import gradio as gr
import matplotlib.pyplot as plt
from PIL import Image
from ultralyticsplus import YOLO
import cv2
import numpy as np
import requests
from io import BytesIO
import os

model = YOLO('Corn-Disease50epoch.pt')
name = ['Leaf Blight', 'Corn Rust', 'Gray Leaf Spot', 'Healthy']
image_directory = "/home/user/app/images"

def response2(image, image_size=640, conf_threshold=0.3, iou_threshold=0.6):
    results = model.predict(image, conf=conf_threshold, iou=iou_threshold, imgsz=image_size)
                       
    text = ""
    name_weap = ""
    solution = ""

    for r in results:
        im_array = r.plot()
        im = Image.fromarray(im_array[..., ::-1])

    for r in results:
        conf = np.array(r.boxes.conf.cpu())
        cls = np.array(r.boxes.cls.cpu())
        cls = cls.astype(int)
        xywh = np.array(r.boxes.xywh.cpu())
        xywh = xywh.astype(int)  
      
        for con, cl, xy in zip(conf, cls, xywh):
            cone = con.astype(float)
            conef = round(cone, 3)
            conef = conef * 100
            text += (f"Detected {name[cl]} with confidence {round(conef, 1)}% at ({xy[0]},{xy[1]})\n")
                
            if name[cl] == "Corn Rust":
                solution = (f"{solution} Apply fungicides with active ingredients like propiconazole or tebuconazole when symptoms appear.\n") 
            elif name[cl] == "Gray Leaf Spot":
                solution = (f"{solution} Use fungicides containing strobilurins (e.g., azoxystrobin) or triazoles.\n") 
            elif name[cl] == "Leaf Blight":
                solution = (f"{solution} Treat with fungicides such as mancozeb or chlorothalonil during the early stages.\n") 
           
    return im, text, solution

def pil_to_cv2(pil_image):
    open_cv_image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
    return open_cv_image

def process_video(video_path):
    cap = cv2.VideoCapture(video_path)
    
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        
        pil_img = Image.fromarray(frame[..., ::-1])  
        result = model.predict(source=pil_img)
        for r in result:
            im_array = r.plot()
            processed_frame = Image.fromarray(im_array[..., ::-1])  
        yield processed_frame
    cap.release()

inputs = [
    gr.Image(type="pil", label="Input Image"),
    gr.Slider(minimum=320, maximum=1280, value=640, step=32, label="Image Size"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.3, step=0.05, label="Confidence Threshold"),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.6, step=0.05, label="IOU Threshold"),
]

outputs = [
    gr.Image(type="pil", label="Output Image"),
    gr.Textbox(label="Result"), 
    gr.Textbox(label="Solution")
]

examples = [
    ["/home/user/app/images/jagung7.jpg", 640, 0.3, 0.6],
    ["/home/user/app/images/jagung4.jpeg", 640, 0.3, 0.6],
    ["/home/user/app/images/jagung6.jpeg", 640, 0.3, 0.6]
]

title = """Corn Diseases Detection Finetuned YOLOv11 <br></br> <a href="https://colab.research.google.com/drive/1vnxtgPKOgfC8nyCL9hjrNFed75StsqGQ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab" style="display:inline-block;"> </a> """
description = 'Image Size: Defines the image size for inference.\nConfidence Treshold: Sets the minimum confidence threshold for detections.\nIOU Treshold: Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Useful for reducing duplicates.'

video_iface = gr.Interface(
    fn=process_video,
    inputs=gr.Video(label="Upload Video", interactive=True),
    outputs=gr.Image(type="pil", label="Result"),
    title=title,
    description="Upload video for inference."
)

image_iface = gr.Interface(
    fn=response2, 
    inputs=inputs, 
    outputs=outputs, 
    examples=examples, 
    title=title, 
    description=description
)

demo = gr.TabbedInterface([image_iface, video_iface], ["Image Inference", "Video Inference"])

if __name__ == '__main__':
    demo.launch()