Upload 4 files

app.py

@@ -0,0 +1,181 @@
+from flask import Flask, render_template, request, jsonify
+from PIL import Image
+import numpy as np
+import os
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.layers import (
+    Input,
+    Conv2D,
+    MaxPooling2D,
+    Flatten,
+    Dense,
+    BatchNormalization,
+    Activation,
+    Add,
+    Concatenate,
+)
+from tensorflow.keras.optimizers import Adam
+from vit_keras import vit
+
+app = Flask(__name__)
+
+# Define the upload directory
+UPLOAD_FOLDER = 'uploads'
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Define transitional block function
+def transitional_block(x, filters):
+    x = Conv2D(filters, kernel_size=(3, 3), strides=(1, 1), padding='same')(x)
+    x = BatchNormalization()(x)
+    x = Activation('relu')(x)
+    x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(x)
+    return x
+
+# Define pointwise convolution block function
+def pointwise_conv_block(x, filters):
+    x = Conv2D(filters, kernel_size=(1, 1), strides=(1, 1), padding='same')(x)
+    x = BatchNormalization()(x)
+    x = Activation('relu')(x)
+    return x
+
+# Define the ViT model
+input_shape = (224, 224, 3)  # Example input shape
+num_classes = 4  # Example number of classes
+vit_model = vit.vit_b32(
+    image_size=input_shape[:2],
+    include_top=False,
+    pretrained=True,
+    pretrained_top=False,
+    classes=num_classes,
+    weights="imagenet21k",
+)
+
+# Freeze the layers of the ViT model
+for layer in vit_model.layers:
+    layer.trainable = False
+
+# Define the modified VGG19 model
+def modified_vgg19(input_tensor):
+    # Block 1
+    x = Conv2D(64, kernel_size=(3, 3), strides=(1, 1), padding='same')(input_tensor)
+    x = BatchNormalization()(x)
+    x = Activation('relu')(x)
+    x = transitional_block(x, 64)
+
+    # Block 2
+    x = transitional_block(x, 128)
+    x = pointwise_conv_block(x, 128)
+
+    # Block 3
+    x = transitional_block(x, 256)
+    x = pointwise_conv_block(x, 256)
+    x = pointwise_conv_block(x, 256)
+    x = pointwise_conv_block(x, 256)
+
+    # Block 4
+    x = transitional_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+
+    # Block 5
+    x = transitional_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+    x = pointwise_conv_block(x, 512)
+
+    x = transitional_block(x, 1024)
+    x = pointwise_conv_block(x, 1024)
+    x = pointwise_conv_block(x, 1024)
+    x = pointwise_conv_block(x, 1024)
+    x = pointwise_conv_block(x, 1024)
+
+    x = Flatten()(x)
+    x = Dense(256, activation='relu')(x)
+    x = Dense(256, activation='relu')(x)
+    output_layer = Dense(4, activation='softmax')(x)
+
+    return output_layer
+    # Your modified VGG19 architecture here
+
+# Register custom layers used in modified_vgg19
+tf.keras.utils.get_custom_objects()['transitional_block'] = transitional_block
+tf.keras.utils.get_custom_objects()['pointwise_conv_block'] = pointwise_conv_block
+
+# Load the pre-trained model
+path = "C:\\Users\\HI BUDDY\\Desktop\\PoultryApp\\strawberryy.h5"
+
+loaded_model = load_model(path, custom_objects={
+    'transitional_block': transitional_block,
+    'pointwise_conv_block': pointwise_conv_block,
+})
+
+# Function to preprocess the image
+def preprocess_image(image_path):
+    img = image.load_img(image_path, target_size=(224, 224))
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = img_array / 255.0
+    return img_array
+
+# Function to check if the file has an allowed extension
+def allowed_file(filename):
+    ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg', 'gif'}
+    return '.' in filename and \
+           filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    # Check if the 'file' key is in the request
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file part'})
+
+    file = request.files['file']
+
+    # Check if file is empty
+    if file.filename == '':
+        return jsonify({'error': 'No selected file'})
+
+    # Check if file is allowed
+    if file and allowed_file(file.filename):
+        # Create the upload directory if it doesn't exist
+        if not os.path.exists(app.config['UPLOAD_FOLDER']):
+            os.makedirs(app.config['UPLOAD_FOLDER'])
+
+        img_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+        file.save(img_path)
+
+        # Preprocess the image
+        img_array = preprocess_image(img_path)
+
+        #labels
+        class_labels = ['klebsila', 'healthy', 'ecoli' , 'pseudomonas', 'staphylococcus', 'streptococcus']
+
+        # Make predictions
+        predictions = loaded_model.predict(img_array)
+
+        # Set confidence threshold
+        confidence_threshold = 0.50  # Adjust as needed  #.55 for normal #.85 for microscope
+
+        #  Get the predicted class label and confidence
+        max_confidence = np.max(predictions)
+
+        if max_confidence >= confidence_threshold:
+            predicted_class_index = np.argmax(predictions)
+            predicted_class_label = class_labels[predicted_class_index]
+            return jsonify({'prediction': predicted_class_label})
+        else:
+            return jsonify({'prediction': "This format is not supported"})
+
+    return jsonify({'error': 'Invalid file format'})
+
+if __name__ == '__main__':
+    app.run(debug=True)

