Update README.md

README.md

@@ -1,20 +1,31 @@
 ---
 title: MushroomClassificationCNN
-emoji: 🚀
+emoji: 🍄
 colorFrom: red
 colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
+sdk: streamlit
+app_file: src/streamlit_app.py
 pinned: false
 short_description: Mushroom image classification with ResNet50
 license: mit
 ---
 
-# Welcome to Streamlit!
+# 🍄 Mushroom Classifier (ResNet50)
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+This app classifies mushroom images into **10 classes** using **Transfer Learning with ResNet50**.
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## ✅ Model
+- Backbone: **ResNet50** (ImageNet pretrained)
+- Input: **224 × 224 RGB**
+- Preprocessing: `tf.keras.applications.resnet50.preprocess_input`
+- Metrics used during training: **accuracy** and **top-3 accuracy**
+
+## 📌 Results (Validation)
+- **Accuracy:** 0.8520  
+- **Top-3 Accuracy:** 0.9704  
+- **Loss:** 0.6097  
+
+## 🚀 How to run locally
+```bash
+pip install -r requirements.txt
+streamlit run app.py