File size: 49,162 Bytes
d9f82df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
"""
This is an almost carbon copy of gaussian_diffusion.py from OpenAI's ImprovedDiffusion repo, which itself:

This code started out as a PyTorch port of Ho et al's diffusion models:
https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/diffusion_utils_2.py

Docstrings have been added, as well as DDIM sampling and a new collection of beta schedules.
"""

import enum
import math

import numpy as np
import torch
import torch as th
from tqdm import tqdm


def normal_kl(mean1, logvar1, mean2, logvar2):
    """
    Compute the KL divergence between two gaussians.

    Shapes are automatically broadcasted, so batches can be compared to
    scalars, among other use cases.
    """
    tensor = None
    for obj in (mean1, logvar1, mean2, logvar2):
        if isinstance(obj, th.Tensor):
            tensor = obj
            break
    assert tensor is not None, "at least one argument must be a Tensor"

    # Force variances to be Tensors. Broadcasting helps convert scalars to
    # Tensors, but it does not work for th.exp().
    logvar1, logvar2 = [
        x if isinstance(x, th.Tensor) else th.tensor(x).to(tensor)
        for x in (logvar1, logvar2)
    ]

    return 0.5 * (
        -1.0
        + logvar2
        - logvar1
        + th.exp(logvar1 - logvar2)
        + ((mean1 - mean2) ** 2) * th.exp(-logvar2)
    )


def approx_standard_normal_cdf(x):
    """
    A fast approximation of the cumulative distribution function of the
    standard normal.
    """
    return 0.5 * (1.0 + th.tanh(np.sqrt(2.0 / np.pi) * (x + 0.044715 * th.pow(x, 3))))


def discretized_gaussian_log_likelihood(x, *, means, log_scales):
    """
    Compute the log-likelihood of a Gaussian distribution discretizing to a
    given image.

    :param x: the target images. It is assumed that this was uint8 values,
              rescaled to the range [-1, 1].
    :param means: the Gaussian mean Tensor.
    :param log_scales: the Gaussian log stddev Tensor.
    :return: a tensor like x of log probabilities (in nats).
    """
    assert x.shape == means.shape == log_scales.shape
    centered_x = x - means
    inv_stdv = th.exp(-log_scales)
    plus_in = inv_stdv * (centered_x + 1.0 / 255.0)
    cdf_plus = approx_standard_normal_cdf(plus_in)
    min_in = inv_stdv * (centered_x - 1.0 / 255.0)
    cdf_min = approx_standard_normal_cdf(min_in)
    log_cdf_plus = th.log(cdf_plus.clamp(min=1e-12))
    log_one_minus_cdf_min = th.log((1.0 - cdf_min).clamp(min=1e-12))
    cdf_delta = cdf_plus - cdf_min
    log_probs = th.where(
        x < -0.999,
        log_cdf_plus,
        th.where(x > 0.999, log_one_minus_cdf_min, th.log(cdf_delta.clamp(min=1e-12))),
    )
    assert log_probs.shape == x.shape
    return log_probs


def mean_flat(tensor):
    """
    Take the mean over all non-batch dimensions.
    """
    return tensor.mean(dim=list(range(1, len(tensor.shape))))


def get_named_beta_schedule(schedule_name, num_diffusion_timesteps):
    """
    Get a pre-defined beta schedule for the given name.

    The beta schedule library consists of beta schedules which remain similar
    in the limit of num_diffusion_timesteps.
    Beta schedules may be added, but should not be removed or changed once
    they are committed to maintain backwards compatibility.
    """
    if schedule_name == "linear":
        # Linear schedule from Ho et al, extended to work for any number of
        # diffusion steps.
        scale = 1000 / num_diffusion_timesteps
        beta_start = scale * 0.0001
        beta_end = scale * 0.02
        return np.linspace(
            beta_start, beta_end, num_diffusion_timesteps, dtype=np.float64
        )
    elif schedule_name == "cosine":
        return betas_for_alpha_bar(
            num_diffusion_timesteps,
            lambda t: math.cos((t + 0.008) / 1.008 * math.pi / 2) ** 2,
        )
    else:
        raise NotImplementedError(f"unknown beta schedule: {schedule_name}")


def betas_for_alpha_bar(num_diffusion_timesteps, alpha_bar, max_beta=0.999):
    """
    Create a beta schedule that discretizes the given alpha_t_bar function,
    which defines the cumulative product of (1-beta) over time from t = [0,1].

    :param num_diffusion_timesteps: the number of betas to produce.
    :param alpha_bar: a lambda that takes an argument t from 0 to 1 and
                      produces the cumulative product of (1-beta) up to that
                      part of the diffusion process.
    :param max_beta: the maximum beta to use; use values lower than 1 to
                     prevent singularities.
    """
    betas = []
    for i in range(num_diffusion_timesteps):
        t1 = i / num_diffusion_timesteps
        t2 = (i + 1) / num_diffusion_timesteps
        betas.append(min(1 - alpha_bar(t2) / alpha_bar(t1), max_beta))
    return np.array(betas)


class ModelMeanType(enum.Enum):
    """
    Which type of output the model predicts.
    """

    PREVIOUS_X = 'previous_x'  # the model predicts x_{t-1}
    START_X = 'start_x'  # the model predicts x_0
    EPSILON = 'epsilon'  # the model predicts epsilon


class ModelVarType(enum.Enum):
    """
    What is used as the model's output variance.

