Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,16 @@
+Dataset/
+data/
+.git/
+__pycache__/
+*.pyc
+.ipynb_checkpoints/
+training_history.png
+history.json
+prepare_data.py
+train_model.py
+test_api.py
+predict_test.py
+plot_history.py
+implementation_plan.md
+static/uploads/*
+!static/uploads/.gitkeep

.hfignore

@@ -0,0 +1,16 @@
+Dataset/
+data/
+.git/
+__pycache__/
+*.pyc
+.ipynb_checkpoints/
+training_history.png
+history.json
+prepare_data.py
+train_model.py
+test_api.py
+predict_test.py
+plot_history.py
+implementation_plan.md
+static/uploads/*
+!static/uploads/.gitkeep

Dockerfile

@@ -0,0 +1,28 @@
+# Use official Python image
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies for OpenCV
+RUN apt-get update && apt-get install -y \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir gunicorn
+
+# Copy application code
+COPY . .
+
+# Create uploads directory
+RUN mkdir -p static/uploads && chmod 777 static/uploads
+
+# Expose port 7860
+EXPOSE 7860
+
+# Run the application with gunicorn
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]

README.md

@@ -1,10 +1,48 @@
----
-title: Bird Vs Drone Image Classification Using Deep Learning
-emoji: 🔥
-colorFrom: red
-colorTo: gray
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Bird vs Drone Classification
+emoji: 🦅🛸
+colorFrom: blue
+colorTo: indigo
+sdk: docker
+app_port: 7860
+pinned: false
+---
+
+# Bird vs Drone Image Classification
+
+An end-to-end deep learning project to classify airborne objects into "Bird" or "Drone" categories using a Convolutional Neural Network (MobileNetV2).
+
+## Features
+- **Deep Learning Model**: MobileNetV2 based architecture for fast and accurate classification.
+- **Data Pipeline**: Automated conversion from YOLO detection labels to classification datasets.
+- **Web Interface**: Premium glassmorphic UI for real-time inference.
+- **Data Augmentation**: Robust training using rotation, flip, and zoom augmentations.
+
+## Project Structure
+- `prepare_data.py`: Prepares the dataset manifests.
+- `train_model.py`: Trains the model on a subset of the 20k+ images.
+- `app.py`: Flask application for the web interface.
+- `templates/` & `static/`: Frontend assets.
+- `bird_vs_drone_model.h5`: The trained model weights.
+
+## Installation
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+1. **Prepare Data**:
+   ```bash
+   python prepare_data.py
+   ```
+2. **Train Model**:
+   ```bash
+   python train_model.py
+   ```
+3. **Run Web App**:
+   ```bash
+   python app.py
+   ```
+
+## Results
+The system provides a confidence score and a visual analysis of the uploaded target, distinguishing between natural avian flight and synthetic drone movement.

app.py

@@ -0,0 +1,72 @@
+from flask import Flask, render_template, request, jsonify
+import tensorflow as tf
+from tensorflow.keras.preprocessing import image
+import numpy as np
+import os
+from werkzeug.utils import secure_filename
+
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'static/uploads'
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+
+# Load model
+MODEL_PATH = 'bird_vs_drone_model.h5'
+model = None
+
+def get_model():
+    global model
+    if model is None:
+        if os.path.exists(MODEL_PATH):
+            model = tf.keras.models.load_model(MODEL_PATH)
+        elif os.path.exists('final_model.h5'):
+            model = tf.keras.models.load_model('final_model.h5')
+    return model
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file uploaded'})
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({'error': 'No file selected'})
+    
+    if file:
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        # Preprocess
+        img = image.load_img(filepath, target_size=(224, 224))
+        img_array = image.img_to_array(img) / 255.0
+        img_array = np.expand_dims(img_array, axis=0)
+        
+        # Predict
+        m = get_model()
+        if m is None:
+            return jsonify({'error': 'Model not found. Please train the model first.'})
+            
+        prediction = m.predict(img_array)[0][0]
+        
+        # Result
+        # Class index 0 is Bird, 1 is Drone (based on our generator)
+        # Binary generator usually sorts class names alphabetically: ['Bird', 'Drone']
+        # So Bird = 0, Drone = 1.
+        # prediction > 0.5 means Drone
+        
+        label = 'Drone' if prediction > 0.5 else 'Bird'
+        confidence = float(prediction) if label == 'Drone' else float(1 - prediction)
+        
+        return jsonify({
+            'label': label,
+            'confidence': f"{confidence*100:.2f}%",
+            'image_url': f"/static/uploads/{filename}"
+        })
+
+if __name__ == '__main__':
+    port = int(os.environ.get('PORT', 7860))
+    app.run(host='0.0.0.0', port=port)

