Upload 18 files

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+src/models/best_model.keras filter=lfs diff=lfs merge=lfs -text
+src/models/classification_model_backup.keras filter=lfs diff=lfs merge=lfs -text
+src/models/flagship_model.keras filter=lfs diff=lfs merge=lfs -text
+src/static/output.jpg filter=lfs diff=lfs merge=lfs -text
+src/templates/wheat[[:space:]]image.jpg filter=lfs diff=lfs merge=lfs -text
+src/templates/wheat[[:space:]]logo.png filter=lfs diff=lfs merge=lfs -text
+src/templates/wheat-image-new.jpg filter=lfs diff=lfs merge=lfs -text
+src/templates/wheat-image.jpg filter=lfs diff=lfs merge=lfs -text

src/api/main.py

@@ -0,0 +1,105 @@
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+import uvicorn
+import io
+import numpy as np
+import cv2
+from PIL import Image
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+import os
+
+app = FastAPI(
+    title="Flagship Wheat Disease Detection API",
+    description="High-performance inference API for wheat disease classification.",
+    version="1.0.0"
+)
+
+# CORS Configuration
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"], # Allow all for dev; restrict in prod
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Global Model Variable
+model = None
+CLASSES = ["Crown and Root Rot", "Healthy Wheat", "Leaf Rust", "Wheat Loose Smut"]
+MODEL_PATH = os.path.join(os.path.dirname(__file__), "../models/flagship_model.keras")
+
+@app.on_event("startup")
+async def load_ml_model():
+    global model
+    print(f"Loading model from {MODEL_PATH}...")
+    try:
+        # Check if model exists
+        if os.path.exists(MODEL_PATH):
+            model = load_model(MODEL_PATH)
+            print("Model loaded successfully!")
+        else:
+            print(f"WARNING: Model file not found at {MODEL_PATH}. API will return mock predictions.")
+    except Exception as e:
+        print(f"ERROR: Failed to load model: {e}")
+
+@app.get("/")
+def read_root():
+    return {"message": "Wheat Analysis Flagship API is running."}
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    if not file.content_type.startswith("image/"):
+        raise HTTPException(status_code=400, detail="File must be an image")
+
+    # Read image
+    contents = await file.read()
+    image = Image.open(io.BytesIO(contents)).convert("RGB")
+    
+    # Preprocess
+    img_np = np.array(image)
+    # Resize to 260x260 (EfficientNetV2B2 native)
+    img_resized = cv2.resize(img_np, (260, 260))
+    img_batch = np.expand_dims(img_resized, axis=0)
+    
+    # Inference
+    if model:
+        predictions = model.predict(img_batch)
+        confidence_scores = predictions[0]
+        predicted_class_index = np.argmax(confidence_scores)
+        raw_confidence = float(confidence_scores[predicted_class_index])
+        
+        # PROBABILITY THRESHOLD: Filter out non-wheat images
+        # If the model isn't at least 70% sure, we flag it.
+        THRESHOLD = 0.70
+        
+        scores_dict = {cls: float(score) for cls, score in zip(CLASSES, confidence_scores)}
+        
+        if raw_confidence < THRESHOLD:
+            result = {
+                "prediction": "Unknown / Not Wheat",
+                "confidence": raw_confidence,
+                "scores": scores_dict,
+                "alert": "Low confidence. Please ensure the image is a clear leaf photo."
+            }
+        else:
+            result = {
+                "prediction": CLASSES[predicted_class_index],
+                "confidence": raw_confidence,
+                "scores": scores_dict
+            }
+    else:
+        # Mock Response for Dev/Testing if model isn't trained yet
+        import random
+        mock_class = random.choice(CLASSES)
+        result = {
+            "prediction": mock_class,
+            "confidence": 0.95,
+            "scores": {c: (0.95 if c == mock_class else 0.01) for c in CLASSES},
+            "warning": "Mock prediction (Model not loaded)"
+        }
+        
+    return result
+
+if __name__ == "__main__":
+    uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)