    The LEARNED_RANGE option has been added to allow the model to predict
    values between FIXED_SMALL and FIXED_LARGE, making its job easier.
    """

    LEARNED = 'learned'
    FIXED_SMALL = 'fixed_small'
    FIXED_LARGE = 'fixed_large'
    LEARNED_RANGE = 'learned_range'


class LossType(enum.Enum):
    MSE = 'mse'  # use raw MSE loss (and KL when learning variances)
    RESCALED_MSE = 'rescaled_mse'  # use raw MSE loss (with RESCALED_KL when learning variances)
    KL = 'kl'  # use the variational lower-bound
    RESCALED_KL = 'rescaled_kl'  # like KL, but rescale to estimate the full VLB

    def is_vb(self):
        return self == LossType.KL or self == LossType.RESCALED_KL


class GaussianDiffusion:
    """
    Utilities for training and sampling diffusion models.

    Ported directly from here, and then adapted over time to further experimentation.
    https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/diffusion_utils_2.py#L42

    :param betas: a 1-D numpy array of betas for each diffusion timestep,
                  starting at T and going to 1.
    :param model_mean_type: a ModelMeanType determining what the model outputs.
    :param model_var_type: a ModelVarType determining how variance is output.
    :param loss_type: a LossType determining the loss function to use.
    :param rescale_timesteps: if True, pass floating point timesteps into the
                              model so that they are always scaled like in the
                              original paper (0 to 1000).
    """

    def __init__(
        self,
        *,
        betas,
        model_mean_type,
        model_var_type,
        loss_type,
        rescale_timesteps=False,
        conditioning_free=False,
        conditioning_free_k=1,
        ramp_conditioning_free=True,
    ):
        self.model_mean_type = ModelMeanType(model_mean_type)
        self.model_var_type = ModelVarType(model_var_type)
        self.loss_type = LossType(loss_type)
        self.rescale_timesteps = rescale_timesteps
        self.conditioning_free = conditioning_free
        self.conditioning_free_k = conditioning_free_k
        self.ramp_conditioning_free = ramp_conditioning_free

        # Use float64 for accuracy.
        betas = np.array(betas, dtype=np.float64)
        self.betas = betas
        assert len(betas.shape) == 1, "betas must be 1-D"
        assert (betas > 0).all() and (betas <= 1).all()

        self.num_timesteps = int(betas.shape[0])

        alphas = 1.0 - betas
        self.alphas_cumprod = np.cumprod(alphas, axis=0)
        self.alphas_cumprod_prev = np.append(1.0, self.alphas_cumprod[:-1])
        self.alphas_cumprod_next = np.append(self.alphas_cumprod[1:], 0.0)
        assert self.alphas_cumprod_prev.shape == (self.num_timesteps,)

        # calculations for diffusion q(x_t | x_{t-1}) and others
        self.sqrt_alphas_cumprod = np.sqrt(self.alphas_cumprod)
        self.sqrt_one_minus_alphas_cumprod = np.sqrt(1.0 - self.alphas_cumprod)
        self.log_one_minus_alphas_cumprod = np.log(1.0 - self.alphas_cumprod)
        self.sqrt_recip_alphas_cumprod = np.sqrt(1.0 / self.alphas_cumprod)
        self.sqrt_recipm1_alphas_cumprod = np.sqrt(1.0 / self.alphas_cumprod - 1)

        # calculations for posterior q(x_{t-1} | x_t, x_0)
        self.posterior_variance = (
            betas * (1.0 - self.alphas_cumprod_prev) / (1.0 - self.alphas_cumprod)
        )
        # log calculation clipped because the posterior variance is 0 at the
        # beginning of the diffusion chain.
        self.posterior_log_variance_clipped = np.log(
            np.append(self.posterior_variance[1], self.posterior_variance[1:])
        )
        self.posterior_mean_coef1 = (
            betas * np.sqrt(self.alphas_cumprod_prev) / (1.0 - self.alphas_cumprod)
        )
        self.posterior_mean_coef2 = (
            (1.0 - self.alphas_cumprod_prev)
            * np.sqrt(alphas)
            / (1.0 - self.alphas_cumprod)
        )

    def q_mean_variance(self, x_start, t):
        """
        Get the distribution q(x_t | x_0).

        :param x_start: the [N x C x ...] tensor of noiseless inputs.
        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
        """
        mean = (
            _extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start
        )
        variance = _extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
        log_variance = _extract_into_tensor(
            self.log_one_minus_alphas_cumprod, t, x_start.shape
        )
        return mean, variance, log_variance

    def q_sample(self, x_start, t, noise=None):
        """
        Diffuse the data for a given number of diffusion steps.

        In other words, sample from q(x_t | x_0).

        :param x_start: the initial data batch.
        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
        :param noise: if specified, the split-out normal noise.
        :return: A noisy version of x_start.
        """
        if noise is None:
            noise = th.randn_like(x_start)
        assert noise.shape == x_start.shape
        return (
            _extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start
            + _extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape)
            * noise
        )

    def q_posterior_mean_variance(self, x_start, x_t, t):
        """
        Compute the mean and variance of the diffusion posterior:

            q(x_{t-1} | x_t, x_0)

        """
        assert x_start.shape == x_t.shape
        posterior_mean = (
            _extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start
            + _extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
        )
        posterior_variance = _extract_into_tensor(self.posterior_variance, t, x_t.shape)
        posterior_log_variance_clipped = _extract_into_tensor(
            self.posterior_log_variance_clipped, t, x_t.shape
        )
        assert (
            posterior_mean.shape[0]
            == posterior_variance.shape[0]
            == posterior_log_variance_clipped.shape[0]
            == x_start.shape[0]
        )
        return posterior_mean, posterior_variance, posterior_log_variance_clipped

    def p_mean_variance(
        self, model, x, t, clip_denoised=True, denoised_fn=None, model_kwargs=None
    ):
        """
        Apply the model to get p(x_{t-1} | x_t), as well as a prediction of
        the initial x, x_0.

