File size: 2,714 Bytes
80fd191
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
import numpy as np
import torch
import torch.nn.functional as F
import gradio as gr
from ormbg import ORMBG
from PIL import Image


def preprocess_image(im: np.ndarray, model_input_size: list) -> torch.Tensor:
    if len(im.shape) < 3:
        im = im[:, :, np.newaxis]
    im_tensor = torch.tensor(im, dtype=torch.float32).permute(2, 0, 1)
    im_tensor = F.interpolate(
        torch.unsqueeze(im_tensor, 0), size=model_input_size, mode="bilinear"
    ).type(torch.uint8)
    image = torch.divide(im_tensor, 255.0)
    return image


def postprocess_image(result: torch.Tensor, im_size: list) -> np.ndarray:
    result = torch.squeeze(F.interpolate(result, size=im_size, mode="bilinear"), 0)
    ma = torch.max(result)
    mi = torch.min(result)
    result = (result - mi) / (ma - mi)
    im_array = (result * 255).permute(1, 2, 0).cpu().data.numpy().astype(np.uint8)
    im_array = np.squeeze(im_array)
    return im_array


def inference(orig_image):

    model_path = "ormbg.pth"

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

    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()

    model_input_size = [1024, 1024]
    orig_im_size = orig_image.shape[0:2]
    image = preprocess_image(orig_image, model_input_size).to(device)

    result = net(image)

    # post process
    result_image = postprocess_image(result[0][0], orig_im_size)

    # save result
    pil_im = Image.fromarray(result_image)
    no_bg_image = Image.new("RGBA", pil_im.size, (0, 0, 0, 0))
    no_bg_image.paste(orig_image, mask=pil_im)

    return no_bg_image


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 = "Background Removal"
description = r"""
This model is a fully open-source background remover 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>.

You can find more about the model <a href='https://huggingface.co/schirrmacher/ormbg' target='_blank'>here</a>.
"""
examples = [
    ["./input.png"],
]

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

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