-
Notifications
You must be signed in to change notification settings - Fork 111
/
Copy pathrun.py
151 lines (118 loc) · 7.02 KB
/
run.py
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
#!/usr/bin/env python
import getopt
import numpy
import PIL
import PIL.Image
import sys
import torch
##########################################################
torch.set_grad_enabled(False) # make sure to not compute gradients for computational performance
torch.backends.cudnn.enabled = True # make sure to use cudnn for computational performance
##########################################################
args_strModel = 'bsds500' # only 'bsds500' for now
args_strIn = './images/sample.png'
args_strOut = './out.png'
for strOption, strArg in getopt.getopt(sys.argv[1:], '', [
'model=',
'in=',
'out=',
])[0]:
if strOption == '--model' and strArg != '': args_strModel = strArg # which model to use
if strOption == '--in' and strArg != '': args_strIn = strArg # path to the input image
if strOption == '--out' and strArg != '': args_strOut = strArg # path to where the output should be stored
# end
##########################################################
class Network(torch.nn.Module):
def __init__(self):
super().__init__()
self.netVggOne = torch.nn.Sequential(
torch.nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False)
)
self.netVggTwo = torch.nn.Sequential(
torch.nn.MaxPool2d(kernel_size=2, stride=2),
torch.nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False)
)
self.netVggThr = torch.nn.Sequential(
torch.nn.MaxPool2d(kernel_size=2, stride=2),
torch.nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False)
)
self.netVggFou = torch.nn.Sequential(
torch.nn.MaxPool2d(kernel_size=2, stride=2),
torch.nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False)
)
self.netVggFiv = torch.nn.Sequential(
torch.nn.MaxPool2d(kernel_size=2, stride=2),
torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False),
torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
torch.nn.ReLU(inplace=False)
)
self.netScoreOne = torch.nn.Conv2d(in_channels=64, out_channels=1, kernel_size=1, stride=1, padding=0)
self.netScoreTwo = torch.nn.Conv2d(in_channels=128, out_channels=1, kernel_size=1, stride=1, padding=0)
self.netScoreThr = torch.nn.Conv2d(in_channels=256, out_channels=1, kernel_size=1, stride=1, padding=0)
self.netScoreFou = torch.nn.Conv2d(in_channels=512, out_channels=1, kernel_size=1, stride=1, padding=0)
self.netScoreFiv = torch.nn.Conv2d(in_channels=512, out_channels=1, kernel_size=1, stride=1, padding=0)
self.netCombine = torch.nn.Sequential(
torch.nn.Conv2d(in_channels=5, out_channels=1, kernel_size=1, stride=1, padding=0),
torch.nn.Sigmoid()
)
self.load_state_dict({ strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.hub.load_state_dict_from_url(url='http://content.sniklaus.com/github/pytorch-hed/network-' + args_strModel + '.pytorch', file_name='hed-' + args_strModel).items() })
# end
def forward(self, tenInput):
tenInput = tenInput * 255.0
tenInput = tenInput - torch.tensor(data=[104.00698793, 116.66876762, 122.67891434], dtype=tenInput.dtype, device=tenInput.device).view(1, 3, 1, 1)
tenVggOne = self.netVggOne(tenInput)
tenVggTwo = self.netVggTwo(tenVggOne)
tenVggThr = self.netVggThr(tenVggTwo)
tenVggFou = self.netVggFou(tenVggThr)
tenVggFiv = self.netVggFiv(tenVggFou)
tenScoreOne = self.netScoreOne(tenVggOne)
tenScoreTwo = self.netScoreTwo(tenVggTwo)
tenScoreThr = self.netScoreThr(tenVggThr)
tenScoreFou = self.netScoreFou(tenVggFou)
tenScoreFiv = self.netScoreFiv(tenVggFiv)
tenScoreOne = torch.nn.functional.interpolate(input=tenScoreOne, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False)
tenScoreTwo = torch.nn.functional.interpolate(input=tenScoreTwo, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False)
tenScoreThr = torch.nn.functional.interpolate(input=tenScoreThr, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False)
tenScoreFou = torch.nn.functional.interpolate(input=tenScoreFou, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False)
tenScoreFiv = torch.nn.functional.interpolate(input=tenScoreFiv, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False)
return self.netCombine(torch.cat([ tenScoreOne, tenScoreTwo, tenScoreThr, tenScoreFou, tenScoreFiv ], 1))
# end
# end
netNetwork = None
##########################################################
def estimate(tenInput):
global netNetwork
if netNetwork is None:
netNetwork = Network().cuda().train(False)
# end
intWidth = tenInput.shape[2]
intHeight = tenInput.shape[1]
assert(intWidth == 480) # remember that there is no guarantee for correctness, comment this line out if you acknowledge this and want to continue
assert(intHeight == 320) # remember that there is no guarantee for correctness, comment this line out if you acknowledge this and want to continue
return netNetwork(tenInput.cuda().view(1, 3, intHeight, intWidth))[0, :, :, :].cpu()
# end
##########################################################
if __name__ == '__main__':
tenInput = torch.FloatTensor(numpy.ascontiguousarray(numpy.array(PIL.Image.open(args_strIn))[:, :, ::-1].transpose(2, 0, 1).astype(numpy.float32) * (1.0 / 255.0)))
tenOutput = estimate(tenInput)
PIL.Image.fromarray((tenOutput.clip(0.0, 1.0).numpy(force=True).transpose(1, 2, 0)[:, :, 0] * 255.0).astype(numpy.uint8)).save(args_strOut)
# end