Update README.md (#2)
Browse files- Update README.md (360ce86602a9cc3fec6bb830ec2a721deb1f7929)
README.md
CHANGED
|
@@ -1,13 +1,12 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- image-classification
|
|
|
|
| 4 |
license: other
|
| 5 |
datasets:
|
| 6 |
- imagenet-1k
|
| 7 |
---
|
| 8 |
-
#
|
| 9 |
-
|
| 10 |
-
A FastViT image classification model. Trained on ImageNet-1k by paper authors.
|
| 11 |
|
| 12 |
Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af5928238cab99c45f64fc3e4e7b1516b8224ba/LICENSE).
|
| 13 |
|
|
@@ -21,4 +20,14 @@ Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af59
|
|
| 21 |
- **Papers:**
|
| 22 |
- FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization: https://arxiv.org/abs/2303.14189
|
| 23 |
- **Original:** https://github.com/apple/ml-fastvit
|
| 24 |
-
- **Dataset:** ImageNet-1k
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- image-classification
|
| 4 |
+
library_name: coreml
|
| 5 |
license: other
|
| 6 |
datasets:
|
| 7 |
- imagenet-1k
|
| 8 |
---
|
| 9 |
+
# FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
|
|
|
|
|
|
|
| 10 |
|
| 11 |
Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af5928238cab99c45f64fc3e4e7b1516b8224ba/LICENSE).
|
| 12 |
|
|
|
|
| 20 |
- **Papers:**
|
| 21 |
- FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization: https://arxiv.org/abs/2303.14189
|
| 22 |
- **Original:** https://github.com/apple/ml-fastvit
|
| 23 |
+
- **Dataset:** ImageNet-1k
|
| 24 |
+
|
| 25 |
+
## Citation
|
| 26 |
+
```bibtex
|
| 27 |
+
@inproceedings{vasufastvit2023,
|
| 28 |
+
author = {Pavan Kumar Anasosalu Vasu and James Gabriel and Jeff Zhu and Oncel Tuzel and Anurag Ranjan},
|
| 29 |
+
title = {FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization},
|
| 30 |
+
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
|
| 31 |
+
year = {2023}
|
| 32 |
+
}
|
| 33 |
+
```
|