-
Notifications
You must be signed in to change notification settings - Fork 0
/
model_structure.txt
389 lines (389 loc) · 14 KB
/
model_structure.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
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
UNetModel(
(time_embed): Sequential(
(0): Linear(in_features=128, out_features=512, bias=True)
(1): SiLU()
(2): Linear(in_features=512, out_features=512, bias=True)
)
(input_blocks): ModuleList(
(0): TimestepEmbedSequential(
(0): Conv2d(3, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(1-3): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=256, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
)
(4): TimestepEmbedSequential(
(0): Downsample(
(op): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
(5): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
)
(6-7): 2 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
)
(8): TimestepEmbedSequential(
(0): Downsample(
(op): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
(9-11): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
)
(12): TimestepEmbedSequential(
(0): Downsample(
(op): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
(13-15): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
)
)
(middle_block): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
(2): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Identity()
)
)
(output_blocks): ModuleList(
(0-2): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 512, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
)
(3): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 512, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): Upsample(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(4-6): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 512, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
)
(7): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 512, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
(2): Upsample(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(8-10): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 512, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
)
(11): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 384, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=512, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(384, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): AttentionBlock(
(norm): GroupNorm32(32, 256, eps=1e-05, affine=True)
(qkv): Conv1d(256, 768, kernel_size=(1,), stride=(1,))
(attention): QKVAttention()
(proj_out): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
)
(2): Upsample(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(12): TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 384, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(384, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=256, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1))
)
)
(13-15): 3 x TimestepEmbedSequential(
(0): ResBlock(
(in_layers): Sequential(
(0): GroupNorm32(32, 256, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(emb_layers): Sequential(
(0): SiLU()
(1): Linear(in_features=512, out_features=256, bias=True)
)
(out_layers): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Dropout(p=0.3, inplace=False)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
(skip_connection): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
)
)
)
(out): Sequential(
(0): GroupNorm32(32, 128, eps=1e-05, affine=True)
(1): SiLU()
(2): Conv2d(128, 6, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)