|
--- |
|
tags: |
|
- RandAugment |
|
- Image Classification |
|
license: apache-2.0 |
|
datasets: |
|
- cifar10 |
|
metrics: |
|
- Accuracy |
|
--- |
|
|
|
## RandAugment for Image Classification for Improved Robustness on the 🤗Hub! |
|
|
|
[Paper](https://arxiv.org/abs/1909.13719) | [Keras Tutorial](https://keras.io/examples/vision/randaugment/) |
|
|
|
Keras Tutorial Credit goes to : [Sayak Paul](https://twitter.com/RisingSayak) |
|
|
|
**Excerpt from the Tutorial:** |
|
|
|
Data augmentation is a very useful technique that can help to improve the translational invariance of convolutional neural networks (CNN). RandAugment is a stochastic vision data augmentation routine composed of strong augmentation transforms like color jitters, Gaussian blurs, saturations, etc. along with more traditional augmentation transforms such as random crops. |
|
|
|
Recently, it has been a key component of works like [Noisy Student Training](https://arxiv.org/abs/1911.04252) and [Unsupervised Data Augmentation for Consistency Training](https://arxiv.org/abs/1904.12848). It has been also central to the success of [EfficientNets](https://arxiv.org/abs/1905.11946). |
|
|
|
## About The dataset |
|
|
|
The model was trained on [**CIFAR-10**](https://huggingface.co/datasets/cifar10), consisting of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. |
|
|
|
|
