ildoonet / Unsupervised Data Augmentation
Licence: apache-2.0
Unofficial PyTorch Implementation of Unsupervised Data Augmentation.
Stars: ✭ 127
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Unsupervised Data Augmentation
awesome-graph-self-supervised-learning
Awesome Graph Self-Supervised Learning
Stars: ✭ 805 (+533.86%)
Mutual labels: unsupervised-learning, data-augmentation
Semsegpipeline
A simpler way of reading and augmenting image segmentation data into TensorFlow
Stars: ✭ 126 (-0.79%)
Mutual labels: data-augmentation
Laravel Natural Language
This package makes using the Google Natural API in your laravel app a breeze with minimum to no configuration, clean syntax and a consistent package API.
Stars: ✭ 119 (-6.3%)
Mutual labels: google
Esp V2
A service proxy that provides API management capabilities using Google Service Infrastructure.
Stars: ✭ 120 (-5.51%)
Mutual labels: google
Cleanlab
The standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
Stars: ✭ 2,526 (+1888.98%)
Mutual labels: unsupervised-learning
Plexidrive
Scripts to facilitate the use of cloud storage (such as Google Drive) as storage for Plex media server
Stars: ✭ 118 (-7.09%)
Mutual labels: google
Gon
Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder
Stars: ✭ 126 (-0.79%)
Mutual labels: unsupervised-learning
Gsheets Db Api
A Python DB-API and SQLAlchemy dialect to Google Spreasheets
Stars: ✭ 122 (-3.94%)
Mutual labels: google
Sfmlearner
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
Stars: ✭ 1,661 (+1207.87%)
Mutual labels: unsupervised-learning
3dpose gan
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations
Stars: ✭ 124 (-2.36%)
Mutual labels: unsupervised-learning
Calc
Convolutional Autoencoder for Loop Closure
Stars: ✭ 119 (-6.3%)
Mutual labels: unsupervised-learning
Tybalt
Training and evaluating a variational autoencoder for pan-cancer gene expression data
Stars: ✭ 126 (-0.79%)
Mutual labels: unsupervised-learning
Turkish Morphology
A two-level morphological analyzer for Turkish.
Stars: ✭ 121 (-4.72%)
Mutual labels: google
Yup Oauth2
An oauth2 client implementation providing the Device, Installed and Service Account flows.
Stars: ✭ 122 (-3.94%)
Mutual labels: google
Placepicker
Free Android Map Place Picker alternative using Geocoder instead of Google APIs
Stars: ✭ 126 (-0.79%)
Mutual labels: google
Combinefirebase
Combine wrapper on Google's iOS Firebase library.
Stars: ✭ 126 (-0.79%)
Mutual labels: google
UDA : Unsupervised Data Augmentation
Unofficial PyTorch Implementation of Unsupervised Data Augmentation.
- Experiments on Text Dataset need to be done. Any Pull-Requests would be appreciated.
- Augmentation policies for SVHN, Imagenet using AutoAugment are not available publicly. We use policies from Fast AutoAugment.
Most of codes are from Fast AutoAugment.
Introduction
todo.
Run
$ python train.py -c confs/wresnet28x2.yaml --unsupervised
Experiments
Cifar10 (Reduced, 4k dataset)
Reproduce Paper's Result
| WResNet 28x2 | Paper | Our Converged(Top1 Err) | Our Best(Top1 Err) |
|---|---|---|---|
| Supervised | 20.26 | 21.30 | |
| AutoAugment | 14.1* | 15.4 | 13.4 |
| UDA | 5.27 | 6.58 | 6.27 |
SVHN
todo.
ImageNet
todo.
References
- Unsupervised Data Augmentation : https://arxiv.org/abs/1904.12848v1
- Official Tensorflow Implementation : https://github.com/google-research/uda
- Fast AutoAugment : https://github.com/kakaobrain/fast-autoaugment
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].