Update app.py

added image url in inference tool

app.py

@@ -5,6 +5,9 @@ import numpy as np
 import time
 from PIL import Image
 from ultralytics import YOLO
+import requests
+from io import BytesIO
+
 
 def save_uploaded_file(uploaded_file):
     """Save an uploaded file to a temporary file and return its path."""
@@ -13,19 +16,41 @@ def save_uploaded_file(uploaded_file):
         return tmp_file.name
 
 def yolo_inference_tool():
-    """
-    Single-model, single-image inference subpage (example).
-    """
     st.header("YOLO Model Inference Tool")
-    st.write("Upload one or more images and a YOLO model (.pt) file to run inference and view detailed results.")
+    st.write(
+        "Upload one or more images and a YOLO model (.pt) file to run inference and view detailed results. "
+        "You can either upload images or provide an image URL."
+    )
     
     # Allow multiple images upload
-    images = st.file_uploader("Upload Images", type=["jpg", "jpeg", "png"], key="inference_images", accept_multiple_files=True)
+    uploaded_files = st.file_uploader(
+        "Upload Images", type=["jpg", "jpeg", "png"], key="inference_images", accept_multiple_files=True
+    )
+    # Text input for a single image URL (you could expand this to multiple URLs if needed)
+    url_input = st.text_input("Enter image URL (optional)", key="inference_url")
+    
+    # Combine uploaded files and URL image into a single list
+    images = []
+    if uploaded_files:
+        images.extend(uploaded_files)
+    if url_input and url_input.strip():
+        try:
+            response = requests.get(url_input)
+            if response.status_code == 200:
+                image_bytes = BytesIO(response.content)
+                # Assign a name attribute for consistency
+                image_bytes.name = url_input
+                images.append(image_bytes)
+            else:
+                st.error("Failed to fetch image from URL.")
+        except Exception as e:
+            st.error(f"Error fetching image from URL: {e}")
+
     model_file = st.file_uploader("Upload YOLO model (.pt)", type=["pt"], key="inference_model")
     
     if st.button("Submit (Single-Model Inference)"):
         if not images or not model_file:
-            st.error("Please upload at least one image and a model.")
+            st.error("Please upload at least one image (or provide an image URL) and a model.")
             return
 
         # Save and load the model file
@@ -60,25 +85,34 @@ def yolo_inference_tool():
             try:
                 pil_img = Image.open(img_file).convert("RGB")
             except Exception as e:
-                st.error(f"Error reading image {img_file.name}: {e}")
+                st.error(f"Error reading image {getattr(img_file, 'name', 'Unknown')}: {e}")
                 continue
 
             try:
                 result = model(np.array(pil_img))
             except Exception as e:
-                st.error(f"Inference error on image {img_file.name}: {e}")
+                st.error(f"Inference error on image {getattr(img_file, 'name', 'Unknown')}: {e}")
                 continue
 
             r = result[0]
-            image_results[img_file.name] = r
+            image_results[getattr(img_file, 'name', 'Unknown')] = r
 
-            # Collect basic metrics if available (e.g., inference time and detections)
+            # Get inference time from r.speed, if available
             inference_time = r.speed.get('inference', None) if isinstance(r.speed, dict) else None
-            detection_count = len(r.boxes) if r.boxes is not None else 0
+            # Compute detection count and average confidence if detections exist
+            if r.boxes is not None and len(r.boxes) > 0:
+                detection_count = len(r.boxes)
+                confs = r.boxes.conf.cpu().numpy() if hasattr(r.boxes.conf, "cpu") else r.boxes.conf
+                avg_conf = float(np.mean(confs))
+            else:
+                detection_count = 0
+                avg_conf = 0.0
+
             metrics.append({
-                "Image": img_file.name,
+                "Image": getattr(img_file, 'name', 'Unknown'),
                 "Inference Time (ms)": inference_time if inference_time is not None else "N/A",
-                "Detections": detection_count
+                "Detections": detection_count,
+                "Average Confidence": f"{avg_conf:.2f}"
             })
         
         eta_placeholder.empty()
@@ -89,7 +123,7 @@ def yolo_inference_tool():
             df_metrics = pd.DataFrame(metrics)
             st.dataframe(df_metrics, use_container_width=True)
         
-        # Display annotated images (using pil=True to ensure RGB output)
+        # Display annotated images using pil=True (ensuring RGB)
         st.subheader("Annotated Images")
         for img_name, r in image_results.items():
             try:
@@ -98,6 +132,7 @@ def yolo_inference_tool():
             except Exception as e:
                 st.error(f"Error generating annotated image for {img_name}: {e}")
 
+
 def yolo_model_comparison_tool():
     """
     Multi-model, multi-image comparison subpage,