Upload 10 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+uploads/IM-0006-0001.jpeg filter=lfs diff=lfs merge=lfs -text
+uploads/IM-0011-0001-0002.jpeg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,73 @@
+import os
+import numpy as np
+from PIL import Image
+import cv2
+from flask import Flask, request, render_template
+from werkzeug.utils import secure_filename
+from tensorflow.keras.models import load_model
+from gradcam_utils import generate_and_merge_heatmaps
+
+app = Flask(__name__)
+UPLOAD_FOLDER = 'static/uploads'
+HEATMAP_PATH = 'static/heatmap.jpg'
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Load your trained ensemble model
+model = load_model('ensemble_model_best(92.3).h5')
+
+# Load the three base models (if required for gradcam)
+from models import create_vgg19_model, create_efficientnet_model, create_densenet_model
+vgg_model = create_vgg19_model()
+efficientnet_model = create_efficientnet_model()
+densenet_model = create_densenet_model()
+
+print('Model loaded. Visit http://127.0.0.1:5000/')
+
+def get_className(classNo):
+    return "Normal" if classNo == 0 else "Pneumonia"
+
+def getResult(img_path):
+    image = cv2.imread(img_path)
+    image = Image.fromarray(image, 'RGB')
+    image = image.resize((224, 224))
+    image = np.array(image)
+    input_img = np.expand_dims(image, axis=0) / 255.0
+    result = model.predict(input_img)
+    result01 = np.argmax(result, axis=1)
+    return result01
+
+@app.route('/', methods=['GET'])
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def upload():
+    if request.method == 'POST':
+        f = request.files['file']
+        filename = secure_filename(f.filename)
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        f.save(file_path)
+
+        # Get prediction
+        value = getResult(file_path)
+        result = get_className(value[0])
+
+        # Generate Grad-CAM heatmap
+        heatmap_img = generate_and_merge_heatmaps(
+            file_path, vgg_model, efficientnet_model, densenet_model
+        )
+
+        # Save heatmap image
+        cv2.imwrite(HEATMAP_PATH, cv2.cvtColor(heatmap_img, cv2.COLOR_RGB2BGR))
+
+        return render_template(
+            'result.html',
+            prediction=result,
+            original_image=file_path,
+            heatmap_image=HEATMAP_PATH
+        )
+    return None
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000, debug=True)

ensemble_model_best(92.3).h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66958912a20cc6764eaec0045841bdd789cb950cd3677feb54cf1a32558ca5c
+size 304608784

gradcam_utils.py

@@ -0,0 +1,71 @@
+import numpy as np
+import cv2
+import tensorflow as tf
+from tensorflow.keras.preprocessing.image import img_to_array, load_img
+import matplotlib.pyplot as plt
+from matplotlib.colors import LinearSegmentedColormap
+
+def preprocess_image(img_path, target_size):
+    img = load_img(img_path, target_size=target_size)
+    img = img_to_array(img)
+    img = np.expand_dims(img, axis=0)
+    img = img / 255.0  # Normalize
+    return img
+
+def make_gradcam_heatmap(model, img_tensor, last_conv_layer_name, classifier_layer_names):
+    grad_model = tf.keras.models.Model(
+        [model.inputs], [model.get_layer(last_conv_layer_name).output, model.output]
+    )
+    with tf.GradientTape() as tape:
+        conv_outputs, predictions = grad_model(img_tensor)
+        loss = predictions[:, 1]  # Targeting class 1 for pneumonia
+
+    grads = tape.gradient(loss, conv_outputs)
+    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
+
+    conv_outputs = conv_outputs[0]
+    heatmap = conv_outputs @ pooled_grads[..., tf.newaxis]
+    heatmap = tf.squeeze(heatmap)
+    heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
+    heatmap = tf.where(tf.math.is_nan(heatmap), tf.zeros_like(heatmap), heatmap)
+    return heatmap.numpy()
+
+def create_custom_colormap():
+    colors = ['blue', 'green', 'yellow', 'red']
+    n_bins = 256
+    cmap = LinearSegmentedColormap.from_list('custom', colors, N=n_bins)
+    return cmap
+
+def apply_custom_colormap(heatmap, cmap):
+    colored_heatmap = cmap(heatmap)
+    colored_heatmap = np.uint8(colored_heatmap * 255)
+    return colored_heatmap
+
+def enhance_heatmap(heatmap, gamma=0.7, percentile=99):
+    heatmap = np.power(heatmap, gamma)
+    heatmap = heatmap / np.percentile(heatmap, percentile)
+    heatmap = np.clip(heatmap, 0, 1)
+    return heatmap
+
+def generate_and_merge_heatmaps(img_path, vgg_model, efficientnet_model, densenet_model, img_size=(224, 224), output_size=(5, 5)):
+    img_tensor = preprocess_image(img_path, img_size)
+
+    vgg_heatmap = make_gradcam_heatmap(vgg_model, img_tensor, 'block5_conv4', ['flatten', 'dense'])
+    efficientnet_heatmap = make_gradcam_heatmap(efficientnet_model, img_tensor, 'top_conv', ['flatten', 'dense'])
+    densenet_heatmap = make_gradcam_heatmap(densenet_model, img_tensor, 'conv5_block16_concat', ['flatten', 'dense'])
+
+    vgg_heatmap_resized = cv2.resize(vgg_heatmap, img_size)
+    efficientnet_heatmap_resized = cv2.resize(efficientnet_heatmap, img_size)
+    densenet_heatmap_resized = cv2.resize(densenet_heatmap, img_size)
+
+    merged_heatmap = (vgg_heatmap_resized + efficientnet_heatmap_resized + densenet_heatmap_resized) / 3.0
+    enhanced_heatmap = enhance_heatmap(merged_heatmap)
+    custom_cmap = create_custom_colormap()
+    colored_heatmap = apply_custom_colormap(enhanced_heatmap, custom_cmap)
+
+    img = cv2.imread(img_path)
+    img = cv2.resize(img, img_size)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+    superimposed_img = cv2.addWeighted(img, 0.6, colored_heatmap[:, :, :3], 0.4, 0)
+    return superimposed_img