bird_vs_drone_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e0a7d7ea6daef662441afa2e2d8fee3aab4808c5aee59cedd61a1a3c97212d
+size 11507656

final_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e0a7d7ea6daef662441afa2e2d8fee3aab4808c5aee59cedd61a1a3c97212d
+size 11507656

requirements.txt

@@ -0,0 +1,7 @@
+tensorflow>=2.15.0
+pandas
+flask
+numpy
+werkzeug
+opencv-python-headless
+gunicorn

static/css/style.css

@@ -0,0 +1,244 @@
+:root {
+    --primary: #00d2ff;
+    --secondary: #3a7bd5;
+    --dark: #0f172a;
+    --glass: rgba(255, 255, 255, 0.05);
+    --glass-border: rgba(255, 255, 255, 0.1);
+    --text: #f8fafc;
+}
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: 'Outfit', sans-serif;
+    background: radial-gradient(circle at top left, #1e293b, #0f172a);
+    color: var(--text);
+    min-height: 100vh;
+    display: flex;
+    justify-content: center;
+    padding: 2rem;
+}
+
+.container {
+    max-width: 900px;
+    width: 100%;
+}
+
+header {
+    text-align: center;
+    margin-bottom: 3rem;
+    animation: fadeInDown 0.8s ease-out;
+}
+
+.logo {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    gap: 1rem;
+    margin-bottom: 0.5rem;
+}
+
+.logo i {
+    font-size: 2.5rem;
+    color: var(--primary);
+}
+
+header h1 {
+    font-size: 2.5rem;
+    font-weight: 600;
+    letter-spacing: -0.025em;
+    background: linear-gradient(to right, var(--primary), var(--secondary));
+    -webkit-background-clip: text;
+    background-clip: text;
+    color: transparent;
+}
+
+header p {
+    color: #94a3b8;
+    font-size: 1.1rem;
+}
+
+.glass-card {
+    background: var(--glass);
+    backdrop-filter: blur(12px);
+    border: 1px solid var(--glass-border);
+    border-radius: 1.5rem;
+    padding: 2rem;
+    box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.5);
+    transition: transform 0.3s ease;
+}
+
+.upload-section {
+    margin-bottom: 2rem;
+    text-align: center;
+}
+
+.drop-zone {
+    border: 2px dashed var(--glass-border);
+    border-radius: 1rem;
+    padding: 3rem 2rem;
+    cursor: pointer;
+    transition: all 0.3s ease;
+    margin-bottom: 1.5rem;
+}
+
+.drop-zone:hover, .drop-zone.active {
+    border-color: var(--primary);
+    background: rgba(0, 210, 255, 0.05);
+}
+
+.drop-zone i {
+    font-size: 3rem;
+    color: var(--primary);
+    margin-bottom: 1rem;
+}
+
+.btn-primary {
+    background: linear-gradient(135deg, var(--primary), var(--secondary));
+    color: white;
+    border: none;
+    padding: 1rem 2.5rem;
+    border-radius: 0.75rem;
+    font-size: 1.1rem;
+    font-weight: 600;
+    cursor: pointer;
+    transition: all 0.3s ease;
+    box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.3);
+}
+
+.btn-primary:hover:not(:disabled) {
+    transform: translateY(-2px);
+    box-shadow: 0 20px 25px -5px rgba(0, 0, 0, 0.4);
+}
+
+.btn-primary:disabled {
+    opacity: 0.5;
+    cursor: not-allowed;
+}
+
+.result-card {
+    display: flex;
+    gap: 2rem;
+    align-items: center;
+    animation: fadeInUp 0.6s ease-out;
+}
+
+.image-preview {
+    position: relative;
+    width: 300px;
+    height: 300px;
+    border-radius: 1rem;
+    overflow: hidden;
+    border: 1px solid var(--glass-border);
+}
+
+.image-preview img {
+    width: 100%;
+    height: 100%;
+    object-fit: cover;
+}
+
+.scan-line {
+    position: absolute;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 2px;
+    background: var(--primary);
+    box-shadow: 0 0 15px var(--primary);
+    animation: scan 2.5s linear infinite;
+}
+
+.analysis-info {
+    flex: 1;
+}
+
+.analysis-info h2 {
+    font-size: 1.5rem;
+    margin-bottom: 1.5rem;
+    color: #cbd5e1;
+}
+
+.result-item {
+    margin-bottom: 1.5rem;
+}
+
+.result-item .label {
+    display: block;
+    color: #94a3b8;
+    margin-bottom: 0.5rem;
+    font-size: 0.9rem;
+    text-transform: uppercase;
+    letter-spacing: 0.05em;
+}
+
+.badge {
+    padding: 0.5rem 1rem;
+    border-radius: 2rem;
+    font-weight: 600;
+    font-size: 1.2rem;
+    display: inline-block;
+}
+
+.badge.bird {
+    background: rgba(34, 197, 94, 0.2);
+    color: #4ade80;
+    border: 1px solid rgba(34, 197, 94, 0.3);
+}
+
+.badge.drone {
+    background: rgba(239, 68, 68, 0.2);
+    color: #f87171;
+    border: 1px solid rgba(239, 68, 68, 0.3);
+}
+
+.progress-bar {
+    width: 100%;
+    height: 8px;
+    background: var(--glass);
+    border-radius: 4px;
+    overflow: hidden;
+    margin-bottom: 0.5rem;
+}
+
+.progress-fill {
+    height: 100%;
+    background: var(--primary);
+    width: 0;
+    transition: width 1s ease-out;
+}
+
+footer {
+    text-align: center;
+    margin-top: 4rem;
+    color: #64748b;
+    font-size: 0.9rem;
+}
+
+@keyframes scan {
+    0% { top: 0; }
+    100% { top: 100%; }
+}
+
+@keyframes fadeInUp {
+    from { opacity: 0; transform: translateY(20px); }
+    to { opacity: 1; transform: translateY(0); }
+}
+
+@keyframes fadeInDown {
+    from { opacity: 0; transform: translateY(-20px); }
+    to { opacity: 1; transform: translateY(0); }
+}
+
+@media (max-width: 768px) {
+    .result-card {
+        flex-direction: column;
+    }
+    .image-preview {
+        width: 100%;
+    }
+}

