-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathHead Settings.txt
376 lines (364 loc) · 18.9 KB
/
Head Settings.txt
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
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
######################## Code for Head
class Head(nn.Module):
def __init__(self, nc, n, mid, ps=0.5):
super().__init__()
layers = [ AdaptiveConcatPool2d(), Flatten()] + \
bn_drop_lin(nc * 2, mid, True, ps / 2, Mish()) + \
bn_drop_lin(mid, n, True, ps)
self.fc = nn.Sequential(*layers)
self._init_weight()
def _init_weight(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
torch.nn.init.kaiming_normal_(m.weight)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1.0)
m.bias.data.zero_()
def forward(self, x):
return self.fc(x)
######################## settings to use for head in your code
# Head Settings:
# n =[168 , 11, 7]
# nc = i/p to the last layer
self.head1 = Head(nc,n[0], mid = 786 , ps =0.36)
self.head2 = Head(nc,n[1], mid = 512 , ps =0.64)
self.head3 = Head(nc,n[2], mid = 512 , ps =0.50)
######################## Model Summary
My_Seresnext_50(
(eff): Sequential(
(0): Sequential(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(pool): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)
)
(1): Sequential(
(0): SEResNeXtBottleneck(
(conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(256, 16, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(16, 256, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
(downsample): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): SEResNeXtBottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(256, 16, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(16, 256, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(2): SEResNeXtBottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(256, 16, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(16, 256, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
)
(2): Sequential(
(0): SEResNeXtBottleneck(
(conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(32, 512, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): SEResNeXtBottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(32, 512, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(2): SEResNeXtBottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(32, 512, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(3): SEResNeXtBottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(512, 32, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(32, 512, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
)
(3): Sequential(
(0): SEResNeXtBottleneck(
(conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
(downsample): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(2): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(3): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(4): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(5): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(1024, 64, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
)
(4): Sequential(
(0): SEResNeXtBottleneck(
(conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(2048, 128, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(128, 2048, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
(downsample): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): SEResNeXtBottleneck(
(conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(2048, 128, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(128, 2048, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
(2): SEResNeXtBottleneck(
(conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(se_module): SEModule(
(avg_pool): AdaptiveAvgPool2d(output_size=1)
(fc1): Conv2d(2048, 128, kernel_size=(1, 1), stride=(1, 1))
(relu): ReLU(inplace=True)
(fc2): Conv2d(128, 2048, kernel_size=(1, 1), stride=(1, 1))
(sigmoid): Sigmoid()
)
)
)
)
(head1): Head_1(
(fc): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(4096, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.18, inplace=False)
(4): Linear(in_features=4096, out_features=786, bias=True)
(5): Mish()
(6): BatchNorm1d(786, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.36, inplace=False)
(8): Linear(in_features=786, out_features=168, bias=True)
)
)
(head2): Head_1(
(fc): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(4096, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.32, inplace=False)
(4): Linear(in_features=4096, out_features=512, bias=True)
(5): Mish()
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.64, inplace=False)
(8): Linear(in_features=512, out_features=11, bias=True)
)
)
(head3): Head_1(
(fc): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(4096, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.25, inplace=False)
(4): Linear(in_features=4096, out_features=512, bias=True)
(5): Mish()
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.5, inplace=False)
(8): Linear(in_features=512, out_features=7, bias=True)
)
)
)