full code again

app.py

@@ -1,46 +1,96 @@
 import gradio as gr
 import numpy as np
 import pandas as pd
-from PIL import Image, ImageDraw
+from PIL import Image
 
-IMAGE_PATH = "output_image.png"
-CSV_PATH = "damage_list.csv"
+# Your helper imports and tensorflow models assumed to be loaded here:
+import clustering
+import utils
+from tensorflow import keras
+import logging
+logging.getLogger().setLevel(logging.INFO)
 
-def dummy_damage_classification(img, threshold):
-    if img is None:
+# Paths to save outputs
+IMAGE_PATH = "classified_damage_sites.png"
+CSV_PATH = "classified_damage_sites.csv"
+
+# Load models once (adjust filenames as needed)
+model1 = keras.models.load_model('rwthmaterials_dp800_network1_inclusion.h5')
+model2 = keras.models.load_model('rwthmaterials_dp800_network2_damage.h5')
+
+damage_classes = {3: "Martensite", 2: "Interface", 0: "Notch", 1: "Shadowing"}
+model1_windowsize = [250, 250]
+model2_windowsize = [100, 100]
+
+def damage_classification(SEM_image, image_threshold, model1_threshold, model2_threshold):
+    if SEM_image is None:
+        logging.error("No image provided")
         return None, None, None
 
-    # Convert to numpy array
-    image_np = np.array(img)
+    damage_sites = {}
+
+    # Step 1: Clustering to find damage centroids
+    all_centroids = clustering.get_centroids(
+        SEM_image,
+        image_threshold=image_threshold,
+        fill_holes=True,
+        filter_close_centroids=True,
+    )
+
+    for c in all_centroids:
+        damage_sites[(c[0], c[1])] = "Not Classified"
 
-    # Draw a red square on the image
-    image_pil = Image.fromarray(image_np).convert("RGB")
-    draw = ImageDraw.Draw(image_pil)
-    draw.rectangle([10, 10, 50, 50], outline="red", width=3)
-    image_pil.save(IMAGE_PATH)
+    # Step 2: Model 1 to identify inclusions
+    images_model1 = utils.prepare_classifier_input(SEM_image, all_centroids, window_size=model1_windowsize)
+    y1_pred = model1.predict(np.asarray(images_model1, dtype=float))
+    inclusions = np.where(y1_pred[:, 0] > model1_threshold)[0]
 
-    # Create dummy CSV file
-    df = pd.DataFrame({"x": [20], "y": [30], "damage_type": ["Dummy"]})
+    for idx in inclusions:
+        coord = all_centroids[idx]
+        damage_sites[(coord[0], coord[1])] = "Inclusion"
+
+    # Step 3: Model 2 to classify remaining damage types
+    centroids_model2 = [list(k) for k, v in damage_sites.items() if v == "Not Classified"]
+    if centroids_model2:
+        images_model2 = utils.prepare_classifier_input(SEM_image, centroids_model2, window_size=model2_windowsize)
+        y2_pred = model2.predict(np.asarray(images_model2, dtype=float))
+        damage_index = np.asarray(y2_pred > model2_threshold).nonzero()
+
+        for i in range(len(damage_index[0])):
+            sample_idx = damage_index[0][i]
+            class_idx = damage_index[1][i]
+            label = damage_classes.get(class_idx, "Unknown")
+            coord = centroids_model2[sample_idx]
+            damage_sites[(coord[0], coord[1])] = label
+
+    # Step 4: Draw boxes on image and save output image
+    image_with_boxes = utils.show_boxes(SEM_image, damage_sites, save_image=True, image_path=IMAGE_PATH)
+
+    # Step 5: Export CSV file
+    data = [[x, y, label] for (x, y), label in damage_sites.items()]
+    df = pd.DataFrame(data, columns=["x", "y", "damage_type"])
     df.to_csv(CSV_PATH, index=False)
 
-    # Return PIL image for display, and file paths (strings) for download buttons
-    return image_pil, IMAGE_PATH, CSV_PATH
+    return image_with_boxes, IMAGE_PATH, CSV_PATH
+
 
 with gr.Blocks() as app:
-    gr.Markdown("# Minimal Damage Classifier Demo")
+    gr.Markdown("# Damage Classification in Dual Phase Steels")
 
     image_input = gr.Image(label="Upload SEM Image")
-    threshold_input = gr.Number(value=20, label="Threshold")
+    cluster_threshold_input = gr.Number(value=20, label="Cluster Threshold")
+    model1_threshold_input = gr.Number(value=0.7, label="Model 1 Threshold")
+    model2_threshold_input = gr.Number(value=0.5, label="Model 2 Threshold")
 
     output_image = gr.Image(label="Classified Image")
     download_image_btn = gr.DownloadButton(label="Download Image")
     download_csv_btn = gr.DownloadButton(label="Download CSV")
 
-    btn = gr.Button("Run Classification")
-    btn.click(
-        dummy_damage_classification,
-        inputs=[image_input, threshold_input],
-        outputs=[output_image, download_image_btn, download_csv_btn]
+    classify_btn = gr.Button("Run Classification")
+    classify_btn.click(
+        damage_classification,
+        inputs=[image_input, cluster_threshold_input, model1_threshold_input, model2_threshold_input],
+        outputs=[output_image, download_image_btn, download_csv_btn],
     )
 
 if __name__ == "__main__":

postBuild

@@ -0,0 +1,12 @@
+#!/bin/bash
+# postBuild script to run after pip install from requirements.txt
+
+echo "Running postBuild script..."
+
+# Upgrade or install a specific version of gradio (example: 4.44.1)
+pip install --upgrade gradio==4.44.1
+
+# (Optional) install or upgrade other packages if needed
+# pip install --upgrade some-package==version
+
+echo "postBuild complete."