Create app.py

app.py

@@ -0,0 +1,50 @@
+import os
+import uuid
+import pandas as pd
+import cv2
+from ultralytics import YOLO
+
+# Initialize the YOLO model
+model = YOLO('runs/segment/train/weights/best.pt')
+
+# Define directories
+image_dir = 'datasetsw/valid/ripe'
+output_dir = 'datasetsw/valid/test_ripe'
+
+# List all image files in the directory
+image_files = [os.path.join(image_dir, f) for f in os.listdir(image_dir) if f.endswith(('.jpg', '.jpeg', '.png'))]
+
+# Initialize an empty list to store the results
+results_list = []
+
+# Process each image
+for image_file in image_files:
+    results = model(image_file)
+    annotated_frame = results[0].plot()
+
+    total_objects = len(results[0].boxes)
+    labels = results[0].boxes.cls.tolist()
+    matang_count = labels.count(0)
+    mentah_count = labels.count(1)
+
+    # Generate a unique filename and save the annotated image
+    unique_id = str(uuid.uuid4())
+    combined_filename = f"{unique_id}.jpg"
+    output_path = os.path.join(output_dir, combined_filename)
+    cv2.imwrite(output_path, annotated_frame)
+
+    # Append the results to the list
+    results_list.append({
+        'image_file': image_file,
+        'total_objects': total_objects,
+        'matang_count': matang_count,
+        'mentah_count': mentah_count
+    })
+
+# Convert the results list to a dataframe
+results_df = pd.DataFrame(results_list)
+
+# Save the dataframe to a CSV file
+results_df.to_csv(os.path.join(output_dir, 'detection_results.csv'), index=False)
+
+cv2.destroyAllWindows()