app.py

from ultralytics import YOLO
from PIL import Image
import gradio as gr
from huggingface_hub import snapshot_download
import os
import tempfile
import cv2

model_path = "best.onnx"


def load_model(repo_id):
    download_dir = snapshot_download(repo_id)
    print(download_dir)
    path = os.path.join(download_dir, "best.onnx")
    print(path)
    detection_model = YOLO(path, task='detect')
    return detection_model


def process_image(pilimg):
    source = pilimg
    result = detection_model.predict(source, conf=0.5)
    img_bgr = result[0].plot()
    out_pilimg = Image.fromarray(img_bgr[..., ::-1])  # RGB-order PIL image
    return out_pilimg


def process_video(video):
    cap = cv2.VideoCapture(video)
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    fps = cap.get(cv2.CAP_PROP_FPS)

    temp_dir = tempfile.mkdtemp()
    fourcc = cv2.VideoWriter_fourcc(*'MP4V')
    output_path = os.path.join(temp_dir, "output.mp4")
    output = cv2.VideoWriter(output_path, fourcc, fps, (int(width), int(height)))

    # Loop through the video frames
    while cap.isOpened():
        # Read a frame from the video
        success, frame = cap.read()

        if success:
            # Run YOLO inference on the frame on GPU Device 0
            results = detection_model.predict(frame, conf=0.5)

            # Visualize the results on the frame
            annotated_frame = results[0].plot()

            # Write the annotated frame
            output.write(annotated_frame)

    output.release()
    output.release()
    cv2.destroyAllWindows()
    cv2.waitKey(1)
    return output_path


REPO_ID = "1657866Y/grocery"
detection_model = load_model(REPO_ID)

# Create the interface for image upload
image_interface = gr.Interface(fn=process_image,
                               inputs=gr.Image(type="pil"),
                               outputs=gr.Image(type="pil"))

# Create the interface for video upload
video_interface = gr.Interface(fn=process_video,
                               inputs=gr.Video(label="Upload a Video"),
                               outputs="video")

# Use gr.Blocks to arrange components and launch the app
with gr.Blocks() as app:
    # Add a header using Markdown
    gr.Markdown("# Grocery? No wait!")
    gr.Markdown("Choose whether to upload an image or a video below!")

    # Add the tabbed interface
    gr.TabbedInterface([image_interface, video_interface],
                       tab_names=["Image Upload", "Video Upload"])


# Launch the interface
app.launch()