import numpy as np
import torch
import torch.nn.functional as F
import gradio as gr
from ormbg import ORMBG
from PIL import Image
import requests

model_path = "ormbg.pth"

net = ORMBG()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net.to(device)

if torch.cuda.is_available():
    net.load_state_dict(torch.load(model_path))
    net = net.cuda()
else:
    net.load_state_dict(torch.load(model_path, map_location="cpu"))
net.eval()

def resize_image(image):
    image = image.convert("RGB")
    model_input_size = (1024, 1024)
    image = image.resize(model_input_size, Image.BILINEAR)
    return image

def inference(image):
    orig_image = image
    w, h = orig_image.size
    image = resize_image(orig_image)
    im_np = np.array(image)
    im_tensor = torch.tensor(im_np, dtype=torch.float32).permute(2, 0, 1)
    im_tensor = torch.unsqueeze(im_tensor, 0)
    im_tensor = torch.divide(im_tensor, 255.0)
    if torch.cuda.is_available():
        im_tensor = im_tensor.cuda()

    result = net(im_tensor)
    result = torch.squeeze(F.interpolate(result[0][0], size=(h, w), mode="bilinear"), 0)
    ma = torch.max(result)
    mi = torch.min(result)
    result = (result - mi) / (ma - mi)
    im_array = (result * 255).cpu().data.numpy().astype(np.uint8)
    pil_im = Image.fromarray(np.squeeze(im_array))
    new_im = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
    new_im.paste(orig_image, mask=pil_im)

    return new_im

# Ссылка на файл CSS
css_url = "https://neurixyufi-aihub.static.hf.space/style.css"

# Получение CSS по ссылке
response = requests.get(css_url)
css = response.text + "h1{text-align:center}"

with gr.Blocks(css=css) as demo:
    gr.Markdown("# Удаление фона")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(label="Загрузите изображение с фоном", type="pil")
            submit_button = gr.Button("Удалить фон")
        with gr.Column():
            output_image = gr.Image(label="Изображение без фона", type="pil")
    
    submit_button.click(
        fn=inference,
        inputs=input_image,
        outputs=output_image,
        concurrency_limit=10
    )

if __name__ == "__main__":
    demo.launch(share=False)