Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ Excerpt from the Tutorial:
|
|
| 17 |
|
| 18 |
Swin Transformer (Shifted Window Transformer) can serve as a general-purpose backbone for computer vision. Swin Transformer is a hierarchical Transformer whose representations are computed with shifted windows. The shifted window scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connections. This architecture has the flexibility to model information at various scales and has a linear computational complexity with respect to image size.
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
The dataset we are using here is called [CIFAR-100](https://www.cs.toronto.edu/~kriz/cifar.html). The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
|
| 23 |
|
|
|
|
| 17 |
|
| 18 |
Swin Transformer (Shifted Window Transformer) can serve as a general-purpose backbone for computer vision. Swin Transformer is a hierarchical Transformer whose representations are computed with shifted windows. The shifted window scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connections. This architecture has the flexibility to model information at various scales and has a linear computational complexity with respect to image size.
|
| 19 |
|
| 20 |
+
## About The dataset
|
| 21 |
|
| 22 |
The dataset we are using here is called [CIFAR-100](https://www.cs.toronto.edu/~kriz/cifar.html). The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
|
| 23 |
|