        :param model: the model, which takes a signal and a batch of timesteps
                      as input.
        :param x: the [N x C x ...] tensor at time t.
        :param t: a 1-D Tensor of timesteps.
        :param clip_denoised: if True, clip the denoised signal into [-1, 1].
        :param denoised_fn: if not None, a function which applies to the
            x_start prediction before it is used to sample. Applies before
            clip_denoised.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.
        :return: a dict with the following keys:
                 - 'mean': the model mean output.
                 - 'variance': the model variance output.
                 - 'log_variance': the log of 'variance'.
                 - 'pred_xstart': the prediction for x_0.
        """
        if model_kwargs is None:
            model_kwargs = {}

        B, C = x.shape[:2]
        assert t.shape == (B,)
        model_output = model(x, self._scale_timesteps(t), **model_kwargs)
        if self.conditioning_free:
            model_output_no_conditioning = model(x, self._scale_timesteps(t), conditioning_free=True, **model_kwargs)

        if self.model_var_type in [ModelVarType.LEARNED, ModelVarType.LEARNED_RANGE]:
            assert model_output.shape == (B, C * 2, *x.shape[2:])
            model_output, model_var_values = th.split(model_output, C, dim=1)
            if self.conditioning_free:
                model_output_no_conditioning, _ = th.split(model_output_no_conditioning, C, dim=1)
            if self.model_var_type == ModelVarType.LEARNED:
                model_log_variance = model_var_values
                model_variance = th.exp(model_log_variance)
            else:
                min_log = _extract_into_tensor(
                    self.posterior_log_variance_clipped, t, x.shape
                )
                max_log = _extract_into_tensor(np.log(self.betas), t, x.shape)
                # The model_var_values is [-1, 1] for [min_var, max_var].
                frac = (model_var_values + 1) / 2
                model_log_variance = frac * max_log + (1 - frac) * min_log
                model_variance = th.exp(model_log_variance)
        else:
            model_variance, model_log_variance = {
                # for fixedlarge, we set the initial (log-)variance like so
                # to get a better decoder log likelihood.
                ModelVarType.FIXED_LARGE: (
                    np.append(self.posterior_variance[1], self.betas[1:]),
                    np.log(np.append(self.posterior_variance[1], self.betas[1:])),
                ),
                ModelVarType.FIXED_SMALL: (
                    self.posterior_variance,
                    self.posterior_log_variance_clipped,
                ),
            }[self.model_var_type]
            model_variance = _extract_into_tensor(model_variance, t, x.shape)
            model_log_variance = _extract_into_tensor(model_log_variance, t, x.shape)

        if self.conditioning_free:
            if self.ramp_conditioning_free:
                assert t.shape[0] == 1  # This should only be used in inference.
                cfk = self.conditioning_free_k * (1 - self._scale_timesteps(t)[0].item() / self.num_timesteps)
            else:
                cfk = self.conditioning_free_k
            model_output = (1 + cfk) * model_output - cfk * model_output_no_conditioning

        def process_xstart(x):
            if denoised_fn is not None:
                x = denoised_fn(x)
            if clip_denoised:
                return x.clamp(-1, 1)
            return x

        if self.model_mean_type == ModelMeanType.PREVIOUS_X:
            pred_xstart = process_xstart(
                self._predict_xstart_from_xprev(x_t=x, t=t, xprev=model_output)
            )
            model_mean = model_output
        elif self.model_mean_type in [ModelMeanType.START_X, ModelMeanType.EPSILON]:
            if self.model_mean_type == ModelMeanType.START_X:
                pred_xstart = process_xstart(model_output)
            else:
                pred_xstart = process_xstart(
                    self._predict_xstart_from_eps(x_t=x, t=t, eps=model_output)
                )
            model_mean, _, _ = self.q_posterior_mean_variance(
                x_start=pred_xstart, x_t=x, t=t
            )
        else:
            raise NotImplementedError(self.model_mean_type)

        assert (
            model_mean.shape == model_log_variance.shape == pred_xstart.shape == x.shape
        )
        return {
            "mean": model_mean,
            "variance": model_variance,
            "log_variance": model_log_variance,
            "pred_xstart": pred_xstart,
        }

    def _predict_xstart_from_eps(self, x_t, t, eps):
        assert x_t.shape == eps.shape
        return (
            _extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t
            - _extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * eps
        )

    def _predict_xstart_from_xprev(self, x_t, t, xprev):
        assert x_t.shape == xprev.shape
        return (  # (xprev - coef2*x_t) / coef1
            _extract_into_tensor(1.0 / self.posterior_mean_coef1, t, x_t.shape) * xprev
            - _extract_into_tensor(
                self.posterior_mean_coef2 / self.posterior_mean_coef1, t, x_t.shape
            )
            * x_t
        )

    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
        return (
            _extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t
            - pred_xstart
        ) / _extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)

    def _scale_timesteps(self, t):
        if self.rescale_timesteps:
            return t.float() * (1000.0 / self.num_timesteps)
        return t

    def condition_mean(self, cond_fn, p_mean_var, x, t, model_kwargs=None):
        """
        Compute the mean for the previous step, given a function cond_fn that
        computes the gradient of a conditional log probability with respect to
        x. In particular, cond_fn computes grad(log(p(y|x))), and we want to
        condition on y.

