Update README.md

## 📈 Evaluation Results

Model performance evaluated on the independent testing dataset:

- **Overall Test Accuracy:** `~95-98%`

- **Classification Performance:**

<p align="center">
<img src="Figure_1.png" alt="Confusion Matrix" width="45%">
<img src="Figure_2.png" alt="Training Graphs" width="45%">
</p>

**Note:** Performance metrics were calculated using `sklearn.metrics.classification_report` after fine-tuning the top 40 layers of EfficientNetB0.

README.md

@@ -73,4 +73,17 @@ outputs = Dense(4, activation='softmax')(x)
 model = Model(inputs=base_model.input, outputs=outputs)
 
 # Load Weights
-model.load_weights("efficientnetb0_finetuned_brain_mri.keras")
+model.load_weights("efficientnetb0_finetuned_brain_mri.keras")
+
+
+## 📊 Dataset & Training Data
+
+- **Source:** Brain Tumor MRI Dataset (Kaggle)
+- **Data Distribution:**
+  - **Training Set:** MRI images augmented with rotation, shift, zoom, and horizontal flips.
+  - **Testing Set:** Independent brain MRI scans for evaluation.
+- **Classes:** 4 categories (Glioma, Meningioma, No Tumor, Pituitary).
+
+
+
+