Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## RandAugment for Image Classification for Improved Robustness on the 🤗Hub!
|
2 |
+
|
3 |
+
[Paper](https://arxiv.org/abs/1909.13719) | [Keras Tutorial](https://keras.io/examples/vision/randaugment/)
|
4 |
+
|
5 |
+
**Excerpt from the Tutorial:**
|
6 |
+
|
7 |
+
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.
|
8 |
+
|
9 |
+
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).
|
10 |
+
|
11 |
+
## About The dataset
|
12 |
+
|
13 |
+
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.
|