        This uses the conditioning strategy from Sohl-Dickstein et al. (2015).
        """
        gradient = cond_fn(x, self._scale_timesteps(t), **model_kwargs)
        new_mean = (
            p_mean_var["mean"].float() + p_mean_var["variance"] * gradient.float()
        )
        return new_mean

    def condition_score(self, cond_fn, p_mean_var, x, t, model_kwargs=None):
        """
        Compute what the p_mean_variance output would have been, should the
        model's score function be conditioned by cond_fn.

        See condition_mean() for details on cond_fn.

        Unlike condition_mean(), this instead uses the conditioning strategy
        from Song et al (2020).
        """
        alpha_bar = _extract_into_tensor(self.alphas_cumprod, t, x.shape)

        eps = self._predict_eps_from_xstart(x, t, p_mean_var["pred_xstart"])
        eps = eps - (1 - alpha_bar).sqrt() * cond_fn(
            x, self._scale_timesteps(t), **model_kwargs
        )

        out = p_mean_var.copy()
        out["pred_xstart"] = self._predict_xstart_from_eps(x, t, eps)
        out["mean"], _, _ = self.q_posterior_mean_variance(
            x_start=out["pred_xstart"], x_t=x, t=t
        )
        return out

    def p_sample(
        self,
        model,
        x,
        t,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
    ):
        """
        Sample x_{t-1} from the model at the given timestep.

        :param model: the model to sample from.
        :param x: the current tensor at x_{t-1}.
        :param t: the value of t, starting at 0 for the first diffusion step.
        :param clip_denoised: if True, clip the x_start prediction to [-1, 1].
        :param denoised_fn: if not None, a function which applies to the
            x_start prediction before it is used to sample.
        :param cond_fn: if not None, this is a gradient function that acts
                        similarly to the model.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.
        :return: a dict containing the following keys:
                 - 'sample': a random sample from the model.
                 - 'pred_xstart': a prediction of x_0.
        """
        out = self.p_mean_variance(
            model,
            x,
            t,
            clip_denoised=clip_denoised,
            denoised_fn=denoised_fn,
            model_kwargs=model_kwargs,
        )
        noise = th.randn_like(x)
        nonzero_mask = (
            (t != 0).float().view(-1, *([1] * (len(x.shape) - 1)))
        )  # no noise when t == 0
        if cond_fn is not None:
            out["mean"] = self.condition_mean(
                cond_fn, out, x, t, model_kwargs=model_kwargs
            )
        sample = out["mean"] + nonzero_mask * th.exp(0.5 * out["log_variance"]) * noise
        return {"sample": sample, "pred_xstart": out["pred_xstart"]}

    def p_sample_loop(
        self,
        model,
        shape,
        noise=None,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
        device=None,
        progress=False,
    ):
        """
        Generate samples from the model.

        :param model: the model module.
        :param shape: the shape of the samples, (N, C, H, W).
        :param noise: if specified, the noise from the encoder to sample.
                      Should be of the same shape as `shape`.
        :param clip_denoised: if True, clip x_start predictions to [-1, 1].
        :param denoised_fn: if not None, a function which applies to the
            x_start prediction before it is used to sample.
        :param cond_fn: if not None, this is a gradient function that acts
                        similarly to the model.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.
        :param device: if specified, the device to create the samples on.
                       If not specified, use a model parameter's device.
        :param progress: if True, show a tqdm progress bar.
        :return: a non-differentiable batch of samples.
        """
        final = None
        for sample in self.p_sample_loop_progressive(
            model,
            shape,
            noise=noise,
            clip_denoised=clip_denoised,
            denoised_fn=denoised_fn,
            cond_fn=cond_fn,
            model_kwargs=model_kwargs,
            device=device,
            progress=progress,
        ):
            final = sample
        return final["sample"]

    def p_sample_loop_progressive(
        self,
        model,
        shape,
        noise=None,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
        device=None,
        progress=False,
    ):
        """
        Generate samples from the model and yield intermediate samples from
        each timestep of diffusion.

        Arguments are the same as p_sample_loop().
        Returns a generator over dicts, where each dict is the return value of
        p_sample().
        """
        if device is None:
            device = next(model.parameters()).device
        assert isinstance(shape, (tuple, list))
        if noise is not None:
            img = noise
        else:
            img = th.randn(*shape, device=device)
        indices = list(range(self.num_timesteps))[::-1]

        for i in tqdm(indices, disable=not progress):
            t = th.tensor([i] * shape[0], device=device)
            with th.no_grad():
                out = self.p_sample(
                    model,
                    img,
                    t,
                    clip_denoised=clip_denoised,
                    denoised_fn=denoised_fn,
                    cond_fn=cond_fn,
                    model_kwargs=model_kwargs,
                )
                yield out
                img = out["sample"]

    def ddim_sample(
        self,
        model,
        x,
        t,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
        eta=0.0,
    ):
        """
        Sample x_{t-1} from the model using DDIM.

