Update app.py

app.py

@@ -1,13 +1,17 @@
+import warnings
+warnings.filterwarnings("ignore")
+
 import streamlit as st
 from ultralytics import YOLO
 from PIL import Image
 import tempfile
 import os
 
-model = YOLO('yolov8n.pt')  # or 'yolov10s.pt'
+# Load model
+model = YOLO('yolov8n.pt')  # You can change to yolov10s.pt or custom weights
 
-st.title("YOLO Object Detection with Streamlit")
-st.write("Upload an image and see object detection results in real-time!")
+st.title("🧠 YOLO Object Detection with Streamlit")
+st.write("Upload an image to run real-time object detection.")
 
 # Upload image
 uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
@@ -15,15 +19,28 @@ uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png
 if uploaded_file is not None:
     # Convert uploaded file to PIL image
     image = Image.open(uploaded_file).convert("RGB")
-    st.image(image, caption="Uploaded Image", width='stretch')
+    st.image(image, caption="Uploaded Image", use_column_width=True)
 
-    # Temporary save to disk for YOLO inference
+    # Save to a temporary file for YOLO inference
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_file:
         temp_path = tmp_file.name
         image.save(temp_path)
 
+    # Confidence threshold
+    conf = st.slider("Confidence Threshold", 0.0, 1.0, 0.25)
+
     # Run YOLO inference
-    results = model(temp_path)
+    results = model(temp_path, conf=conf)
+
+    # Display detection results
+    st.image(results[0].plot(), caption="Detected Objects", use_column_width=True)
+
+    # Detection details
+    with st.expander("Detection Details"):
+        for box in results[0].boxes:
+            cls = model.names[int(box.cls)]
+            conf = float(box.conf)
+            st.write(f"**{cls}** — Confidence: {conf:.2f}")
 
-    # Show detection results in Streamlit
-    st.image(results[0].plot(), caption="Detected Objects", width='stretch')
+    # Clean up temp file
+    os.remove(temp_path)