Delete app.py

app.py

@@ -1,59 +0,0 @@
-import streamlit as st
-from ultralytics import YOLO
-import cv2
-from gtts import gTTS
-import tempfile
-import os
-from PIL import Image
-import numpy as np
-
-# Load YOLOv8 model
-@st.cache_resource
-def load_model():
-    return YOLO("yolov8n.pt")  # Automatically downloads and loads YOLOv8 model
-
-model = load_model()
-
-# Streamlit App
-st.title("Real-Time Object Detection for Blind Assistance")
-st.write(
-    "This app detects objects in real-time using a webcam feed or video stream and provides audio feedback."
-)
-
-# Use Streamlit's camera input
-video_feed = st.camera_input("Enable Webcam Feed")
-
-if video_feed is not None:
-    # Convert video_feed to an image
-    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".jpg")
-    temp_file.write(video_feed.getvalue())
-
-    # Load the captured frame
-    frame = cv2.imread(temp_file.name)
-
-    # Convert to RGB (if needed, for PIL compatibility)
-    frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-
-    # Perform object detection
-    results = model(frame_rgb)
-
-    # Annotate the frame
-    annotated_frame = results[0].plot()
-
-    # Convert annotated frame back to displayable format
-    annotated_image = Image.fromarray(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
-
-    # Display annotated frame in Streamlit
-    st.image(annotated_image, caption="Real-Time Detection", use_column_width=True)
-
-    # Generate feedback for detected objects
-    detected_objects = [model.names[int(box.cls)] for box in results[0].boxes]
-    if detected_objects:
-        objects_text = ", ".join(set(detected_objects))
-        st.write(f"Detected objects: {objects_text}")
-
-        # Provide audio feedback
-        tts = gTTS(text=f"Detected objects are: {objects_text}", lang="en")
-        audio_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
-        tts.save(audio_file.name)
-        st.audio(audio_file.name, format="audio/mp3")