        Same usage as p_sample().
        """
        out = self.p_mean_variance(
            model,
            x,
            t,
            clip_denoised=clip_denoised,
            denoised_fn=denoised_fn,
            model_kwargs=model_kwargs,
        )
        if cond_fn is not None:
            out = self.condition_score(cond_fn, out, x, t, model_kwargs=model_kwargs)

        # Usually our model outputs epsilon, but we re-derive it
        # in case we used x_start or x_prev prediction.
        eps = self._predict_eps_from_xstart(x, t, out["pred_xstart"])

        alpha_bar = _extract_into_tensor(self.alphas_cumprod, t, x.shape)
        alpha_bar_prev = _extract_into_tensor(self.alphas_cumprod_prev, t, x.shape)
        sigma = (
            eta
            * th.sqrt((1 - alpha_bar_prev) / (1 - alpha_bar))
            * th.sqrt(1 - alpha_bar / alpha_bar_prev)
        )
        # Equation 12.
        noise = th.randn_like(x)
        mean_pred = (
            out["pred_xstart"] * th.sqrt(alpha_bar_prev)
            + th.sqrt(1 - alpha_bar_prev - sigma ** 2) * eps
        )
        nonzero_mask = (
            (t != 0).float().view(-1, *([1] * (len(x.shape) - 1)))
        )  # no noise when t == 0
        sample = mean_pred + nonzero_mask * sigma * noise
        return {"sample": sample, "pred_xstart": out["pred_xstart"]}

    def ddim_reverse_sample(
        self,
        model,
        x,
        t,
        clip_denoised=True,
        denoised_fn=None,
        model_kwargs=None,
        eta=0.0,
    ):
        """
        Sample x_{t+1} from the model using DDIM reverse ODE.
        """
        assert eta == 0.0, "Reverse ODE only for deterministic path"
        out = self.p_mean_variance(
            model,
            x,
            t,
            clip_denoised=clip_denoised,
            denoised_fn=denoised_fn,
            model_kwargs=model_kwargs,
        )
        # Usually our model outputs epsilon, but we re-derive it
        # in case we used x_start or x_prev prediction.
        eps = (
            _extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x.shape) * x
            - out["pred_xstart"]
        ) / _extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x.shape)
        alpha_bar_next = _extract_into_tensor(self.alphas_cumprod_next, t, x.shape)

        # Equation 12. reversed
        mean_pred = (
            out["pred_xstart"] * th.sqrt(alpha_bar_next)
            + th.sqrt(1 - alpha_bar_next) * eps
        )

        return {"sample": mean_pred, "pred_xstart": out["pred_xstart"]}

    def ddim_sample_loop(
        self,
        model,
        shape,
        noise=None,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
        device=None,
        progress=False,
        eta=0.0,
    ):
        """
        Generate samples from the model using DDIM.

        Same usage as p_sample_loop().
        """
        final = None
        for sample in self.ddim_sample_loop_progressive(
            model,
            shape,
            noise=noise,
            clip_denoised=clip_denoised,
            denoised_fn=denoised_fn,
            cond_fn=cond_fn,
            model_kwargs=model_kwargs,
            device=device,
            progress=progress,
            eta=eta,
        ):
            final = sample
        return final["sample"]

    def ddim_sample_loop_progressive(
        self,
        model,
        shape,
        noise=None,
        clip_denoised=True,
        denoised_fn=None,
        cond_fn=None,
        model_kwargs=None,
        device=None,
        progress=False,
        eta=0.0,
    ):
        """
        Use DDIM to sample from the model and yield intermediate samples from
        each timestep of DDIM.

        Same usage as p_sample_loop_progressive().
        """
        if device is None:
            device = next(model.parameters()).device
        assert isinstance(shape, (tuple, list))
        if noise is not None:
            img = noise
        else:
            img = th.randn(*shape, device=device)
        indices = list(range(self.num_timesteps))[::-1]

        if progress:
            # Lazy import so that we don't depend on tqdm.
            from tqdm.auto import tqdm

            indices = tqdm(indices, disable=not progress)

        for i in indices:
            t = th.tensor([i] * shape[0], device=device)
            with th.no_grad():
                out = self.ddim_sample(
                    model,
                    img,
                    t,
                    clip_denoised=clip_denoised,
                    denoised_fn=denoised_fn,
                    cond_fn=cond_fn,
                    model_kwargs=model_kwargs,
                    eta=eta,
                )
                yield out
                img = out["sample"]

    def _vb_terms_bpd(
        self, model, x_start, x_t, t, clip_denoised=True, model_kwargs=None
    ):
        """
        Get a term for the variational lower-bound.

        The resulting units are bits (rather than nats, as one might expect).
        This allows for comparison to other papers.

        :return: a dict with the following keys:
                 - 'output': a shape [N] tensor of NLLs or KLs.
                 - 'pred_xstart': the x_0 predictions.
        """
        true_mean, _, true_log_variance_clipped = self.q_posterior_mean_variance(
            x_start=x_start, x_t=x_t, t=t
        )
        out = self.p_mean_variance(
            model, x_t, t, clip_denoised=clip_denoised, model_kwargs=model_kwargs
        )
        kl = normal_kl(
            true_mean, true_log_variance_clipped, out["mean"], out["log_variance"]
        )
        kl = mean_flat(kl) / np.log(2.0)

        decoder_nll = -discretized_gaussian_log_likelihood(
            x_start, means=out["mean"], log_scales=0.5 * out["log_variance"]
        )
        assert decoder_nll.shape == x_start.shape
        decoder_nll = mean_flat(decoder_nll) / np.log(2.0)

        # At the first timestep return the decoder NLL,
        # otherwise return KL(q(x_{t-1}|x_t,x_0) || p(x_{t-1}|x_t))
        output = th.where((t == 0), decoder_nll, kl)
        return {"output": output, "pred_xstart": out["pred_xstart"]}

    def training_losses(self, model, x_start, t, model_kwargs=None, noise=None):
        """
        Compute training losses for a single timestep.

