Upload app.py

app.py

@@ -5,28 +5,34 @@ from transformers import pipeline
 
 # Create a sentiment analysis pipeline
 object_detection = pipeline("sentiment-analysis", model="chayanee/Detected_img")
+try:
+    # Create an object detection pipeline
+    object_detection = pipeline("object-detection")
 
-# Set the title for your Streamlit app
-st.title("Object Detection")
+    # Set the title for your Streamlit app
+    st.title("Object Detection")
 
-# Image Upload Widget
-uploaded_image = st.file_uploader("Upload an image for Detection", type=["jpg", "jpeg", "png"])
+    # Image Upload Widget
+    uploaded_image = st.file_uploader("Upload an image for Detection", type=["jpg", "jpeg", "png"])
 
-# Perform object detection when the user clicks a button
-if st.button("Detection"):
-    # Analyze the uploaded image if available
-    if uploaded_image:
-        # Display the uploaded image
-        image = Image.open(uploaded_image)
-        st.image(image, caption="Uploaded Image", use_column_width=True)
+    # Perform object detection when the user clicks a button
+    if st.button("Detection"):
+        # Analyze the uploaded image if available
+        if uploaded_image:
+            # Display the uploaded image
+            image = Image.open(uploaded_image)
+            st.image(image, caption="Uploaded Image", use_column_width=True)
 
-        # Perform object detection on the image
-        results = object_detection(image)
+            # Perform object detection on the image
+            results = object_detection(image)
 
-        # Display detected objects and their confidence levels
-        st.subheader("Detected Objects:")
-        for result in results:
-            label = result["label"]
-            confidence = result["score"]
-            box = result["box"]
-            st.write(f"Detected {label} with confidence {confidence:.3f} at location {box}")
+            # Display detected objects and their confidence levels
+            st.subheader("Detected Objects:")
+            for result in results:
+                label = result["label"]
+                confidence = result["score"]
+                box = result["box"]
+                st.write(f"Detected {label} with confidence {confidence:.3f} at location {box}")
+
+except Exception as e:
+    st.error(f"An error occurred: {e}")