src/app.py

@@ -0,0 +1,126 @@
+from flask import Flask, render_template, request, flash, redirect, url_for
+from tensorflow.keras.models import load_model
+import numpy as np
+from PIL import Image
+import io
+import cv2
+import os
+import tensorflow as tf
+import json
+import time
+
+app = Flask(__name__)
+app.secret_key = b'_5#y2L"F4Q8z\n\xec]/'  # Secret key for flash messages
+
+# Define allowed extensions for image uploads
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+# Load the classification labels from a JSON file
+with open(os.path.join(os.path.dirname(os.path.abspath(__file__)), 'labels.json'), 'r') as f:
+    CLASSIFICATION_LABELS = json.load(f)
+
+# Get the absolute path to the classification model
+model_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'models/classification_model.keras')
+# Load the pre-trained classification model
+classification_model = load_model(model_path)
+
+def allowed_file(filename):
+    """
+    Checks if a given filename has an allowed image extension.
+
+    Args:
+        filename (str): The name of the file.
+
+    Returns:
+        bool: True if the file extension is allowed, False otherwise.
+    """
+    return '.' in filename and \
+           filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    """
+    Renders the main index page of the web application.
+    """
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    """
+    Handles image uploads, preprocesses the image, makes a prediction using the
+    classification model, and displays the result.
+    """
+    # Check if a file was part of the request
+    if 'file' not in request.files:
+        flash('No file part')
+        return redirect(request.url)
+    
+    file = request.files['file']
+    
+    # Check if a file was selected
+    if file.filename == '':
+        flash('No selected file')
+        return redirect(request.url)
+    
+    # Process the file if it exists and is allowed
+    if file and allowed_file(file.filename):
+        # Read the image file into a BytesIO object
+        img = Image.open(io.BytesIO(file.read()))
+        img_np = np.array(img)
+        
+        # Convert RGB image to BGR for OpenCV compatibility (if needed for other operations)
+        img_bgr = cv2.cvtColor(img_np, cv2.COLOR_RGB2BGR)
+
+        # Preprocess the image for the classification model (Expected input: 300x300 for EfficientNetV2B3)
+        img_resized_classification = cv2.resize(img_np, (300, 300))  # Resize to model's expected input
+        img_reshaped_classification = np.reshape(img_resized_classification, (1, 300, 300, 3)) # Reshape for model input
+        
+        # EfficientNetV2B3 handles normalization internally (expects 0-255 inputs)
+        # So we just pass the resized image directly
+        img_preprocessed = img_reshaped_classification
+
+        # Run the classification model to get predictions
+        prediction = classification_model.predict(img_preprocessed)
+        label_index = np.argmax(prediction)  # Get the index of the highest probability class
+        label = CLASSIFICATION_LABELS[label_index]  # Get the corresponding label string
+
+        # Generate a unique filename for the output image using a timestamp
+        timestamp = str(int(time.time()))
+        output_image_filename = f'output_{timestamp}.jpg'
+        # Define the path to save the output image in the static folder
+        output_image_path = os.path.join('static', output_image_filename)
+        # Save the processed image (original BGR version) to the static folder
+        cv2.imwrite(output_image_path, img_bgr)
+
+        # Cleanup old images (older than 1 hour)
+        cleanup_old_images()
+
+        # Render the result page with the predicted label and image path
+        return render_template('result.html', image_path=output_image_filename, label=label, timestamp=timestamp)
+    else:
+        # Flash an error message for invalid file types and redirect to the index page
+        flash('Invalid file type. Please upload an image (png, jpg, jpeg).')
+        return redirect(url_for('index'))
+
+def cleanup_old_images(folder='static', age_seconds=3600):
+    """
+    Removes files in the specified folder that are older than age_seconds.
+    """
+    try:
+        current_time = time.time()
+        folder_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), folder)
+        for filename in os.listdir(folder_path):
+            if filename.startswith('output_') and filename.endswith('.jpg'):
+                file_path = os.path.join(folder_path, filename)
+                file_creation_time = os.path.getmtime(file_path)
+                if current_time - file_creation_time > age_seconds:
+                    os.remove(file_path)
+                    print(f"Deleted old image: {filename}")
+    except Exception as e:
+        print(f"Error cleaning up images: {e}")
+
+if __name__ == '__main__':
+    # Get the port from environment variable or use 5000 as default
+    port = int(os.environ.get('PORT', 5000))
+    # Run the Flask application
+    app.run(host='0.0.0.0', port=port, debug=True)