        :param model: the model to evaluate loss on.
        :param x_start: the [N x C x ...] tensor of inputs.
        :param t: a batch of timestep indices.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.
        :param noise: if specified, the specific Gaussian noise to try to remove.
        :return: a dict with the key "loss" containing a tensor of shape [N].
                 Some mean or variance settings may also have other keys.
        """
        if model_kwargs is None:
            model_kwargs = {}
        if noise is None:
            noise = th.randn_like(x_start)
        x_t = self.q_sample(x_start, t, noise=noise)

        terms = {}

        if self.loss_type == LossType.KL or self.loss_type == LossType.RESCALED_KL:
            # TODO: support multiple model outputs for this mode.
            terms["loss"] = self._vb_terms_bpd(
                model=model,
                x_start=x_start,
                x_t=x_t,
                t=t,
                clip_denoised=False,
                model_kwargs=model_kwargs,
            )["output"]
            if self.loss_type == LossType.RESCALED_KL:
                terms["loss"] *= self.num_timesteps
        elif self.loss_type == LossType.MSE or self.loss_type == LossType.RESCALED_MSE:
            model_outputs = model(x_t, self._scale_timesteps(t), **model_kwargs)
            if isinstance(model_outputs, tuple):
                model_output = model_outputs[0]
                terms['extra_outputs'] = model_outputs[1:]
            else:
                model_output = model_outputs

            if self.model_var_type in [
                ModelVarType.LEARNED,
                ModelVarType.LEARNED_RANGE,
            ]:
                B, C = x_t.shape[:2]
                assert model_output.shape == (B, C * 2, *x_t.shape[2:])
                model_output, model_var_values = th.split(model_output, C, dim=1)
                # Learn the variance using the variational bound, but don't let
                # it affect our mean prediction.
                frozen_out = th.cat([model_output.detach(), model_var_values], dim=1)
                terms["vb"] = self._vb_terms_bpd(
                    model=lambda *args, r=frozen_out: r,
                    x_start=x_start,
                    x_t=x_t,
                    t=t,
                    clip_denoised=False,
                )["output"]
                if self.loss_type == LossType.RESCALED_MSE:
                    # Divide by 1000 for equivalence with initial implementation.
                    # Without a factor of 1/1000, the VB term hurts the MSE term.
                    terms["vb"] *= self.num_timesteps / 1000.0

            if self.model_mean_type == ModelMeanType.PREVIOUS_X:
                target = self.q_posterior_mean_variance(
                    x_start=x_start, x_t=x_t, t=t
                )[0]
                x_start_pred = torch.zeros(x_start)  # Not supported.
            elif self.model_mean_type == ModelMeanType.START_X:
                target = x_start
                x_start_pred = model_output
            elif self.model_mean_type == ModelMeanType.EPSILON:
                target = noise
                x_start_pred = self._predict_xstart_from_eps(x_t, t, model_output)
            else:
                raise NotImplementedError(self.model_mean_type)
            assert model_output.shape == target.shape == x_start.shape
            terms["mse"] = mean_flat((target - model_output) ** 2)
            terms["x_start_predicted"] = x_start_pred
            if "vb" in terms:
                terms["loss"] = terms["mse"] + terms["vb"]
            else:
                terms["loss"] = terms["mse"]
        else:
            raise NotImplementedError(self.loss_type)

        return terms

    def autoregressive_training_losses(self, model, x_start, t, model_output_keys, gd_out_key, model_kwargs=None, noise=None):
        """
        Compute training losses for a single timestep.

        :param model: the model to evaluate loss on.
        :param x_start: the [N x C x ...] tensor of inputs.
        :param t: a batch of timestep indices.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.
        :param noise: if specified, the specific Gaussian noise to try to remove.
        :return: a dict with the key "loss" containing a tensor of shape [N].
                 Some mean or variance settings may also have other keys.
        """
        if model_kwargs is None:
            model_kwargs = {}
        if noise is None:
            noise = th.randn_like(x_start)
        x_t = self.q_sample(x_start, t, noise=noise)
        terms = {}
        if self.loss_type == LossType.KL or self.loss_type == LossType.RESCALED_KL:
            assert False  # not currently supported for this type of diffusion.
        elif self.loss_type == LossType.MSE or self.loss_type == LossType.RESCALED_MSE:
            model_outputs = model(x_t, x_start, self._scale_timesteps(t), **model_kwargs)
            terms.update({k: o for k, o in zip(model_output_keys, model_outputs)})
            model_output = terms[gd_out_key]
            if self.model_var_type in [
                ModelVarType.LEARNED,
                ModelVarType.LEARNED_RANGE,
            ]:
                B, C = x_t.shape[:2]
                assert model_output.shape == (B, C, 2, *x_t.shape[2:])
                model_output, model_var_values = model_output[:, :, 0], model_output[:, :, 1]
                # Learn the variance using the variational bound, but don't let
                # it affect our mean prediction.
                frozen_out = th.cat([model_output.detach(), model_var_values], dim=1)
                terms["vb"] = self._vb_terms_bpd(
                    model=lambda *args, r=frozen_out: r,
                    x_start=x_start,
                    x_t=x_t,
                    t=t,
                    clip_denoised=False,
                )["output"]
                if self.loss_type == LossType.RESCALED_MSE:
                    # Divide by 1000 for equivalence with initial implementation.
                    # Without a factor of 1/1000, the VB term hurts the MSE term.
                    terms["vb"] *= self.num_timesteps / 1000.0