index.html

@@ -0,0 +1,117 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Image Classifier</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='styles.css') }}">
+</head>
+<body>
+    <div id="headerContainer" class="header-container">
+        <h1>BerryWatch AI</h1>
+    </div>
+    
+    <div id="mainContainer" style="display: flex;">
+        <div id="inputContainer" style="flex-grow: 1;">
+            <input type="file" id="uploadInput">
+            <button id="uploadButton">Upload</button>
+            <div id="predictionResult"></div>
+            <div id="diseaseInfo" style="display: none;">
+                <h2>General Precaution</h2>
+                <div id="diseaseDescription"></div>
+                <div id="prevention"></div>
+                <div id="suggestions"></div>
+            </div>
+        </div>
+        <div id="uploadedImageContainer" style="flex-grow: 1; margin-left: 20px;">
+            <img id="uploadedImage" src="#" alt="Uploaded Image" style="max-width: 100%; max-height: 300px; display: none;">
+        </div>
+    </div>
+    <script>
+        document.getElementById('uploadInput').addEventListener('change', function() {
+            const fileInput = document.getElementById('uploadInput');
+            const file = fileInput.files[0];
+            if (!file) {
+                alert('Please select a file.');
+                return;
+            }
+
+            // Display uploaded image
+            const uploadedImage = document.getElementById('uploadedImage');
+            uploadedImage.src = URL.createObjectURL(file);
+            uploadedImage.style.display = 'block';
+        });
+
+        document.getElementById('uploadButton').addEventListener('click', async function() {
+            const fileInput = document.getElementById('uploadInput');
+            const file = fileInput.files[0];
+            if (!file) {
+                alert('Please select a file.');
+                return;
+            }
+
+            const formData = new FormData();
+            formData.append('file', file);
+
+            try {
+                const response = await fetch('/predict', {
+                    method: 'POST',
+                    body: formData
+                });
+                const data = await response.json();
+                document.getElementById('predictionResult').innerText = data.prediction;
+
+                // Display additional information based on prediction
+                const diseaseInfo = document.getElementById('diseaseInfo');
+                const diseaseDescription = document.getElementById('diseaseDescription');
+                const prevention = document.getElementById('prevention');
+                const suggestions = document.getElementById('suggestions');
+
+                // Reset previous content
+                diseaseDescription.innerHTML = '';
+                prevention.innerHTML = '';
+                suggestions.innerHTML = '';
+
+                switch (data.prediction.toLowerCase()) {
+                    case 'ecoli':
+                        diseaseDescription.innerHTML = 'Disease caused by E. coli.';
+                        prevention.innerHTML = 'Prevent contamination of food and water sources.';
+                        suggestions.innerHTML = 'Use organic fertilizers such as compost.';
+                        diseaseInfo.style.display = 'block';
+                        break;
+                    case 'streptococcus':
+                        diseaseDescription.innerHTML = 'Disease caused by Streptococcus bacteria.';
+                        prevention.innerHTML = 'Maintain good hygiene and cleanliness.';
+                        suggestions.innerHTML = 'Regularly sanitize surfaces and avoid close contact with infected individuals.';
+                        diseaseInfo.style.display = 'block';
+                        break;
+                    case 'staphylococcus':
+                        diseaseDescription.innerHTML = 'Disease caused by Staphylococcus bacteria.';
+                        prevention.innerHTML = 'Practice good personal hygiene and wound care.';
+                        suggestions.innerHTML = 'Use antibiotics as prescribed by a healthcare professional.';
+                        diseaseInfo.style.display = 'block';
+                        break;
+                    case 'klebsiella':
+                        diseaseDescription.innerHTML = 'Disease caused by Klebsiella bacteria.';
+                        prevention.innerHTML = 'Prevent transmission through proper sanitation measures.';
+                        suggestions.innerHTML = 'Avoid overuse of antibiotics.';
+                        diseaseInfo.style.display = 'block';
+                        break;
+                    case 'pseudomonas':
+                        diseaseDescription.innerHTML = 'Disease caused by Pseudomonas bacteria.';
+                        prevention.innerHTML = 'Maintain proper hygiene and cleanliness in healthcare settings.';
+                        suggestions.innerHTML = 'Use appropriate disinfectants and antibiotics.';
+                        diseaseInfo.style.display = 'block';
+                        break;
+                    default:
+                        // If prediction does not match any specific case, hide the additional info
+                        diseaseInfo.style.display = 'none';
+                        break;
+                }
+            } catch (error) {
+                console.error('Error:', error);
+            }
+        });
+    </script>
+</body>
+</html>

strawberryy.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdebd3d638467558fd0320d8c8581538fe3cf4db699e1acd0d77704b9c3e141
+size 569303136

styles.css

@@ -0,0 +1,64 @@
+body {
+    font-family: Arial, sans-serif;
+    margin: 0;
+    padding: 0;
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    justify-content: center;
+    height: 100vh;
+    background-color: #c26e82;
+}
+
+h1 {
+    margin-bottom: 20px;
+}
+
+#uploadInput {
+    margin-bottom: 20px;
+}
+
+#uploadButton {
+    padding: 10px 20px;
+    background-color: #4caf50;
+    color: white;
+    border: none;
+    border-radius: 5px;
+    cursor: pointer;
+}
+
+#uploadButton:hover {
+    background-color: #45a049;
+}
+
+#predictionResult {
+    margin-top: 20px;
+    font-weight: bold;
+}
+
+/* Added styles for uploaded image container */
+#uploadedImageContainer {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+  
+}
+
+/* Added styles for disease information container */
+#diseaseInfo {
+    margin-top: 20px;
+    padding: 20px;
+    background-color: #fff;
+    border-radius: 5px;
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
+}
+
+#diseaseInfo h2 {
+    margin-bottom: 10px;
+    color: #333;
+}
+
+#diseaseInfo div {
+    margin-bottom: 10px;
+}
+