Create app.py

app.py

@@ -0,0 +1,49 @@
+import streamlit as st
+from huggingface_hub import hf_hub_download
+from ultralytics import YOLO
+import cv2
+import numpy as np
+from PIL import Image
+
+# Define repository and file path
+repo_id = "krishnamishra8848/Face_Mask_Detection"
+filename = "best.pt"  # File name in your Hugging Face repo
+
+# Download the model file
+model_path = hf_hub_download(repo_id=repo_id, filename=filename)
+
+# Load the YOLO model
+model = YOLO(model_path)
+
+# Streamlit UI
+st.title("Face Mask Detection with YOLOv8")
+st.write("Upload an image to detect face masks.")
+
+# File upload
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    # Load image
+    image = Image.open(uploaded_file)
+    image_np = np.array(image)
+
+    # Run inference
+    st.write("Running inference...")
+    results = model.predict(source=image_np, conf=0.5)
+
+    # Annotate image
+    annotated_image = None
+    for result in results:
+        annotated_image = result.plot()
+
+    # Convert annotated image for Streamlit
+    if annotated_image is not None:
+        annotated_image_rgb = cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB)
+        st.image(annotated_image_rgb, caption="Prediction Results", use_column_width=True)
+
+    # Display bounding boxes and confidence scores
+    st.write("Detection Results:")
+    for result in results:
+        for box in result.boxes.data.cpu().numpy():
+            x1, y1, x2, y2, conf, cls = box
+            st.write(f"Class: {int(cls)}, Confidence: {conf:.2f}, Box: [{x1:.0f}, {y1:.0f}, {x2:.0f}, {y2:.0f}]")