            if self.model_mean_type == ModelMeanType.PREVIOUS_X:
                target = self.q_posterior_mean_variance(
                    x_start=x_start, x_t=x_t, t=t
                )[0]
                x_start_pred = torch.zeros(x_start)  # Not supported.
            elif self.model_mean_type == ModelMeanType.START_X:
                target = x_start
                x_start_pred = model_output
            elif self.model_mean_type == ModelMeanType.EPSILON:
                target = noise
                x_start_pred = self._predict_xstart_from_eps(x_t, t, model_output)
            else:
                raise NotImplementedError(self.model_mean_type)
            assert model_output.shape == target.shape == x_start.shape
            terms["mse"] = mean_flat((target - model_output) ** 2)
            terms["x_start_predicted"] = x_start_pred
            if "vb" in terms:
                terms["loss"] = terms["mse"] + terms["vb"]
            else:
                terms["loss"] = terms["mse"]
        else:
            raise NotImplementedError(self.loss_type)

        return terms

    def _prior_bpd(self, x_start):
        """
        Get the prior KL term for the variational lower-bound, measured in
        bits-per-dim.

        This term can't be optimized, as it only depends on the encoder.

        :param x_start: the [N x C x ...] tensor of inputs.
        :return: a batch of [N] KL values (in bits), one per batch element.
        """
        batch_size = x_start.shape[0]
        t = th.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
        kl_prior = normal_kl(
            mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0
        )
        return mean_flat(kl_prior) / np.log(2.0)

    def calc_bpd_loop(self, model, x_start, clip_denoised=True, model_kwargs=None):
        """
        Compute the entire variational lower-bound, measured in bits-per-dim,
        as well as other related quantities.

        :param model: the model to evaluate loss on.
        :param x_start: the [N x C x ...] tensor of inputs.
        :param clip_denoised: if True, clip denoised samples.
        :param model_kwargs: if not None, a dict of extra keyword arguments to
            pass to the model. This can be used for conditioning.

        :return: a dict containing the following keys:
                 - total_bpd: the total variational lower-bound, per batch element.
                 - prior_bpd: the prior term in the lower-bound.
                 - vb: an [N x T] tensor of terms in the lower-bound.
                 - xstart_mse: an [N x T] tensor of x_0 MSEs for each timestep.
                 - mse: an [N x T] tensor of epsilon MSEs for each timestep.
        """
        device = x_start.device
        batch_size = x_start.shape[0]

        vb = []
        xstart_mse = []
        mse = []
        for t in list(range(self.num_timesteps))[::-1]:
            t_batch = th.tensor([t] * batch_size, device=device)
            noise = th.randn_like(x_start)
            x_t = self.q_sample(x_start=x_start, t=t_batch, noise=noise)
            # Calculate VLB term at the current timestep
            with th.no_grad():
                out = self._vb_terms_bpd(
                    model,
                    x_start=x_start,
                    x_t=x_t,
                    t=t_batch,
                    clip_denoised=clip_denoised,
                    model_kwargs=model_kwargs,
                )
            vb.append(out["output"])
            xstart_mse.append(mean_flat((out["pred_xstart"] - x_start) ** 2))
            eps = self._predict_eps_from_xstart(x_t, t_batch, out["pred_xstart"])
            mse.append(mean_flat((eps - noise) ** 2))

        vb = th.stack(vb, dim=1)
        xstart_mse = th.stack(xstart_mse, dim=1)
        mse = th.stack(mse, dim=1)

        prior_bpd = self._prior_bpd(x_start)
        total_bpd = vb.sum(dim=1) + prior_bpd
        return {
            "total_bpd": total_bpd,
            "prior_bpd": prior_bpd,
            "vb": vb,
            "xstart_mse": xstart_mse,
            "mse": mse,
        }


def get_named_beta_schedule(schedule_name, num_diffusion_timesteps):
    """
    Get a pre-defined beta schedule for the given name.

    The beta schedule library consists of beta schedules which remain similar
    in the limit of num_diffusion_timesteps.
    Beta schedules may be added, but should not be removed or changed once
    they are committed to maintain backwards compatibility.
    """
    if schedule_name == "linear":
        # Linear schedule from Ho et al, extended to work for any number of
        # diffusion steps.
        scale = 1000 / num_diffusion_timesteps
        beta_start = scale * 0.0001
        beta_end = scale * 0.02
        return np.linspace(
            beta_start, beta_end, num_diffusion_timesteps, dtype=np.float64
        )
    elif schedule_name == "cosine":
        return betas_for_alpha_bar(
            num_diffusion_timesteps,
            lambda t: math.cos((t + 0.008) / 1.008 * math.pi / 2) ** 2,
        )
    else:
        raise NotImplementedError(f"unknown beta schedule: {schedule_name}")


class SpacedDiffusion(GaussianDiffusion):
    """
    A diffusion process which can skip steps in a base diffusion process.

