app.py

import gradio as gr
import cv2
import requests
import os

from ultralytics import YOLO

model = YOLO("best_model.pt")
example_imgs = [
    os.path.join("example", "img", example) for example in os.listdir("example/img")
]
example_vids = [
    os.path.join("example", "vid", example) for example in os.listdir("example/vid")
]


def show_preds_image(image_path):
    image = cv2.imread(image_path)
    outputs = model.predict(source=image_path)
    results = outputs[0].cpu().numpy()
    for i, det in enumerate(results.boxes.xyxy):
        cv2.rectangle(
            image,
            (int(det[0]), int(det[1])),
            (int(det[2]), int(det[3])),
            color=(0, 0, 255),
            thickness=2,
            lineType=cv2.LINE_AA,
        )
    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)


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


# Define the Gradio interface for image input
interface_image = gr.Interface(
    fn=show_preds_image,
    inputs=gr.components.Image(type="filepath", label="Input Image"),
    outputs=gr.components.Image(type="numpy", label="Output Image"),
    title="Pothole Detector - Image",
    examples=example_imgs,
    cache_examples=False,
)


# For video processing, it's best to process and then show the output video.
def show_preds_video(video_path):
    cap = cv2.VideoCapture(video_path)
    while(cap.isOpened()):
        ret, frame = cap.read()
        if ret:
            frame_copy = frame.copy()
            outputs = model.predict(source=frame)
            results = outputs[0].cpu().numpy()
            for det in results.boxes.xyxy:
                cv2.rectangle(
                    frame_copy,
                    (int(det[0]), int(det[1])),
                    (int(det[2]), int(det[3])),
                    color=(0, 0, 255),
                    thickness=2,
                    lineType=cv2.LINE_AA
                )
            yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
        else:
            break
    cap.release()
    
inputs_video = gr.components.Video(label="Input Video")
outputs_video = gr.components.Image(label="Output Image", type="numpy")

interface_video = gr.Interface(
    fn=show_preds_video,
    inputs=inputs_video,
    outputs=outputs_video,
    title="Pothole Detector",
    examples=example_vids,
    cache_examples=False,
)
# Combine the interfaces into a tabbed interface
gr.TabbedInterface(
    [interface_image, interface_video], tab_names=["Image Inference", "Video Inference"]
).launch()