File size: 7,951 Bytes
1cd3e6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchsummary import summary
from torch.utils.data import TensorDataset, DataLoader

class recon_encoder(nn.Module):

    def __init__(self, latent_size, nconv=16, pool=4, drop=0.05):
        super(recon_encoder, self).__init__()


        self.encoder = nn.Sequential( # Appears sequential has similar functionality as TF avoiding need for separate model definition and activ
          nn.Conv2d(in_channels=1, out_channels=nconv, kernel_size=3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv, nconv, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          nn.Conv2d(nconv, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),          
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          nn.Conv2d(nconv*2, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),     
          nn.Dropout(drop),     
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          #nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),     
          #nn.Dropout(drop),     
          #nn.ReLU(),
          #nn.MaxPool2d((pool,pool)),
        )


        self.bottleneck = nn.Sequential(
          # FC layer at bottleneck -- dropout might not make sense here
          nn.Flatten(),
          nn.Linear(1024, latent_size),
          #nn.Dropout(drop),
          nn.ReLU(),
#          nn.Linear(latent_size, 1024),
#          #nn.Dropout(drop),
#          nn.ReLU(),
#          nn.Unflatten(1,(64,4,4))# 0 is batch dimension
          )


        self.decoder1 = nn.Sequential(

          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*4, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),
            
          #nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*2, 1, 3, stride=1, padding=(1,1)), #Output conv layer has 2 for mu and sigma
          nn.Sigmoid() #Amplitude mode
          )
    

    def forward(self,x):
        with torch.cuda.amp.autocast():
            x1 = self.encoder(x)
            x1 = self.bottleneck(x1)
            #print(x1.shape)
            return x1


    #Helper function to calculate size of flattened array from conv layer shapes    
    def calc_fc_shape(self):
        x0 = torch.zeros([256,256]).unsqueeze(0)
        x0 = self.encoder(x0)

        self.conv_bock_output_shape = x0.shape
        #print ("Output of conv block shape is", self.conv_bock_output_shape)
        self.flattened_size = x0.flatten().shape[0]
        #print ("Flattened layer size is", self.flattened_size)
        return self.flattened_size

class recon_model(nn.Module):

    def __init__(self, latent_size, nconv=16, pool=4, drop=0.05):
        super(recon_model, self).__init__()


        self.encoder = nn.Sequential( # Appears sequential has similar functionality as TF avoiding need for separate model definition and activ
          nn.Conv2d(in_channels=1, out_channels=nconv, kernel_size=3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv, nconv, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          nn.Conv2d(nconv, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),          
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          nn.Conv2d(nconv*2, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),     
          nn.Dropout(drop),     
          nn.ReLU(),
          nn.MaxPool2d((pool,pool)),

          #nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),     
          #nn.Dropout(drop),     
          #nn.ReLU(),
          #nn.MaxPool2d((pool,pool)),
        )


        self.bottleneck = nn.Sequential(
          # FC layer at bottleneck -- dropout might not make sense here
          nn.Flatten(),
          nn.Linear(1024, latent_size),
          #nn.Dropout(drop),
          nn.ReLU(),
          nn.Linear(latent_size, 1024),
          #nn.Dropout(drop),
          nn.ReLU(),
          nn.Unflatten(1,(64,4,4))# 0 is batch dimension
          )


        self.decoder1 = nn.Sequential(

          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*4, nconv*4, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*4, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          nn.Dropout(drop),
          nn.ReLU(),
          nn.Upsample(scale_factor=pool, mode='bilinear'),
            
          #nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Conv2d(nconv*2, nconv*2, 3, stride=1, padding=(1,1)),
          #nn.Dropout(drop),
          #nn.ReLU(),
          #nn.Upsample(scale_factor=pool, mode='bilinear'),

          nn.Conv2d(nconv*2, 1, 3, stride=1, padding=(1,1)), #Output conv layer has 2 for mu and sigma
          nn.Sigmoid() #Amplitude mode
          )
    

    def forward(self,x):
        with torch.cuda.amp.autocast():
            x1 = self.encoder(x)
            x1 = self.bottleneck(x1)
            #print(x1.shape)
            return self.decoder1(x1)


    #Helper function to calculate size of flattened array from conv layer shapes    
    def calc_fc_shape(self):
        x0 = torch.zeros([256,256]).unsqueeze(0)
        x0 = self.encoder(x0)

        self.conv_bock_output_shape = x0.shape
        #print ("Output of conv block shape is", self.conv_bock_output_shape)
        self.flattened_size = x0.flatten().shape[0]
        #print ("Flattened layer size is", self.flattened_size)
        return self.flattened_size