    :param use_timesteps: a collection (sequence or set) of timesteps from the
                          original diffusion process to retain.
    :param kwargs: the kwargs to create the base diffusion process.
    """

    def __init__(self, use_timesteps, **kwargs):
        self.use_timesteps = set(use_timesteps)
        self.timestep_map = []
        self.original_num_steps = len(kwargs["betas"])

        base_diffusion = GaussianDiffusion(**kwargs)  # pylint: disable=missing-kwoa
        last_alpha_cumprod = 1.0
        new_betas = []
        for i, alpha_cumprod in enumerate(base_diffusion.alphas_cumprod):
            if i in self.use_timesteps:
                new_betas.append(1 - alpha_cumprod / last_alpha_cumprod)
                last_alpha_cumprod = alpha_cumprod
                self.timestep_map.append(i)
        kwargs["betas"] = np.array(new_betas)
        super().__init__(**kwargs)

    def p_mean_variance(
        self, model, *args, **kwargs
    ):  # pylint: disable=signature-differs
        return super().p_mean_variance(self._wrap_model(model), *args, **kwargs)

    def training_losses(
        self, model, *args, **kwargs
    ):  # pylint: disable=signature-differs
        return super().training_losses(self._wrap_model(model), *args, **kwargs)

    def autoregressive_training_losses(
        self, model, *args, **kwargs
    ):  # pylint: disable=signature-differs
        return super().autoregressive_training_losses(self._wrap_model(model, True), *args, **kwargs)

    def condition_mean(self, cond_fn, *args, **kwargs):
        return super().condition_mean(self._wrap_model(cond_fn), *args, **kwargs)

    def condition_score(self, cond_fn, *args, **kwargs):
        return super().condition_score(self._wrap_model(cond_fn), *args, **kwargs)

    def _wrap_model(self, model, autoregressive=False):
        if isinstance(model, _WrappedModel) or isinstance(model, _WrappedAutoregressiveModel):
            return model
        mod = _WrappedAutoregressiveModel if autoregressive else _WrappedModel
        return mod(
            model, self.timestep_map, self.rescale_timesteps, self.original_num_steps
        )

    def _scale_timesteps(self, t):
        # Scaling is done by the wrapped model.
        return t


def space_timesteps(num_timesteps, section_counts):
    """
    Create a list of timesteps to use from an original diffusion process,
    given the number of timesteps we want to take from equally-sized portions
    of the original process.

    For example, if there's 300 timesteps and the section counts are [10,15,20]
    then the first 100 timesteps are strided to be 10 timesteps, the second 100
    are strided to be 15 timesteps, and the final 100 are strided to be 20.

    If the stride is a string starting with "ddim", then the fixed striding
    from the DDIM paper is used, and only one section is allowed.

    :param num_timesteps: the number of diffusion steps in the original
                          process to divide up.
    :param section_counts: either a list of numbers, or a string containing
                           comma-separated numbers, indicating the step count
                           per section. As a special case, use "ddimN" where N
                           is a number of steps to use the striding from the
                           DDIM paper.
    :return: a set of diffusion steps from the original process to use.
    """
    if isinstance(section_counts, str):
        if section_counts.startswith("ddim"):
            desired_count = int(section_counts[len("ddim") :])
            for i in range(1, num_timesteps):
                if len(range(0, num_timesteps, i)) == desired_count:
                    return set(range(0, num_timesteps, i))
            raise ValueError(
                f"cannot create exactly {num_timesteps} steps with an integer stride"
            )
        section_counts = [int(x) for x in section_counts.split(",")]
    size_per = num_timesteps // len(section_counts)
    extra = num_timesteps % len(section_counts)
    start_idx = 0
    all_steps = []
    for i, section_count in enumerate(section_counts):
        size = size_per + (1 if i < extra else 0)
        if size < section_count:
            raise ValueError(
                f"cannot divide section of {size} steps into {section_count}"
            )
        if section_count <= 1:
            frac_stride = 1
        else:
            frac_stride = (size - 1) / (section_count - 1)
        cur_idx = 0.0
        taken_steps = []
        for _ in range(section_count):
            taken_steps.append(start_idx + round(cur_idx))
            cur_idx += frac_stride
        all_steps += taken_steps
        start_idx += size
    return set(all_steps)


class _WrappedModel:
    def __init__(self, model, timestep_map, rescale_timesteps, original_num_steps):
        self.model = model
        self.timestep_map = timestep_map
        self.rescale_timesteps = rescale_timesteps
        self.original_num_steps = original_num_steps

    def __call__(self, x, ts, **kwargs):
        map_tensor = th.tensor(self.timestep_map, device=ts.device, dtype=ts.dtype)
        new_ts = map_tensor[ts]
        if self.rescale_timesteps:
            new_ts = new_ts.float() * (1000.0 / self.original_num_steps)
        return self.model(x, new_ts, **kwargs)


class _WrappedAutoregressiveModel:
    def __init__(self, model, timestep_map, rescale_timesteps, original_num_steps):
        self.model = model
        self.timestep_map = timestep_map
        self.rescale_timesteps = rescale_timesteps
        self.original_num_steps = original_num_steps

    def __call__(self, x, x0, ts, **kwargs):
        map_tensor = th.tensor(self.timestep_map, device=ts.device, dtype=ts.dtype)
        new_ts = map_tensor[ts]
        if self.rescale_timesteps:
            new_ts = new_ts.float() * (1000.0 / self.original_num_steps)
        return self.model(x, x0, new_ts, **kwargs)

def _extract_into_tensor(arr, timesteps, broadcast_shape):
    """
    Extract values from a 1-D numpy array for a batch of indices.

    :param arr: the 1-D numpy array.
    :param timesteps: a tensor of indices into the array to extract.
    :param broadcast_shape: a larger shape of K dimensions with the batch
                            dimension equal to the length of timesteps.
    :return: a tensor of shape [batch_size, 1, ...] where the shape has K dims.
    """
    res = th.from_numpy(arr.astype(np.float32)).to(device=timesteps.device)[timesteps]
    while len(res.shape) < len(broadcast_shape):
        res = res[..., None]
    return res.expand(broadcast_shape)