src/labels.json

@@ -0,0 +1 @@
+["Crown and Root Rot", "Healthy Wheat", "Leaf Rust", "Wheat Loose Smut"]

src/models/best_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f102b8281196a966f8b075acefe05a6523c04d7274e104c3b272cf442fb96a1
+size 159529661

src/models/classification_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc8f32fcc51a455b25255dc5d540a69fa5b5279fa2355cdae93f47d334a14ed
+size 81005272

src/models/classification_model_backup.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb9ccc358eff58035d072c7a0c62e93dab9ea5be3e5737d28bd79792c106b84
+size 159515976

src/models/flagship_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868154920618fbabbef924056df3af16e5e2484ad3e844219f77ff735ce1f4ed
+size 40667128

src/static/css/style.css

@@ -0,0 +1,129 @@
+:root {
+    --primary-color: #2e7d32;
+    --secondary-color: #1b5e20;
+    --accent-color: #ffd54f;
+    --text-color: #333;
+    --glass-bg: rgba(255, 255, 255, 0.1);
+    --glass-border: rgba(255, 255, 255, 0.2);
+    --glass-shadow: 0 8px 32px 0 rgba(0, 0, 0, 0.37);
+}
+
+body {
+    font-family: 'Poppins', sans-serif;
+    margin: 0;
+    padding: 0;
+    overflow-x: hidden;
+    background-color: #1a1a1a; /* Fallback */
+}
+
+/* Background with overlay */
+.background-overlay {
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: url('../wheat-image-new.jpg') no-repeat center center/cover;
+    z-index: -1;
+}
+
+.background-overlay::before {
+    content: '';
+    position: absolute;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: linear-gradient(135deg, rgba(0, 0, 0, 0.7) 0%, rgba(20, 50, 20, 0.6) 100%);
+    backdrop-filter: blur(5px);
+}
+
+/* Glassmorphism Card */
+.glass-card {
+    background: var(--glass-bg);
+    backdrop-filter: blur(12px);
+    -webkit-backdrop-filter: blur(12px);
+    border: 1px solid var(--glass-border);
+    border-radius: 20px;
+    box-shadow: var(--glass-shadow);
+    width: 100%;
+    max-width: 500px;
+    transition: transform 0.3s ease;
+}
+
+.glass-card:hover {
+    transform: translateY(-5px);
+}
+
+/* Logo */
+.logo-img {
+    width: 80px;
+    height: auto;
+    filter: drop-shadow(0 0 10px rgba(255, 255, 255, 0.3));
+}
+
+/* Upload Zone */
+.upload-zone {
+    border: 2px dashed rgba(255, 255, 255, 0.5);
+    border-radius: 15px;
+    padding: 30px;
+    text-align: center;
+    transition: all 0.3s ease;
+    background: rgba(255, 255, 255, 0.05);
+    cursor: pointer;
+}
+
+.upload-zone:hover, .upload-zone.drag-over {
+    background: rgba(255, 255, 255, 0.15);
+    border-color: #fff;
+}
+
+/* Buttons */
+.btn-gradient {
+    background: linear-gradient(45deg, var(--primary-color), var(--secondary-color));
+    border: none;
+    color: white;
+    font-weight: 600;
+    padding: 12px 20px;
+    border-radius: 10px;
+    transition: all 0.3s ease;
+    box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2);
+}
+
+.btn-gradient:hover {
+    background: linear-gradient(45deg, var(--secondary-color), var(--primary-color));
+    transform: scale(1.02);
+    box-shadow: 0 6px 20px rgba(0, 0, 0, 0.3);
+    color: white;
+}
+
+.btn-gradient:disabled {
+    background: #555;
+    cursor: not-allowed;
+    transform: none;
+}
+
+/* Result Page */
+.result-image-container {
+    padding: 10px;
+    background: rgba(255, 255, 255, 0.1);
+    border-radius: 15px;
+}
+
+.result-img {
+    max-height: 300px;
+    object-fit: contain;
+    width: 100%;
+}
+
+.result-badge {
+    background: rgba(0, 0, 0, 0.4);
+    padding: 15px;
+    border-radius: 10px;
+    border: 1px solid rgba(255, 255, 255, 0.1);
+}
+
+/* Utilities */
+.tracking-wider {
+    letter-spacing: 0.1em;
+}

