app.py

import gradio as gr
import cv2
import requests
import os
from ultralytics import YOLO

file_urls = [
    'https://www.dropbox.com/s/b5g97xo901zb3ds/pothole_example.jpg?dl=1',
    'https://www.dropbox.com/s/86uxlxxlm1iaexa/pothole_screenshot.png?dl=1',
    'https://www.dropbox.com/s/7sjfwncffg8xej2/video_7.mp4?dl=1'
]

def download_file(url, save_name):
    if not os.path.exists(save_name):
        file = requests.get(url)
        with open(save_name, 'wb') as f:
            f.write(file.content)

for i, url in enumerate(file_urls):
    if url.endswith('.mp4') or '.mp4?' in url:
        download_file(url, 'video.mp4')
    else:
        download_file(url, f'image_{i}.jpg')

model = YOLO('best.pt')
path = [['image_0.jpg'], ['image_1.jpg']]
video_path = [['video.mp4']]

def show_preds_image(image_path):
    image = cv2.imread(image_path)
    results = model(image_path)[0]
    for box in results.boxes.xyxy:
        cv2.rectangle(
            image,
            (int(box[0]), int(box[1])),
            (int(box[2]), int(box[3])),
            color=(0, 0, 255),
            thickness=2,
            lineType=cv2.LINE_AA
        )
    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

inputs_image = [
    gr.Image(type="filepath", label="Input Image"),
]
outputs_image = [
    gr.Image(type="numpy", label="Output Image"),
]
interface_image = gr.Interface(
    fn=show_preds_image,
    inputs=inputs_image,
    outputs=outputs_image,
    title="Pothole detector",
    examples=path,
    cache_examples=False,
)

def show_preds_video(video_path):
    cap = cv2.VideoCapture(video_path)
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        frame_copy = frame.copy()
        results = model(frame_copy)[0]
        for box in results.boxes.xyxy:
            cv2.rectangle(
                frame_copy,
                (int(box[0]), int(box[1])),
                (int(box[2]), int(box[3])),
                color=(0, 0, 255),
                thickness=2,
                lineType=cv2.LINE_AA
            )
        yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
    cap.release()

inputs_video = [
    gr.Video(label="Input Video"),
]
outputs_video = [
    gr.Image(type="numpy", label="Output Frame"),
]
interface_video = gr.Interface(
    fn=show_preds_video,
    inputs=inputs_video,
    outputs=outputs_video,
    title="Pothole detector",
    examples=video_path,
    cache_examples=False,
)

gr.TabbedInterface(
    [interface_image, interface_video],
    tab_names=['Image inference', 'Video inference']
).queue().launch()