Update app.py

app.py

@@ -3,14 +3,44 @@ from roboflow import Roboflow
 import tempfile
 import os
 from sahi.slicing import slice_image
-from sahi.postprocess import postprocess_predictions
+import numpy as np
+import cv2
 
 # Inisialisasi Roboflow (for model path)
 rf = Roboflow(api_key="Otg64Ra6wNOgDyjuhMYU")
 project = rf.workspace("alat-pelindung-diri").project("nescafe-4base")
 model = project.version(16).model
 
-# Fungsi untuk deteksi objek menggunakan SAHI dan Roboflow Model
+# Fungsi untuk melakukan Non-Maximum Suppression (NMS)
+def apply_nms(predictions, iou_threshold=0.5):
+    boxes = []
+    scores = []
+    classes = []
+
+    # Extract boxes, scores, and class info
+    for prediction in predictions:
+        boxes.append(prediction['bbox'])
+        scores.append(prediction['confidence'])
+        classes.append(prediction['class'])
+
+    boxes = np.array(boxes)
+    scores = np.array(scores)
+    classes = np.array(classes)
+
+    # Perform NMS using OpenCV
+    indices = cv2.dnn.NMSBoxes(boxes.tolist(), scores.tolist(), score_threshold=0.25, nms_threshold=iou_threshold)
+    nms_predictions = []
+
+    for i in indices.flatten():
+        nms_predictions.append({
+            'class': classes[i],
+            'bbox': boxes[i],
+            'confidence': scores[i]
+        })
+
+    return nms_predictions
+
+# Fungsi untuk deteksi objek menggunakan Roboflow Model
 def detect_objects(image):
     # Menyimpan gambar sementara
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
@@ -39,12 +69,8 @@ def detect_objects(image):
         predictions = model.predict(image_path=sliced_image_path).json()
         all_predictions.extend(predictions['predictions'])
 
-    # Postprocess dan gabungkan hasil prediksi
-    postprocessed_predictions = postprocess_predictions(
-        predictions=all_predictions,
-        postprocess_type='NMS',
-        iou_threshold=0.5
-    )
+    # Aplikasikan NMS untuk menghapus duplikat deteksi
+    postprocessed_predictions = apply_nms(all_predictions, iou_threshold=0.5)
 
     # Annotate gambar dengan hasil prediksi
     annotated_image = model.annotate_image_with_predictions(temp_file_path, postprocessed_predictions)