Update app.py

app.py

@@ -1,73 +1,132 @@
-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)
+# 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)
+
+
+
+
+
+
+import gradio as gr
+import numpy as np
+import cv2
+from PIL import Image
+from tensorflow.keras.models import load_model
+from models import create_vgg19_model, create_efficientnet_model, create_densenet_model
+from gradcam_utils import generate_and_merge_heatmaps
+
+# Load models
+ensemble_model = load_model("ensemble_model_best(92.3).h5")
+vgg_model = create_vgg19_model()
+efficientnet_model = create_efficientnet_model()
+densenet_model = create_densenet_model()
+
+def get_class_name(class_id):
+    return "Normal" if class_id == 0 else "Pneumonia"
+
+def predict_and_heatmap(image):
+    # Preprocess input image
+    img = image.resize((224, 224))
+    img_array = np.array(img) / 255.0
+    img_array = np.expand_dims(img_array, axis=0)
+
+    # Predict using ensemble model
+    prediction = ensemble_model.predict(img_array)
+    class_id = np.argmax(prediction[0])
+    result = get_class_name(class_id)
+
+    # Save uploaded image temporarily
+    temp_img_path = "temp_input.jpg"
+    image.save(temp_img_path)
+
+    # Generate Grad-CAM heatmap
+    heatmap_img = generate_and_merge_heatmaps(
+        temp_img_path, vgg_model, efficientnet_model, densenet_model
+    )
+
+    return result, Image.fromarray(heatmap_img)
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=predict_and_heatmap,
+    inputs=gr.Image(type="pil", label="Upload Chest X-ray"),
+    outputs=[
+        gr.Label(label="Prediction"),
+        gr.Image(label="Grad-CAM Heatmap")
+    ],
+    title="Pneumonia Detection Using Deep Learning",
+    description="Upload a chest X-ray to detect Pneumonia and see the heatmap visualization (Grad-CAM)."
+)
+
+if __name__ == "__main__":
+    interface.launch()