignments and quizzes from all courses within the GANs specialization offered by deeplearning.ai
Stars: ✭ 277 (-34.67%)
allie🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).
Stars: ✭ 93 (-78.07%)
EPCDepth[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation
Stars: ✭ 105 (-75.24%)
SpecaugmentA Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Stars: ✭ 408 (-3.77%)
ccglTKDE 22. CCCL: Contrastive Cascade Graph Learning.
Stars: ✭ 20 (-95.28%)
mixupspeechpro.com/
Stars: ✭ 23 (-94.58%)
SnapMixSnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)
Stars: ✭ 127 (-70.05%)
EmotionalConversionStarGANThis repository contains code to replicate results from the ICASSP 2020 paper "StarGAN for Emotional Speech Conversion: Validated by Data Augmentation of End-to-End Emotion Recognition".
Stars: ✭ 92 (-78.3%)
mnist-challengeMy solution to TUM's Machine Learning MNIST challenge 2016-2017 [winner]
Stars: ✭ 68 (-83.96%)
advchain[Medical Image Analysis] Adversarial Data Augmentation with Chained Transformations (AdvChain)
Stars: ✭ 32 (-92.45%)
machine learning courseArtificial intelligence/machine learning course at UCF in Spring 2020 (Fall 2019 and Spring 2019)
Stars: ✭ 47 (-88.92%)
augraphyAugmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
Stars: ✭ 49 (-88.44%)
polyagammaAn efficient and flexible sampler of the Pólya-Gamma distribution with a NumPy/SciPy compatible interface.
Stars: ✭ 15 (-96.46%)
bird species classificationSupervised Classification of bird species 🐦 in high resolution images, especially for, Himalayan birds, having diverse species with fairly low amount of labelled data
Stars: ✭ 59 (-86.08%)
DeepconvsepDeep Convolutional Neural Networks for Musical Source Separation
Stars: ✭ 424 (+0%)
MixupImplementation of the mixup training method
Stars: ✭ 377 (-11.08%)
DaliA GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Stars: ✭ 3,624 (+754.72%)
DeepSentiPersRepository for the experiments described in the paper named "DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus"
Stars: ✭ 17 (-95.99%)
candockA time series signal analysis and classification framework
Stars: ✭ 56 (-86.79%)