src/templates/index.html

@@ -0,0 +1,96 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Wheat Disease Detection</title>
+    <!-- Google Fonts -->
+    <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;600&display=swap" rel="stylesheet">
+    <!-- Bootstrap CSS -->
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/css/bootstrap.min.css" rel="stylesheet">
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+    <!-- Font Awesome -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
+</head>
+<body>
+
+    <div class="background-overlay"></div>
+
+    <div class="container d-flex align-items-center justify-content-center min-vh-100">
+        <div class="glass-card p-5 text-center">
+            <div class="mb-4">
+                <img src="{{ url_for('static', filename='wheat-logo-new.png') }}" alt="Logo" class="logo-img mb-3" onerror="this.style.display='none'">
+                <h1 class="display-4 fw-bold text-white">Wheat Guardian</h1>
+                <p class="lead text-white-50">Advanced AI Disease Detection</p>
+            </div>
+
+            <form action="/predict" method="post" enctype="multipart/form-data" id="uploadForm">
+                <div class="upload-zone mb-4" id="dropZone">
+                    <i class="fas fa-cloud-upload-alt fa-3x text-white mb-3"></i>
+                    <p class="text-white mb-2">Drag & Drop your image here</p>
+                    <p class="text-white-50 small">or</p>
+                    <label for="fileInput" class="btn btn-outline-light btn-sm mt-2">Browse Files</label>
+                    <input type="file" id="fileInput" name="file" accept="image/*" hidden required>
+                    <p id="fileName" class="text-white mt-2 small"></p>
+                </div>
+
+                <button type="submit" class="btn btn-gradient btn-lg w-100" id="submitBtn">
+                    <span id="btnText">Analyze Crop</span>
+                    <span id="loadingSpinner" class="spinner-border spinner-border-sm d-none" role="status" aria-hidden="true"></span>
+                </button>
+            </form>
+        </div>
+    </div>
+
+    <script>
+        const dropZone = document.getElementById('dropZone');
+        const fileInput = document.getElementById('fileInput');
+        const fileName = document.getElementById('fileName');
+        const uploadForm = document.getElementById('uploadForm');
+        const submitBtn = document.getElementById('submitBtn');
+        const btnText = document.getElementById('btnText');
+        const loadingSpinner = document.getElementById('loadingSpinner');
+
+        // Drag & Drop functionality
+        dropZone.addEventListener('dragover', (e) => {
+            e.preventDefault();
+            dropZone.classList.add('drag-over');
+        });
+
+        dropZone.addEventListener('dragleave', () => {
+            dropZone.classList.remove('drag-over');
+        });
+
+        dropZone.addEventListener('drop', (e) => {
+            e.preventDefault();
+            dropZone.classList.remove('drag-over');
+            const files = e.dataTransfer.files;
+            if (files.length > 0) {
+                fileInput.files = files;
+                updateFileName();
+            }
+        });
+
+        fileInput.addEventListener('change', updateFileName);
+
+        function updateFileName() {
+            if (fileInput.files.length > 0) {
+                fileName.textContent = fileInput.files[0].name;
+            } else {
+                fileName.textContent = '';
+            }
+        }
+
+        // Form Submit Animation
+        uploadForm.addEventListener('submit', () => {
+            submitBtn.disabled = true;
+            btnText.textContent = 'Analyzing...';
+            loadingSpinner.classList.remove('d-none');
+        });
+    </script>
+
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/js/bootstrap.bundle.min.js"></script>
+</body>
+</html>