models.py

@@ -0,0 +1,27 @@
+from tensorflow.keras.applications import VGG19, EfficientNetB0, DenseNet121
+from tensorflow.keras.models import Model
+from tensorflow.keras.layers import Dense, Flatten, GlobalAveragePooling2D, Input
+
+def create_vgg19_model():
+    base_model = VGG19(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
+    x = Flatten()(base_model.output)
+    x = Dense(128, activation='relu')(x)
+    output = Dense(2, activation='softmax')(x)
+    model = Model(inputs=base_model.input, outputs=output)
+    return model
+
+def create_efficientnet_model():
+    base_model = EfficientNetB0(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
+    x = GlobalAveragePooling2D()(base_model.output)
+    x = Dense(128, activation='relu')(x)
+    output = Dense(2, activation='softmax')(x)
+    model = Model(inputs=base_model.input, outputs=output)
+    return model
+
+def create_densenet_model():
+    base_model = DenseNet121(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
+    x = GlobalAveragePooling2D()(base_model.output)
+    x = Dense(128, activation='relu')(x)
+    output = Dense(2, activation='softmax')(x)
+    model = Model(inputs=base_model.input, outputs=output)
+    return model

templates/import.html

@@ -0,0 +1,29 @@
+
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta http-equiv="X-UA-Compatible" content="ie=edge">
+    <title>Advance Project : PNEUMONIA DETECTION Using Deep Learning</title>
+    <link href="{{ url_for('static', filename='css/bootstrap.min.css') }}" rel="stylesheet">
+    <script src="{{ url_for('static', filename='js/jquery.min.js') }}"></script>
+    <script src="{{ url_for('static', filename='js/bootstrap.min.js') }}"></script>
+    <link href="{{ url_for('static', filename='css/test.css') }}" rel="stylesheet">
+    <script src="{{ url_for('static', filename='js/newjs.js') }}" type="text/javascript"></script>
+</head>
+
+<body>
+    <nav class="navbar navbar-dark bg-dark">
+        <div class="container">
+            <a class="navbar-brand" href="#">Advance Project : PNEUMONIA DETECTION Using Deep Learning</a>
+        </div>
+    </nav>
+
+    {% block content %}
+    {% endblock %}
+
+</body>
+
+
+</html>

templates/index.html

@@ -0,0 +1,73 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>PNEUMONIA DETECTION Using Deep Learning</title>
+    <style>
+        body {
+            margin: 0;
+            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+            background-color: #ffffff;
+            text-align: center;
+        }
+
+        .navbar {
+            background-color: #2c3e50;
+            color: white;
+            padding: 15px;
+            font-size: 18px;
+        }
+
+        h1 {
+            margin-top: 40px;
+            font-size: 28px;
+            color: #222;
+        }
+
+        .upload-box {
+            margin-top: 30px;
+        }
+
+        .custom-file-input {
+            padding: 10px 15px;
+            border: none;
+            background-color: #28a745;
+            color: white;
+            font-size: 16px;
+            border-radius: 6px;
+            cursor: pointer;
+        }
+
+        .custom-file-input:hover {
+            background-color: #218838;
+        }
+
+        input[type="file"] {
+            display: none;
+        }
+
+        label {
+            display: inline-block;
+            margin-bottom: 10px;
+        }
+    </style>
+</head>
+<body>
+    <div class="navbar">
+        Advance Project : PNEUMONIA DETECTION Using Deep Learning
+    </div>
+
+    <h1>PNEUMONIA DETECTION Using Deep Learning</h1>
+
+    <div class="upload-box">
+        <form action="/predict" method="post" enctype="multipart/form-data">
+            <label class="custom-file-input">
+                Choose File
+                <input type="file" name="file" accept="image/*" required>
+            </label>
+            <br><br>
+            <button class="custom-file-input" type="submit">Predict</button>
+        </form>
+    </div>
+</body>
+</html>

templates/result.html

@@ -0,0 +1,22 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Pneumonia Detection Result</title>
+    <style>
+        body { font-family: Arial, sans-serif; text-align: center; padding: 40px; }
+        img { margin: 20px; border-radius: 10px; box-shadow: 0 4px 10px rgba(0,0,0,0.1); }
+    </style>
+</head>
+<body>
+    <h1>Prediction: {{ prediction }}</h1>
+
+    <h2>Original Image</h2>
+    <img src="{{ original_image }}" width="300" alt="Original X-ray">
+
+    <h2>Grad-CAM Heatmap</h2>
+    <img src="{{ heatmap_image }}" width="300" alt="Grad-CAM Heatmap">
+
+    <br><br>
+    <a href="/">Back to Home</a>
+</body>
+</html>