Upload yolo_applicaiton.py

yolo_applicaiton.py

@@ -0,0 +1,163 @@
+import streamlit as st
+import cv2
+from PIL import Image
+import os
+from ultralytics import YOLO
+
+# Ensure the temp directory exists
+if not os.path.exists("temp"):
+    os.makedirs("temp")
+
+# HTML/CSS for the header and container styling
+header_html = """
+<header style="background-color: #4CAF50; color: white; padding: 10px 0; text-align: center;">
+    <h1>Auto License Plate Detector</h1>
+</header>
+"""
+
+container_style = """
+<style>
+    .container {
+        width: 80%;
+        margin: 20px auto;
+        background-color: white;
+        padding: 20px;
+        box-shadow: 0 0 10px rgba(0,0,0,0.1);
+        text-align: center;
+    }
+    .image-section {
+        margin-bottom: 20px;
+    }
+    .image-section img {
+        max-width: 100%;
+        height: auto;
+        display: white;
+        margin: 0 auto;
+    }
+</style>
+"""
+
+# Insert header and style into the Streamlit app
+st.markdown(header_html, unsafe_allow_html=True)
+st.markdown(container_style, unsafe_allow_html=True)
+
+# Allow users to upload images or videos
+uploaded_file = st.file_uploader("Upload an image or video",
+                                 type=["jpg", "jpeg", "png", "bmp", "mp4", "avi", "mov", "mkv"])
+
+# Load YOLO model
+try:
+    model = YOLO('best.pt')  # Use the relative path to your trained YOLO model
+except Exception as e:
+    st.error(f"Error loading YOLO model: {e}")
+
+
+def predict_and_save_image(path_test_car, output_image_path):
+    """
+    Predicts and saves the bounding boxes on the given test image using the trained YOLO model.
+
+    Parameters:
+    path_test_car (str): Path to the test image file.
+    output_image_path (str): Path to save the output image file.
+
+    Returns:
+    str: The path to the saved output image file.
+    """
+    try:
+        results = model.predict(path_test_car, device='cpu')
+        image = cv2.imread(path_test_car)
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        for result in results:
+            for box in result.boxes:
+                x1, y1, x2, y2 = map(int, box.xyxy[0])
+                confidence = box.conf[0]
+                cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                cv2.putText(image, f'{confidence * 100:.2f}%', (x1, y1 - 10),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 0, 0), 2)
+        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+        cv2.imwrite(output_image_path, image)
+        return output_image_path
+    except Exception as e:
+        st.error(f"Error processing image: {e}")
+        return None
+
+
+def predict_and_plot_video(video_path, output_path):
+    """
+    Predicts and saves the bounding boxes on the given test video using the trained YOLO model.
+
+    Parameters:
+    video_path (str): Path to the test video file.
+    output_path (str): Path to save the output video file.
+
+    Returns:
+    str: The path to the saved output video file.
+    """
+    try:
+        cap = cv2.VideoCapture(video_path)
+        if not cap.isOpened():
+            st.error(f"Error opening video file: {video_path}")
+            return None
+        frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        fps = int(cap.get(cv2.CAP_PROP_FPS))
+        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+        out = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            results = model.predict(rgb_frame, device='cpu')
+            for result in results:
+                for box in result.boxes:
+                    x1, y1, x2, y2 = map(int, box.xyxy[0])
+                    confidence = box.conf[0]
+                    cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                    cv2.putText(frame, f'{confidence * 100:.2f}%', (x1, y1 - 10),
+                                cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 0, 0), 2)
+            out.write(frame)
+        cap.release()
+        out.release()
+        return output_path
+    except Exception as e:
+        st.error(f"Error processing video: {e}")
+        return None
+
+
+def process_media(input_path, output_path):
+    """
+    Processes the uploaded media file (image or video) and returns the path to the saved output file.
+
+    Parameters:
+    input_path (str): Path to the input media file.
+    output_path (str): Path to save the output media file.
+
+    Returns:
+    str: The path to the saved output media file.
+    """
+    file_extension = os.path.splitext(input_path)[1].lower()
+    if file_extension in ['.mp4', '.avi', '.mov', '.mkv']:
+        return predict_and_plot_video(input_path, output_path)
+    elif file_extension in ['.jpg', '.jpeg', '.png', '.bmp']:
+        return predict_and_save_image(input_path, output_path)
+    else:
+        st.error(f"Unsupported file type: {file_extension}")
+        return None
+
+
+if uploaded_file is not None:
+    input_path = os.path.join("temp", uploaded_file.name)
+    output_path = os.path.join("temp", f"output_{uploaded_file.name}")
+    try:
+        with open(input_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        st.write("Processing...")
+        result_path = process_media(input_path, output_path)
+        if result_path:
+            if input_path.endswith(('.mp4', '.avi', '.mov', '.mkv')):
+                st.video(result_path)
+            else:
+                st.image(result_path)
+    except Exception as e:
+        st.error(f"Error uploading or processing file: {e}")