mrm8488 commited on
Commit
5b76e6f
1 Parent(s): cc1150a

Add evaluation info

Browse files
Files changed (1) hide show
  1. README.md +3 -0
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 = **86.50** while in the original paper it was reported top-1 accuracy = 86.2.
87
+ If you want to reproduce our evaluation process you can use [This Colab Notebook](https://colab.research.google.com/drive/1xl8hcdoDYVt5aSk1AYH-nLm1Sgvhac4L?usp=sharing)
88
+
89
  ### BibTeX entry and citation info
90
 
91
  ```bibtex