app.py

import gradio as gr
import cv2
import requests
import os

from ultralytics import YOLO

file_urls = [
    'https://huggingface.co/spaces/iamsuman/ripe-and-unripe-tomatoes-detection/resolve/main/samples/riped_tomato_93.jpeg?download=true',
    'https://huggingface.co/spaces/iamsuman/ripe-and-unripe-tomatoes-detection/resolve/main/samples/unriped_tomato_18.jpeg?download=true',
    'https://huggingface.co/spaces/iamsuman/ripe-and-unripe-tomatoes-detection/resolve/main/samples/tomatoes.mp4?download=true',
]

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

for i, url in enumerate(file_urls):
    if 'mp4' in file_urls[i]:
        download_file(
            file_urls[i],
            f"video.mp4"
        )
    else:
        download_file(
            file_urls[i],
            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)
    outputs = model.predict(source=image_path)
    results = outputs[0].cpu().numpy()

    # Print the detected objects' information (class, coordinates, and probability)
    box = results[0].boxes
    names = model.model.names
    boxes = results.boxes

    for box, conf, cls in zip(boxes.xyxy, boxes.conf, boxes.cls):

        x1, y1, x2, y2 = map(int, box)

        class_name = names[int(cls)]
        print(class_name, "class_name", class_name.lower() == 'ripe')
        if class_name.lower() == 'ripe':
            color = (0, 0, 255)  # Red for ripe
        else:
            color = (0, 255, 0)  # Green for unripe

        # Draw rectangle around object
        cv2.rectangle(
            image,
            (x1, y1),
            (x2, y2),
            color=color,
            thickness=2,
            lineType=cv2.LINE_AA
        )

        # Display class label on top of rectangle
        label = f"{class_name.capitalize()}: {conf:.2f}"
        cv2.putText(image, label, (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, color,  # Use the same color as the rectangle
            2,
            cv2.LINE_AA)
        
    # Convert image to RGB (Gradio expects RGB format)
    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    

inputs_image = [
    gr.components.Image(type="filepath", label="Input Image"),
]
outputs_image = [
    gr.components.Image(type="numpy", label="Output Image"),
]
interface_image = gr.Interface(
    fn=show_preds_image,
    inputs=inputs_image,
    outputs=outputs_image,
    title="Ripe And Unripe Tomatoes Detection",
    examples=path,
    cache_examples=False,
)

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()
            
            boxes = results.boxes
            confidences = boxes.conf
            classes = boxes.cls
            names = model.model.names

            for box, conf, cls in zip(boxes.xyxy, confidences, classes):
                x1, y1, x2, y2 = map(int, box)

                # Determine color based on class
                class_name = names[int(cls)]
                if class_name.lower() == 'ripe':
                    color = (0, 0, 255)  # Red for ripe
                else:
                    color = (0, 255, 0)  # Green for unripe

                # Draw rectangle around object
                cv2.rectangle(
                    frame_copy,
                    (x1, y1),
                    (x2, y2),
                    color=color,
                    thickness=2,
                    lineType=cv2.LINE_AA
                )

                # Display class label on top of rectangle with capitalized class name
                label = f"{class_name.capitalize()}: {conf:.2f}"
                cv2.putText(
                    frame_copy,
                    label,
                    (x1, y1 - 10),  # Position slightly above the top of the rectangle
                    cv2.FONT_HERSHEY_SIMPLEX,
                    0.5,
                    color,  # Use the same color as the rectangle
                    1,
                    cv2.LINE_AA
                )

            # Convert frame to RGB (Gradio expects RGB format)
            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(type="numpy", label="Output Image"),
]
interface_video = gr.Interface(
    fn=show_preds_video,
    inputs=inputs_video,
    outputs=outputs_video,
    title="Ripe And Unripe Tomatoes Detection",
    examples=video_path,
    cache_examples=False,
)

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