Spaces:
Sleeping
Sleeping
| import cv2 | |
| import torch | |
| import gradio as gr | |
| import numpy as np | |
| from ultralytics import YOLO | |
| # Load YOLOv8 model and set device (GPU if available) | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model = YOLO('./data/best.pt') # Path to your model | |
| model.to(device) | |
| # Define the function that processes the uploaded video | |
| def process_video(video): | |
| # video is now the file path string, not a file object | |
| input_video = cv2.VideoCapture(video) # Directly pass the path to cv2.VideoCapture | |
| # Get frame width, height, and fps from input video | |
| frame_width = int(input_video.get(cv2.CAP_PROP_FRAME_WIDTH)) | |
| frame_height = int(input_video.get(cv2.CAP_PROP_FRAME_HEIGHT)) | |
| fps = input_video.get(cv2.CAP_PROP_FPS) | |
| # Resize to reduce computation (optional) | |
| new_width, new_height = 640, 480 # Resize to 640x480 resolution | |
| frame_width, frame_height = new_width, new_height | |
| # List to store processed frames for Gradio output | |
| processed_frames = [] | |
| frame_counter = 0 # Counter to limit the number of frames for processing | |
| while True: | |
| # Read a frame from the video | |
| ret, frame = input_video.read() | |
| if not ret: | |
| break # End of video | |
| # Resize the frame to reduce computational load | |
| frame = cv2.resize(frame, (new_width, new_height)) | |
| # Perform inference on the frame | |
| results = model(frame) # Automatically uses GPU if available | |
| # Check if any object was detected | |
| if len(results[0].boxes) > 0: # If there are detected objects | |
| # Annotate the frame with bounding boxes | |
| annotated_frame = results[0].plot() # Plot the frame with bounding boxes | |
| # Convert the annotated frame to RGB format for displaying | |
| annotated_frame_rgb = cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB) | |
| # Append the annotated frame to the list for Gradio | |
| processed_frames.append(annotated_frame_rgb) | |
| # Limit the number of frames processed (to speed up processing) | |
| frame_counter += 1 | |
| if frame_counter > 100: # Process only 100 frames, adjust as necessary | |
| break | |
| # Release resources | |
| input_video.release() | |
| # Return the processed frames for Gradio to display as a video | |
| return processed_frames | |
| # Create a Gradio interface for video upload | |
| iface = gr.Interface(fn=process_video, | |
| inputs=gr.Video(label="Upload Video"), # Updated line | |
| outputs=gr.Video(label="Processed Video"), # This will display the output video directly | |
| title="YOLOv8 Object Detection - Real-Time Display", | |
| description="Upload a video for object detection using YOLOv8. The frames with detections will be shown in real-time.") | |
| # Launch the interface | |
| iface.launch() | |