Update README.md
Browse files
README.md
CHANGED
|
@@ -83,6 +83,9 @@ For all pre-training related hyperparameters, we refer to the [original paper](h
|
|
| 83 |
|
| 84 |
For evaluation results on several image classification benchmarks, we refer to tables 1 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution. Of course, increasing the model size will result in better performance.
|
| 85 |
|
|
|
|
|
|
|
|
|
|
| 86 |
### BibTeX entry and citation info
|
| 87 |
|
| 88 |
```bibtex
|
|
|
|
| 83 |
|
| 84 |
For evaluation results on several image classification benchmarks, we refer to tables 1 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution. Of course, increasing the model size will result in better performance.
|
| 85 |
|
| 86 |
+
We evaluated the model on `ImageNet1K` and got top-1 accuracy = **83.97** while in the original paper it was reported top-1 accuracy = 84.2.
|
| 87 |
+
If you want to reproduce our evaluation process you can use [This Colab Notebook](https://colab.research.google.com/drive/1Tse8Rfv-QhapMEMzauxUqnAQyXUgnTLK?usp=sharing)
|
| 88 |
+
|
| 89 |
### BibTeX entry and citation info
|
| 90 |
|
| 91 |
```bibtex
|