Update app.py

app.py

@@ -2,6 +2,7 @@ import torch
 import gradio as gr
 from transformers import Owlv2Processor, Owlv2ForObjectDetection
 import spaces
+import json
 
 # Use GPU if available
 if torch.cuda.is_available():
@@ -30,12 +31,18 @@ def query_image(img, text_queries, score_threshold):
     boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
 
     result_labels = []
+    boxes_coords = []
     for box, score, label in zip(boxes, scores, labels):
         box = [int(i) for i in box.tolist()]
         if score < score_threshold:
             continue
+        boxes_coords.append({
+            "object": text_queries[label.item()],
+            "pos": box
+        })
         result_labels.append((box, text_queries[label.item()]))
-    return img, result_labels, boxes
+    print(boxes_coords)
+    return [img, result_labels], boxes_coords
 
 
 description = """
@@ -56,10 +63,5 @@ demo = gr.Interface(
     outputs=["annotatedimage", "json"],
     title="Zero-Shot Object Detection with OWLv2",
     description=description,
-    examples=[
-        ["assets/astronaut.png", "human face, rocket, star-spangled banner, nasa badge", 0.11],
-        ["assets/coffee.png", "coffee mug, spoon, plate", 0.1],
-        ["assets/butterflies.jpeg", "orange butterfly", 0.3],
-    ],
 )
 demo.launch()