src/templates/result.html

@@ -0,0 +1,44 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Analysis Result - Wheat Guardian</title>
+    <!-- Google Fonts -->
+    <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;600&display=swap" rel="stylesheet">
+    <!-- Bootstrap CSS -->
+    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/css/bootstrap.min.css" rel="stylesheet">
+    <!-- Custom CSS -->
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+    <!-- Font Awesome -->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
+</head>
+<body>
+
+    <div class="background-overlay"></div>
+
+    <div class="container d-flex align-items-center justify-content-center min-vh-100">
+        <div class="glass-card p-4 text-center" style="max-width: 600px; width: 100%;">
+            <h2 class="text-white mb-4 fw-bold">Analysis Report</h2>
+            
+            <div class="result-image-container mb-4">
+                <img src="{{ url_for('static', filename=image_path) }}?v={{ timestamp }}" class="img-fluid rounded shadow-lg result-img" alt="Analyzed Image">
+            </div>
+
+            <div class="result-badge mb-4">
+                <span class="text-white-50 small text-uppercase tracking-wider">Detected Condition</span>
+                <h3 class="text-white fw-bold mt-1">{{ label }}</h3>
+            </div>
+
+            <div class="d-grid gap-2">
+                <a href="/" class="btn btn-outline-light btn-lg">
+                    <i class="fas fa-redo me-2"></i>Analyze Another
+                </a>
+            </div>
+        </div>
+    </div>
+
+    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/js/bootstrap.bundle.min.js"></script>
+</body>
+</html>

src/templates/style.css

@@ -0,0 +1,80 @@
+html{
+    height: 100%
+}
+body {
+    background-color: brown;
+    background-image: url(wheat-image-new.jpg);
+    background-size: cover;
+    background-repeat: no-repeat;
+    background-position: center;
+
+}
+
+
+
+.container{
+    margin-left: auto;
+    margin-right: auto;
+    width: 1024px;
+}
+
+header {
+    height: 100px;
+    width: 1024px;
+    padding-top: 30px;
+    text-align: center;
+}
+
+nav {
+    background-color: rgba(0, 0, 0, 0.158);
+    height: 50px;
+    width: 1024px;
+    text-align: center;
+    padding-top: 25px;
+}
+
+main {
+    height: 500px;
+    width: 1024px;
+}
+
+nav a{
+    text-decoration: none;
+    padding-left: 50px;
+    padding-right: 50px;
+    color:  white;
+    font-size: 18px;
+
+}
+
+footer {
+    background-color: rgba(0, 0, 0, 0.158);
+    height: 50px;
+    width: 1024px;
+}
+
+h1 {
+    text-align: center;
+    padding-top: 50px;
+    color: rgba(82, 55, 55, 0.774);
+}
+
+main p {
+    text-align: center;
+    padding-left: 150px;
+    padding-right: 150px;
+    color: white;
+    font-family:Arial, Helvetica, sans-serif;
+    font-size: 18px;
+}
+
+footer p{
+    font-family: Arial, Helvetica, sans-serif;
+    color: white;
+    padding-left: 150px;
+    padding-right: 150px;
+    font-size: 15px;
+    padding-top: 5px;
+    text-align: center;
+
+}