-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtrain.log
17417 lines (17201 loc) · 953 KB
/
train.log
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
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
22-09-02 11:12:13.066 : task: swinir_denoising_color_15
model: plain
gpu_ids: [0, 1, 2, 3]
dist: True
n_channels: 3
path:[
root: /root/paddlejob/workspace/output/denoising
pretrained_netG: None
pretrained_netE: None
task: /root/paddlejob/workspace/output/denoising/swinir_denoising_color_15
log: /root/paddlejob/workspace/output/denoising/swinir_denoising_color_15
options: /root/paddlejob/workspace/output/denoising/swinir_denoising_color_15/options
models: /root/paddlejob/workspace/output/denoising/swinir_denoising_color_15/models
images: /root/paddlejob/workspace/output/denoising/swinir_denoising_color_15/images
pretrained_optimizerG: None
]
datasets:[
train:[
name: train_dataset
dataset_type: dncnn
dataroot_H: trainsets/trainH
dataroot_L: None
H_size: 128
sigma: 15
sigma_test: 15
dataloader_shuffle: True
dataloader_num_workers: 8
dataloader_batch_size: 2
phase: train
scale: 1
n_channels: 3
]
test:[
name: test_dataset
dataset_type: dncnn
dataroot_H: testsets/CBSD68
dataroot_L: None
sigma: 15
sigma_test: 15
phase: test
scale: 1
n_channels: 3
]
]
netG:[
net_type: swinir
upscale: 1
in_chans: 3
img_size: 128
window_size: 8
img_range: 1.0
depths: [6, 6, 6, 6, 6, 6]
embed_dim: 180
num_heads: [6, 6, 6, 6, 6, 6]
mlp_ratio: 2
upsampler: None
resi_connection: 1conv
init_type: default
scale: 1
]
train:[
G_lossfn_type: charbonnier
G_lossfn_weight: 1.0
G_charbonnier_eps: 1e-09
E_decay: 0.999
G_optimizer_type: adam
G_optimizer_lr: 0.0002
G_optimizer_wd: 0
G_optimizer_clipgrad: None
G_optimizer_reuse: True
G_scheduler_type: MultiStepLR
G_scheduler_milestones: [800000, 1200000, 1400000, 1500000, 1600000]
G_scheduler_gamma: 0.5
G_regularizer_orthstep: None
G_regularizer_clipstep: None
G_param_strict: True
E_param_strict: True
manual_seed: 42
checkpoint_test: 2000
checkpoint_save: 2000
checkpoint_print: 400
F_feature_layer: 34
F_weights: 1.0
F_lossfn_type: l1
F_use_input_norm: True
F_use_range_norm: False
G_optimizer_betas: [0.9, 0.999]
G_scheduler_restart_weights: 1
]
opt_path: options/train_swinir_multi_card_32.json
is_train: True
merge_bn: False
merge_bn_startpoint: -1
scale: 1
find_unused_parameters: True
use_static_graph: False
num_gpu: 4
nranks: 4
22-09-02 11:12:13.100 : Number of train images: 8,694, iters: 4,347
22-09-02 11:12:14.245 :
Networks name: SwinIR
Params number: Tensor(shape=[1], dtype=int64, place=Place(gpu:0), stop_gradient=False,
[11504163])
Net structure:
SwinIR(
(conv_first): Conv2D(3, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed(
(norm): LayerNorm(normalized_shape=[180], epsilon=1e-05)
)
(patch_unembed): PatchUnEmbed()
(pos_drop): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(layers): LayerList(
(0): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): Identity()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
(1): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
(2): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
(3): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
(4): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
(5): RSTB(
(residual_group): BasicLayer(dim=180, input_resolution=(128, 128), depth=6
(blocks): LayerList(
(0): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(1): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(2): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(3): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(4): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=0, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
(5): SwinTransformerBlock(dim=180, input_resolution=(128, 128), num_heads=6, window_size=8, shift_size=4, mlp_ratio=2
(norm1): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(attn): WindowAttention(dim=180, window_size=(8, 8), num_heads=6
(qkv): Linear(in_features=180, out_features=540, dtype=float32)
(attn_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(proj): Linear(in_features=180, out_features=180, dtype=float32)
(proj_dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
(softmax): Softmax(axis=-1)
)
(drop_path): DropPath()
(norm2): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(mlp): Mlp(
(fc1): Linear(in_features=180, out_features=360, dtype=float32)
(fc2): Linear(in_features=360, out_features=180, dtype=float32)
(act): GELU(approximate=False)
(dropout): Dropout(p=0.0, axis=None, mode=upscale_in_train)
)
)
)
)
(conv): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(patch_embed): PatchEmbed()
(patch_unembed): PatchUnEmbed()
)
)
(norm): LayerNorm(normalized_shape=[180], epsilon=1e-05)
(conv_after_body): Conv2D(180, 180, kernel_size=[3, 3], padding=1, data_format=NCHW)
(conv_last): Conv2D(180, 3, kernel_size=[3, 3], padding=1, data_format=NCHW)
)
22-09-02 11:12:14.464 :
| mean | min | max | std || shape
| -0.002 | -0.941 | 1.199 | 0.274 | (180, 3, 3, 3) || conv_first.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || conv_first.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || patch_embed.norm.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || patch_embed.norm.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.norm1.bias
| -0.000 | -0.040 | 0.040 | 0.017 | (225, 6) || layers.0.residual_group.blocks.0.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.0.attn.relative_position_index
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.0.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.0.attn.qkv.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.0.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.norm2.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.0.mlp.fc1.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.0.mlp.fc1.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.0.mlp.fc2.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.0.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.0.residual_group.blocks.1.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.norm1.bias
| -0.001 | -0.040 | 0.040 | 0.018 | (225, 6) || layers.0.residual_group.blocks.1.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.1.attn.relative_position_index
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.1.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.1.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.1.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.1.mlp.fc1.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.1.mlp.fc1.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.1.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.1.mlp.fc2.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.norm1.bias
| 0.001 | -0.040 | 0.040 | 0.018 | (225, 6) || layers.0.residual_group.blocks.2.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.2.attn.relative_position_index
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.2.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.2.attn.qkv.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.2.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.norm2.bias
