Update README.md

README.md

@@ -1,23 +1,35 @@
+---
+language: "en"
+library_name: "keras"
+tags:
+- image-classification
+- fire-detection
+license: "mit"
+datasets:
+- flame
+metrics:
+- accuracy
+- f1
+model_creator: "CPSquad"
+course: "1INF52 (PUCP)"
+---
+
 # Fire Classification Models
 
-This repository contains several Keras models trained for fire vs. no-fire image classification:
+These Keras models were developed by **CPSquad** as part of a Deep Learning project for the **1INF52 course** at **PUCP**. We trained them on the **FLAME dataset**, which provides UAV-based imagery of wildfires.
 
 - **DenseNet**: `densenet_final.keras`
 - **ResNet**: `resnet_final.keras`
 - **Xception**: `xception_final.keras`
 - **Ensemble**: `ensemble_model.keras`
 
-## Usage
+## Hyperparameter Tuning
 
-1. Download the `.keras` file you want (e.g. `ensemble_model.keras`).
-2. Load it in Python:
-   ```python
-   import tensorflow as tf
+Using [Keras Tuner](https://keras.io/keras_tuner/), we optimized:
+- Dropout rate
+- L2 regularization factor
+- Number of layers unfrozen
+- Learning rate
 
-   model = tf.keras.models.load_model("ensemble_model.keras")
-   prediction = model.predict(...)
-  ```
+These improvements helped boost performance metrics such as **accuracy** and **F1-score**, allowing us to reach SOTA results on FLAME’s fire/no-fire classification task.
 
----
-license: mit
----