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


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):

    # prepare input
    orig_image = Image.fromarray(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()

    # inference
    result = net(im_tensor)
    # post process
    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)
    # image to pil
    im_array = (result * 255).cpu().data.numpy().astype(np.uint8)
    pil_im = Image.fromarray(np.squeeze(im_array))
    # paste the mask on the original image
    new_im = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
    new_im.paste(orig_image, mask=pil_im)

    return new_im


gr.Markdown("## Open Remove Background Model (ormbg)")
gr.HTML(
    """
  <p style="margin-bottom: 10px; font-size: 94%">
    This is a demo for Open Remove Background Model (ormbg) that using
    <a href="https://huggingface.co/schirrmacher/ormbg" target="_blank">Open Remove Background Model (ormbg) model</a> as backbone.
  </p>
"""
)
title = "Open Remove Background Model (ormbg)"
description = r"""
This model is a <strong>fully open-source background remover</strong> optimized for images with humans.
It is based on <a href='https://github.com/xuebinqin/DIS' target='_blank'>Highly Accurate Dichotomous Image Segmentation research</a>.

<a href='https://huggingface.co/schirrmacher/ormbg' target='_blank'>Model information here.</a>
"""
examples = [
    ["./example1.png", "./example2.png", "./example3.png"],
]

demo = gr.Interface(
    fn=inference,
    inputs="image",
    outputs="image",
    examples=examples,
    title=title,
    description=description,
)

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