| 0.001 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.2.mlp.fc1.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.2.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.2.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.2.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.0.residual_group.blocks.3.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.norm1.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (225, 6) || layers.0.residual_group.blocks.3.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.3.attn.relative_position_index
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.3.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.3.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.3.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.3.mlp.fc1.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.3.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.3.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.3.mlp.fc2.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.norm1.bias
| 0.000 | -0.039 | 0.040 | 0.018 | (225, 6) || layers.0.residual_group.blocks.4.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.4.attn.relative_position_index
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.4.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.4.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.4.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.4.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.4.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.4.mlp.fc2.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.4.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.0.residual_group.blocks.5.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.norm1.bias
| -0.000 | -0.040 | 0.039 | 0.018 | (225, 6) || layers.0.residual_group.blocks.5.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.0.residual_group.blocks.5.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.0.residual_group.blocks.5.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.0.residual_group.blocks.5.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.0.residual_group.blocks.5.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.norm2.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.0.residual_group.blocks.5.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.0.residual_group.blocks.5.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.0.residual_group.blocks.5.mlp.fc2.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.0.residual_group.blocks.5.mlp.fc2.bias
| -0.000 | -0.155 | 0.158 | 0.035 | (180, 180, 3, 3) || layers.0.conv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.0.conv.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.norm1.bias
| -0.000 | -0.040 | 0.039 | 0.018 | (225, 6) || layers.1.residual_group.blocks.0.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.0.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.0.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.0.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.0.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.norm2.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.0.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.1.residual_group.blocks.0.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.1.residual_group.blocks.0.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.0.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.1.residual_group.blocks.1.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.norm1.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (225, 6) || layers.1.residual_group.blocks.1.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.1.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.1.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.1.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.1.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.norm2.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.1.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.1.residual_group.blocks.1.mlp.fc1.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.1.residual_group.blocks.1.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.1.mlp.fc2.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.norm1.bias
| -0.001 | -0.040 | 0.040 | 0.018 | (225, 6) || layers.1.residual_group.blocks.2.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.2.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.2.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.2.attn.qkv.bias
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.2.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.2.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.1.residual_group.blocks.2.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.1.residual_group.blocks.2.mlp.fc2.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.2.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.1.residual_group.blocks.3.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.norm1.bias
| 0.001 | -0.040 | 0.040 | 0.017 | (225, 6) || layers.1.residual_group.blocks.3.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.3.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.3.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.3.attn.qkv.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.3.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.3.mlp.fc1.weight
| -0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.1.residual_group.blocks.3.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.1.residual_group.blocks.3.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.3.mlp.fc2.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.norm1.bias
| 0.000 | -0.040 | 0.040 | 0.017 | (225, 6) || layers.1.residual_group.blocks.4.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.4.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.4.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.4.attn.qkv.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.4.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.norm2.bias
| -0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.4.mlp.fc1.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (360,) || layers.1.residual_group.blocks.4.mlp.fc1.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (360, 180) || layers.1.residual_group.blocks.4.mlp.fc2.weight
| 0.000 | -0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.4.mlp.fc2.bias
| -6.152 | -100.000 | -0.000 | 24.029 | (256, 64, 64) || layers.1.residual_group.blocks.5.attn_mask
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.5.norm1.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.5.norm1.bias
| 0.000 | -0.039 | 0.040 | 0.018 | (225, 6) || layers.1.residual_group.blocks.5.attn.relative_position_bias_table
| 112.000 | 0.000 | 224.000 | 48.713 | (64, 64) || layers.1.residual_group.blocks.5.attn.relative_position_index
| 0.000 | -0.040 | 0.040 | 0.018 | (180, 540) || layers.1.residual_group.blocks.5.attn.qkv.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (540,) || layers.1.residual_group.blocks.5.attn.qkv.bias
| -0.000 | -0.040 | 0.040 | 0.018 | (180, 180) || layers.1.residual_group.blocks.5.attn.proj.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.5.attn.proj.bias
| 1.000 | 1.000 | 1.000 | 0.000 | (180,) || layers.1.residual_group.blocks.5.norm2.weight
| 0.000 | 0.000 | 0.000 | 0.000 | (180,) || layers.1.residual_group.blocks.5.norm2.bias
| 0.000 | -0.105 | 0.105 | 0.061 | (180, 360) || layers.1.residual_group.blocks.5.mlp.fc1.weight