templates/index.html

@@ -0,0 +1,142 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>SkyGuard | Bird vs Drone Classifier</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+    <link href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;600&display=swap" rel="stylesheet">
+    <script src="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/js/all.min.js"></script>
+</head>
+<body>
+    <div class="container">
+        <header>
+            <div class="logo">
+                <i class="fas fa-shield-alt"></i>
+                <h1>SkyGuard AI</h1>
+            </div>
+            <p>Advanced Aerial Identification System</p>
+        </header>
+
+        <main>
+            <div class="glass-card upload-section">
+                <div class="drop-zone" id="drop-zone">
+                    <i class="fas fa-cloud-upload-alt"></i>
+                    <p>Drag & drop or Click to Upload Image</p>
+                    <input type="file" id="file-input" hidden accept="image/*">
+                </div>
+                <button id="predict-btn" class="btn-primary" disabled>Analyze Target</button>
+            </div>
+
+            <div class="result-section" id="result-section" style="display: none;">
+                <div class="glass-card result-card">
+                    <div class="image-preview">
+                        <img id="preview-img" src="" alt="Target Analysis">
+                        <div class="scan-line"></div>
+                    </div>
+                    <div class="analysis-info">
+                        <h2>Analysis Results</h2>
+                        <div class="result-item">
+                            <span class="label">Classification:</span>
+                            <span id="res-label" class="value badge">---</span>
+                        </div>
+                        <div class="result-item">
+                            <span class="label">Confidence:</span>
+                            <div class="progress-bar">
+                                <div id="res-conf-bar" class="progress-fill" style="width: 0%"></div>
+                            </div>
+                            <span id="res-conf-text" class="value">0%</span>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </main>
+
+        <footer>
+            <p>&copy; 2026 Deep Learning Aerial Surveillance Project</p>
+        </footer>
+    </div>
+
+    <script>
+        const dropZone = document.getElementById('drop-zone');
+        const fileInput = document.getElementById('file-input');
+        const predictBtn = document.getElementById('predict-btn');
+        const resultSection = document.getElementById('result-section');
+        const previewImg = document.getElementById('preview-img');
+        const resLabel = document.getElementById('res-label');
+        const resConfText = document.getElementById('res-conf-text');
+        const resConfBar = document.getElementById('res-conf-bar');
+
+        let selectedFile = null;
+
+        dropZone.onclick = () => fileInput.click();
+
+        fileInput.onchange = (e) => {
+            selectedFile = e.target.files[0];
+            if (selectedFile) {
+                const reader = new FileReader();
+                reader.onload = (e) => {
+                    previewImg.src = e.target.result;
+                    resultSection.style.display = 'block';
+                    predictBtn.disabled = false;
+                    // Reset labels
+                    resLabel.textContent = '---';
+                    resLabel.className = 'value badge';
+                    resConfText.textContent = '0%';
+                    resConfBar.style.width = '0%';
+                };
