Update app.py

app.py

@@ -77,19 +77,76 @@
 
 
 
+# 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()
+
+
+
+
+
+
+
 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
+from models import create_vgg19_model
+from gradcam_utils import generate_heatmap_tf_explain
 
 # 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()
+vgg_model = create_vgg19_model()  # Used for Grad-CAM
 
 def get_class_name(class_id):
     return "Normal" if class_id == 0 else "Pneumonia"
@@ -102,19 +159,13 @@ def predict_and_heatmap(image):
 
     # Predict using ensemble model
     prediction = ensemble_model.predict(img_array)
-    class_id = np.argmax(prediction[0])
+    class_id = int(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
-    )
+    # Generate heatmap using tf-explain and VGG19
+    heatmap_img = generate_heatmap_tf_explain(image, vgg_model, class_index=class_id)
 
-    return result, Image.fromarray(heatmap_img)
+    return result, heatmap_img
 
 # Gradio Interface
 interface = gr.Interface(
@@ -125,8 +176,9 @@ interface = gr.Interface(
         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)."
+    description="Upload a chest X-ray to detect Pneumonia and see the heatmap visualization (Grad-CAM powered by tf-explain)."
 )
 
 if __name__ == "__main__":
     interface.launch()
+