An implementation of "mixup: Beyond Empirical Risk Minimization"
-
Updated
Nov 5, 2017 - Jupyter Notebook
An implementation of "mixup: Beyond Empirical Risk Minimization"
mixup: Beyond Empirical Risk Minimization
Implementation of the mixup training method
How to do mixup training from image files in Keras
a lightweight project for classification and bag of tricks are employed for better performance
Review materials for the TWiML Study Group. Contains annotated versions of the original Jupyter noteboooks (look for names like *_jcat.ipynb ), slide decks from weekly Zoom meetups, etc.
Official adversarial mixup resynthesis repository
ManifoldMixup with support for Interpolated Adversarial training
A repository to host recent papers on Manifold Mixup.
Tensorflow2(Keras)のImageDataGeneratorのJupyter上での実行例。
Tensorflow2/KerasのImageDataGenerator向けのmixupの実装。
Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.
An implementation of MobileNetV3 with pyTorch
A new regularization technique by encountering samples through exponential smoothing
Exploring mixup strategies for text classification
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)
Add a description, image, and links to the mixup topic page so that developers can more easily learn about it.
To associate your repository with the mixup topic, visit your repo's landing page and select "manage topics."