Update README.md

README.md

@@ -2,12 +2,108 @@
 license: mit
 title: Smilo
 sdk: gradio
+sdk_version: 6.10.0
+python_version: '3.13'
 emoji: 😃
 colorFrom: blue
 colorTo: green
 short_description: Real-Time Emotion Detection powered by PyTorch & OpenCV
+app_file: app.py
 pinned: false
-sdk_version: 6.10.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Smilo 😃
+**Real-Time Emotion Detection powered by PyTorch & OpenCV**
+
+Smilo is a lightweight, deep learning-based application that detects and classifies **7 facial emotions** in real-time:
+😠 Angry · 🤢 Disgust · 😨 Fear · 😃 Happy · 😐 Neutral · 😔 Sad · 😮 Surprise
+
+It features a beautiful Gradio 6 web interface with **live webcam streaming**, **confidence score charts**, and instant upload detection.
+
+---
+
+## 🚀 Deploy to Hugging Face Spaces
+
+> **Prerequisite:** Your model weights (`face_classifier.pth`) must be tracked with **Git LFS** (Large File Storage) before pushing, since the file is >100 MB.
+
+### Step 1 – Install Git LFS (once per machine)
+```bash
+git lfs install
+```
+
+### Step 2 – Create a new Space
+Go to [huggingface.co/new-space](https://huggingface.co/new-space), choose **Gradio** as the SDK, and clone the empty repo:
+```bash
+git clone https://huggingface.co/spaces/<your-username>/Smilo
+cd Smilo
+```
+
+### Step 3 – Track the model weights with LFS
+```bash
+git lfs track "*.pth"
+git add .gitattributes
+```
+
+### Step 4 – Copy your project files into the repo
+```
+app.py
+model.py
+main.py
+classes.pkl
+face_classifier.pth   ← large file, handled by LFS
+requirements.txt
+README.md
+.gitattributes
+```
+
+### Step 5 – Commit and push
+```bash
+git add .
+git commit -m "🚀 Initial Smilo deployment"
+git push
+```
+
+Hugging Face will automatically build and serve your app — usually within 1–2 minutes. Visit your Space URL to see it live!
+
+---
+
+## 💻 Run Locally
+
+```bash
+git clone <your-repo-url>
+cd Smilo
+pip install -r requirements.txt
+
+# Web interface (Gradio 6, supports live webcam streaming)
+python app.py
+
+# Desktop OpenCV window
+python main.py   # press Q to quit
+```
+
+---
+
+## 🧠 Architecture
+
+| Component | Details |
+|-----------|---------|
+| Face detection | OpenCV Haar Cascades (fast CPU inference) |
+| Emotion model | Custom 3-layer CNN (PyTorch), 128×128 RGB input |
+| Classes | 7 emotions |
+| Interface | Gradio 6 with real-time webcam streaming & confidence scores |
+
+---
+
+## 🛠️ Retrain
+
+Open `Train_model.ipynb` and follow the notebook. It will export updated `face_classifier.pth` and `classes.pkl`.
+
+---
+
+## 📝 Notes
+- Ensure good frontal lighting for best accuracy.
+- Free HF Spaces use CPU — inference is fast enough for smooth streaming.
+- For GPU acceleration, upgrade the Space hardware in the HF settings.
+
+## License
+MIT — see the LICENSE file for details.