Update app.py

app.py

@@ -1,54 +1,95 @@
-# streamlit_yolo_segmentation.py
-
-import streamlit as st
-import cv2
-import numpy as np
-from ultralytics import YOLO
-from PIL import Image
-
-# -------------------------------
-# Streamlit App Title
-# -------------------------------
-st.title("YOLOv8 Image Segmentation")
-
-# -------------------------------
-# Load YOLO Segmentation Model
-# -------------------------------
-@st.cache_resource
-def load_model(model_name="yolov8n-seg.pt"):
-    return YOLO(model_name)
-
-model = load_model()
-
-# -------------------------------
-# Upload Image
-# -------------------------------
-uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
-
-if uploaded_file is not None:
-    # Load uploaded image
-    image = Image.open(uploaded_file).convert("RGB")
-    img_array = np.array(image)
-
-    # Perform Inference
-    results = model(img_array)
-
-    # Annotated results with masks
-    annotated_img = results[0].plot()
-
-    # Get shape of annotated image
-    h, w, c = annotated_img.shape
-    st.write(f"**Annotated Image Shape:** {h} x {w} x {c}")
-
-    # Display Input and Output
-    col1, col2 = st.columns(2)
-    with col1:
-        st.image(image, caption="Original Image", use_column_width=True)
-    with col2:
-        st.image(annotated_img, caption="Segmented Image", use_column_width=True)
-
-    # Option to download the annotated image
-    result_bgr = cv2.cvtColor(annotated_img, cv2.COLOR_RGB2BGR)
-    cv2.imwrite("segmented_output.jpg", result_bgr)
-    with open("segmented_output.jpg", "rb") as f:
-        st.download_button("Download Segmented Image", f, "segmented_output.jpg")
+# app.py
+
+import streamlit as st
+import cv2
+import numpy as np
+from ultralytics import YOLO
+from PIL import Image
+import pandas as pd
+
+# -------------------------------
+# Streamlit Page Config
+# -------------------------------
+st.set_page_config(page_title="YOLOv8 Object Detection", page_icon="🤖", layout="wide")
+
+# -------------------------------
+# App Title
+# -------------------------------
+st.title("🤖 YOLOv8 Object Detection App")
+st.markdown(
+    """
+    Upload an image and let **YOLOv8** detect objects in real-time.  
+    You can adjust detection parameters in the sidebar.  
+    """
+)
+
+# -------------------------------
+# Sidebar Controls
+# -------------------------------
+st.sidebar.header("⚙️ Detection Settings")
+confidence = st.sidebar.slider("Confidence Threshold", 0.1, 1.0, 0.25, 0.05)
+iou = st.sidebar.slider("IoU Threshold", 0.1, 1.0, 0.45, 0.05)
+
+st.sidebar.markdown("---")
+st.sidebar.info("Built with [YOLOv8](https://docs.ultralytics.com/) and [Streamlit](https://streamlit.io/)")
+
+# -------------------------------
+# Load YOLO Model
+# -------------------------------
+@st.cache_resource
+def load_model(model_name="yolov8n.pt"):
+    return YOLO(model_name)
+
+model = load_model()
+
+# -------------------------------
+# Upload Image
+# -------------------------------
+uploaded_file = st.file_uploader("📷 Upload an image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Load uploaded image
+    image = Image.open(uploaded_file).convert("RGB")
+    img_array = np.array(image)
+
+    with st.spinner("🔍 Detecting objects..."):
+        results = model.predict(img_array, conf=confidence, iou=iou)
+
+    # Annotated results
+    annotated_img = results[0].plot()
+
+    # Display Input and Output
+    col1, col2 = st.columns(2)
+    with col1:
+        st.image(image, caption="Original Image", use_column_width=True)
+    with col2:
+        st.image(annotated_img, caption="Detected Objects", use_column_width=True)
+
+    # -------------------------------
+    # Show Detection Details
+    # -------------------------------
+    st.subheader("📊 Detection Results")
+
+    if len(results[0].boxes) > 0:
+        data = []
+        for box in results[0].boxes:
+            cls = model.names[int(box.cls)]
+            conf = float(box.conf)
+            x1, y1, x2, y2 = box.xyxy[0].tolist()
+            data.append([cls, round(conf, 3), int(x1), int(y1), int(x2), int(y2)])
+
+        df = pd.DataFrame(data, columns=["Class", "Confidence", "X1", "Y1", "X2", "Y2"])
+        st.dataframe(df, use_container_width=True)
+
+        # Option to download CSV
+        csv = df.to_csv(index=False).encode("utf-8")
+        st.download_button("📥 Download Results as CSV", csv, "detections.csv", "text/csv")
+
+    else:
+        st.warning("No objects detected.")
+
+    # Option to download the annotated image
+    result_bgr = cv2.cvtColor(annotated_img, cv2.COLOR_RGB2BGR)
+    cv2.imwrite("annotated_output.jpg", result_bgr)
+    with open("annotated_output.jpg", "rb") as f:
+        st.download_button("📥 Download Annotated Image", f, "annotated_output.jpg")