File size: 4,410 Bytes
de51c6d
 
 
 
18f931d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9f4814
 
18f931d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9f4814
 
 
 
 
 
18f931d
 
 
 
 
 
 
 
 
ca61862
18f931d
 
 
 
 
 
 
c388d64
18f931d
 
 
 
de51c6d
 
b9f4814
23fd166
 
b9f4814
23fd166
18f931d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23fd166
de51c6d
 
 
 
 
 
 
1682357
de51c6d
23fd166
de51c6d
 
 
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import os

import gradio as gr

import sys
sys.path.insert(0, 'U-2-Net')

from skimage import io, transform
import torch
import torchvision
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms#, utils
# import torch.optim as optim

import numpy as np
from PIL import Image
import glob

from data_loader import RescaleT
from data_loader import ToTensor
from data_loader import ToTensorLab
from data_loader import SalObjDataset

from model import U2NET # full size version 173.6 MB
from model import U2NETP # small version u2net 4.7 MB

from modnet import ModNet
import huggingface_hub

# normalize the predicted SOD probability map
def normPRED(d):
    ma = torch.max(d)
    mi = torch.min(d)

    dn = (d-mi)/(ma-mi)

    return dn
def save_output(image_name,pred,d_dir):
    predict = pred
    predict = predict.squeeze()
    predict_np = predict.cpu().data.numpy()

    im = Image.fromarray(predict_np*255).convert('RGB')
    img_name = image_name.split(os.sep)[-1]
    image = io.imread(image_name)
    imo = im.resize((image.shape[1],image.shape[0]),resample=Image.BILINEAR)

    pb_np = np.array(imo)

    aaa = img_name.split(".")
    bbb = aaa[0:-1]
    imidx = bbb[0]
    for i in range(1,len(bbb)):
        imidx = imidx + "." + bbb[i]

    imo.save(d_dir+'/'+imidx+'.png')
    return d_dir+'/'+imidx+'.png'



modnet_path = huggingface_hub.hf_hub_download('hylee/apdrawing_model',
                                                      'modnet.onnx',
                                                      force_filename='modnet.onnx')
modnet = ModNet(modnet_path)

 # --------- 1. get image path and name ---------
model_name='u2net_portrait'#u2netp


image_dir = 'portrait_im'
prediction_dir = 'portrait_results'
if(not os.path.exists(prediction_dir)):
    os.mkdir(prediction_dir)

model_dir = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'U-2-Net/saved_models/u2net_portrait/u2net_portrait.pth')


# --------- 3. model define ---------

print("...load U2NET---173.6 MB")
net = U2NET(3,1)

net.load_state_dict(torch.load(model_dir, map_location='cpu'))
# if torch.cuda.is_available():
#     net.cuda()
net.eval()


def process(im):
    image = modnet.segment(im.name)
    im_path = os.path.abspath(os.path.basename(im.name))
    Image.fromarray(np.uint8(image)).save(im_path)

    img_name_list = [im_path]
    print("Number of images: ", len(img_name_list))
    # --------- 2. dataloader ---------
    # 1. dataloader
    test_salobj_dataset = SalObjDataset(img_name_list=img_name_list,
                                        lbl_name_list=[],
                                        transform=transforms.Compose([RescaleT(512),
                                                                      ToTensorLab(flag=0)])
                                        )
    test_salobj_dataloader = DataLoader(test_salobj_dataset,
                                        batch_size=1,
                                        shuffle=False,
                                        num_workers=1)

    results = []
    # --------- 4. inference for each image ---------
    for i_test, data_test in enumerate(test_salobj_dataloader):

        print("inferencing:", img_name_list[i_test].split(os.sep)[-1])

        inputs_test = data_test['image']
        inputs_test = inputs_test.type(torch.FloatTensor)

        # if torch.cuda.is_available():
        #     inputs_test = Variable(inputs_test.cuda())
        # else:
        inputs_test = Variable(inputs_test)

        d1, d2, d3, d4, d5, d6, d7 = net(inputs_test)

        # normalization
        pred = 1.0 - d1[:, 0, :, :]
        pred = normPRED(pred)

        # save results to test_results folder
        results.append(save_output(img_name_list[i_test], pred, prediction_dir))

        del d1, d2, d3, d4, d5, d6, d7

    print(results)

    return Image.open(results[0])
        
title = "U-2-Net"
description = "Gradio demo for U-2-Net, https://github.com/xuebinqin/U-2-Net"
article = ""

gr.Interface(
    process, 
    [gr.inputs.Image(type="file", label="Input")
], 
    [gr.outputs.Image(type="pil", label="Output")],
    title=title,
    description=description,
    article=article,
    examples=[],
    allow_flagging=False,
    allow_screenshot=False
    ).launch(enable_queue=True,cache_examples=True)