import gradio as gr
import cv2
import requests
import os
from PIL import Image
import torch
import ultralytics

model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5_0.65map_exp7_best.pt",
                        force_reload=False) 

model.conf = 0.20  # NMS confidence threshold

path  = [['img/test-image.jpg'], ['img/test-image-2.jpg']]

# def show_preds_image(image_path):
#     image = cv2.imread(image_path)
#     # outputs = model(source=image_path)
#     # results = outputs[0].cpu().numpy()
#     results = model(image_path)
#     results.xyxy[0]  # img1 predictions (tensor)
#     results.pandas().xyxy[0]  # img1 predictions (pandas)
#     predictions = results.pred[0]
#     boxes = predictions[:, :4] # x1, y1, x2, y2
#     scores = predictions[:, 4]
#     categories = predictions[:, 5]

#     # 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 results.show()

def show_preds_image(im, size=640):
    g = (size / max(im.size))  # gain
    im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize

    results = model(im)  # inference
    results.render()  # updates results.imgs with boxes and labels
    results.save()
    os.system("ls")
    return "out.png"

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

interface_image.launch()