GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → ayulockin → DataAugmentationTF

ayulockin / DataAugmentationTF

Licence: other
Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

computer-visionkerasdeeplearningcutoutdata-augmentationmixuptensorflow2cutmixaugmix

Projects that are alternatives of or similar to DataAugmentationTF

SnapMix
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)
Stars: ✭ 127 (+262.86%)
Mutual labels:  data-augmentation, mixup, cutmix
mixup
speechpro.com/
Stars: ✭ 23 (-34.29%)
Mutual labels:  data-augmentation, mixup
Torchsample
High-Level Training, Data Augmentation, and Utilities for Pytorch
Stars: ✭ 1,731 (+4845.71%)
Mutual labels:  data-augmentation
Zeroth
Kaldi-based Korean ASR (한국어 음성인식) open-source project
Stars: ✭ 248 (+608.57%)
Mutual labels:  data-augmentation
Tsaug
A Python package for time series augmentation
Stars: ✭ 180 (+414.29%)
Mutual labels:  data-augmentation
Evoskeleton
Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data"
Stars: ✭ 154 (+340%)
Mutual labels:  data-augmentation
Scaper
A library for soundscape synthesis and augmentation
Stars: ✭ 186 (+431.43%)
Mutual labels:  data-augmentation
Unsupervised Data Augmentation
Unofficial PyTorch Implementation of Unsupervised Data Augmentation.
Stars: ✭ 127 (+262.86%)
Mutual labels:  data-augmentation
Tinycrayon Ios Sdk
A smart and easy-to-use image masking and cutout SDK for mobile apps.
Stars: ✭ 1,767 (+4948.57%)
Mutual labels:  cutout
Muda
A library for augmenting annotated audio data
Stars: ✭ 177 (+405.71%)
Mutual labels:  data-augmentation
Nlp Data Augmentation
Data Augmentation for NLP. NLP数据增强
Stars: ✭ 235 (+571.43%)
Mutual labels:  data-augmentation
Torch videovision
Transforms for video datasets in pytorch
Stars: ✭ 174 (+397.14%)
Mutual labels:  data-augmentation
Imagecorruptions
Python package to corrupt arbitrary images.
Stars: ✭ 158 (+351.43%)
Mutual labels:  data-augmentation
Face.evolve.pytorch
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
Stars: ✭ 2,719 (+7668.57%)
Mutual labels:  data-augmentation
Copy Paste Aug
Copy-paste augmentation for segmentation and detection tasks
Stars: ✭ 132 (+277.14%)
Mutual labels:  data-augmentation
Solt
Streaming over lightweight data transformations
Stars: ✭ 249 (+611.43%)
Mutual labels:  data-augmentation
Ghost Free Shadow Removal
[AAAI 2020] Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
Stars: ✭ 133 (+280%)
Mutual labels:  data-augmentation
Stylealign
[ICCV 2019]Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Transition
Stars: ✭ 172 (+391.43%)
Mutual labels:  data-augmentation
Tensorflow Mnist Cnn
MNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
Stars: ✭ 182 (+420%)
Mutual labels:  data-augmentation
tensorflow 2.0 tutorial
tensorflow 2.0 正式版实用教程/tutorial
Stars: ✭ 48 (+37.14%)
Mutual labels:  tensorflow2
View All Similar Projects ➔

Modern Data Augmentation Techniques for Computer Vision

About

Implementation of various data augmentation techniques in TensorFlow 2.x. They can be easily used in your training pipeline. This repository contain the supplementary notebooks for the Modern Data Augmentation Techniques for Computer Vision(Weights and Biases) report.

Techniques Covered

Note: Cutout, Mixup and CutMix are implememted in tf.data and can be found in the linked colab notebooks. I am using TensorFlow 2.x implementation of AugMix by Aakash Nain. His repo can be found here. The fork of this repo contains Weights and Biases integration and some additional command like arguments for more control.

Result

Check out the linked report for:

  • The comparative study of these augmentation techniques.
  • Augmentation implementations.
  • Evaluation of these augmentation techniques against Cifar-10-C dataset.

Model Used

ResNet-20

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].