Update README.md

README.md

@@ -1,13 +1,16 @@
+---
+license: mit
+language:
+- en
+metrics:
+- accuracy
+library_name: keras
+---
 # HAR Transformer
 Transformer for Human Activity Recognition
 
 Please check our paper [Wearable Sensor-Based Human Activity Recognition with Transformer Model](https://www.mdpi.com/1424-8220/22/5/1911) for more details.
 
-![Tag](https://img.shields.io/github/v/tag/markub3327/HAR-Transformer)
-[![Issues](https://img.shields.io/github/issues/markub3327/HAR-Transformer)](https://github.com/markub3327/HAR-Transformer/issues)
-![Commits](https://img.shields.io/github/commit-activity/w/markub3327/HAR-Transformer)
-![Size](https://img.shields.io/github/repo-size/markub3327/HAR-Transformer)
-
 ## Papers
   * Sikder, N.; Nahid, A.A.; KU-HAR: An open dataset for heterogeneous human activity recognition. Pattern Recognition Letters 2021, 146, 46-54, DOI: 10.1016/j.patrec.2021.02.024.
   * Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Advances in neural information processing systems 2017, 30.
@@ -22,24 +25,6 @@ The Transformer for Human Activity Recognition operates in sequence-to-sequence
 
 [KU-HAR](https://www.kaggle.com/datasets/niloy333/kuhar?resource=download)
 
-## Model
-
-<p align="center">
-  <img src="img/model.png" style="background-color: white;">
-</p>
-
-## Results
-
-<p align="center">
-  <b>Confusion matrix</b>
-  <img src="img/result.png" style="background-color: white;">
-</p>
-
-<p align="center">
-  <b>Hyperparameters</b>
-  <img src="img/hyperparams.png">
-</p>
-
 ----------------------------------
 
-**Frameworks:** TensorFlow, NumPy, Pandas, Scikit-learn, WanDB
+**Frameworks:** TensorFlow, NumPy, Pandas, Scikit-learn, WanDB