+                reader.readAsDataURL(selectedFile);
+            }
+        };
+
+        predictBtn.onclick = async () => {
+            if (!selectedFile) return;
+
+            predictBtn.innerHTML = '<i class="fas fa-spinner fa-spin"></i> Analyzing...';
+            predictBtn.disabled = true;
+
+            const formData = new FormData();
+            formData.append('file', selectedFile);
+
+            try {
+                const response = await fetch('/predict', {
+                    method: 'POST',
+                    body: formData
+                });
+                const data = await response.json();
+
+                if (data.error) {
+                    alert(data.error);
+                } else {
+                    resLabel.textContent = data.label;
+                    resLabel.classList.add(data.label.toLowerCase());
+                    resConfText.textContent = data.confidence;
+                    resConfBar.style.width = data.confidence;
+                    
+                    // Smooth scroll to results
+                    resultSection.scrollIntoView({ behavior: 'smooth' });
+                }
+            } catch (error) {
+                console.error('Error:', error);
+                alert('Analysis failed. Check console for details.');
+            } finally {
+                predictBtn.innerHTML = 'Analyze Target';
+                predictBtn.disabled = false;
+            }
+        };
+
+        // Drag and Drop
+        dropZone.ondragover = (e) => {
+            e.preventDefault();
+            dropZone.classList.add('active');
+        };
+        dropZone.ondragleave = () => dropZone.classList.remove('active');
+        dropZone.ondrop = (e) => {
+            e.preventDefault();
+            dropZone.classList.remove('active');
+            fileInput.files = e.dataTransfer.files;
+            fileInput.onchange({ target: fileInput });
+        };
+    </script>
+</body>
+</html>

upload_to_hf.py

@@ -0,0 +1,49 @@
+import os
+from huggingface_hub import HfApi, create_repo
+
+# Configuration
+REPO_NAME = "Bird-vs-Drone-image-classification-using-Deep-Learning" 
+USERNAME = "d-e-e-k-11" # Your Hugging Face username
+REPO_ID = f"{USERNAME}/{REPO_NAME}"
+
+api = HfApi()
+
+def upload():
+    print(f"Starting upload to https://huggingface.co/spaces/{REPO_ID}")
+    
+    try:
+        # 1. Create the repo if it doesn't exist
+        print(f"Checking if repo {REPO_ID} exists...")
+        create_repo(repo_id=REPO_ID, repo_type="space", space_sdk="docker", exist_ok=True)
+        
+        # 2. Upload the folder while ignoring the large dataset
+        print("Hashing files and uploading (ignoring Dataset/ and data/)...")
+        # We use a custom ignore list to be 100% sure
+        ignore_patterns = [
+            "Dataset/*", 
+            "data/*", 
+            ".git/*", 
+            "__pycache__/*", 
+            "*.pyc",
+            "training_history.png",
+            "history.json"
+        ]
+        
+        api.upload_folder(
+            folder_path=".",
+            repo_id=REPO_ID,
+            repo_type="space",
+            ignore_patterns=ignore_patterns,
+            delete_patterns=None # Set to "Dataset/*" etc if you want to clean remote
+        )
+        
+        print(f"\nSuccess! Your app is live at: https://huggingface.co/spaces/{REPO_ID}")
+        print("Note: It may take a few minutes for the Docker container to build on Hugging Face.")
+        
+    except Exception as e:
+        print(f"\nError: {e}")
+        print("\nIf you are not logged in, run: huggingface-cli login")
+        print("Or provide a token in the script.")
+
+if __name__ == "__main__":
+    upload()