Update app.py

app.py

@@ -17,41 +17,7 @@ moondream = AutoModelForCausalLM.from_pretrained(
 )
 moondream.compile()
 
-# Encode image once
-image = Image.open("complex_scene.jpg")
-encoded = moondream.encode_image(image)
-
-# Reuse the encoding for multiple queries
-questions = [
-    "How many people are in this image?",
-    "What time of day was this taken?",
-    "What's the weather like?"
-]
-
-for q in questions:
-    result = moondream.query(image=encoded, question=q, reasoning=False)
-    print(f"Q: {q}")
-    print(f"A: {result['answer']}\n")
-
-# Also works with other skills
-caption = moondream.caption(encoded, length="normal")
-objects = moondream.detect(encoded, "poop")
-pointe = moondream.point(encoded, "grass")
-print(f"caption: {e}, objects:{g}, point:{h}")
-
-# Segment an object
-result = moondream.segment(image, "cat")
-svg_path = result["path"]
-bbox = result["bbox"]
-
-print(f"SVG Path: {svg_path[:100]}...")
-print(f"Bounding box: {bbox}")
-
-# With spatial hint (point) to guide segmentation
-result = model.segment(image, "cat", spatial_refs=[[0.5, 0.3]])
-
-# With spatial hint (bounding box)
-result = model.segment(image, "cat", spatial_refs=[[0.2, 0.1, 0.8, 0.9]])
+
 
 """
 #model_id = "vikhyatk/moondream2"
@@ -83,6 +49,42 @@ model = AutoModelForCausalLM.from_pretrained(
 
 @spaces.GPU(durtion="150")
 def answer_questions(image_tuples, prompt_text):
+    # Encode image once
+    image = Image.open("complex_scene.jpg")
+    encoded = moondream.encode_image(image)
+
+    # Reuse the encoding for multiple queries
+    questions = [
+        "How many people are in this image?",
+        "What time of day was this taken?",
+        "What's the weather like?"
+    ]
+
+    for q in questions:
+        result = moondream.query(image=encoded, question=q, reasoning=False)
+        print(f"Q: {q}")
+        print(f"A: {result['answer']}\n")
+
+    # Also works with other skills
+    caption = moondream.caption(encoded, length="normal")
+    objects = moondream.detect(encoded, "poop")
+    pointe = moondream.point(encoded, "grass")
+    print(f"caption: {e}, objects:{g}, point:{h}")
+
+    # Segment an object
+    result = moondream.segment(image, "cat")
+    svg_path = result["path"]
+    bbox = result["bbox"]
+
+    print(f"SVG Path: {svg_path[:100]}...")
+    print(f"Bounding box: {bbox}")
+
+    # With spatial hint (point) to guide segmentation
+    result = model.segment(image, "cat", spatial_refs=[[0.5, 0.3]])
+
+    # With spatial hint (bounding box)
+    result = model.segment(image, "cat", spatial_refs=[[0.2, 0.1, 0.8, 0.9]])
+
     result = ""
     Q_and_A = ""
     prompts = [p.strip() for p in prompt_text.split('?')]