File size: 24,964 Bytes
3b7b011
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
import sys
import logging

logger = logging.getLogger(__name__)

now_dir = os.getcwd()
sys.path.append(os.path.join(now_dir))

import datetime

from lib.infer.infer_libs.train import utils

hps = utils.get_hparams()
os.environ["CUDA_VISIBLE_DEVICES"] = hps.gpus.replace("-", ",")
n_gpus = len(hps.gpus.split("-"))
from random import randint, shuffle

import torch
try:
    import intel_extension_for_pytorch as ipex # pylint: disable=import-error, unused-import
    if torch.xpu.is_available():
        from lib.infer.modules.ipex import ipex_init
        from lib.infer.modules.ipex.gradscaler import gradscaler_init
        from torch.xpu.amp import autocast
        GradScaler = gradscaler_init()
        ipex_init()
    else:
        from torch.cuda.amp import GradScaler, autocast
except Exception:
    from torch.cuda.amp import GradScaler, autocast

torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = False
from time import sleep
from time import time as ttime

import torch.distributed as dist
import torch.multiprocessing as mp

from torch.nn import functional as F
from torch.nn.parallel import DistributedDataParallel as DDP
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from lib.infer.infer_libs.infer_pack import commons
from lib.infer.infer_libs.train.data_utils import (
    DistributedBucketSampler,
    TextAudioCollate,
    TextAudioCollateMultiNSFsid,
    TextAudioLoader,
    TextAudioLoaderMultiNSFsid,
)

if hps.version == "v1":
    from lib.infer.infer_libs.infer_pack.models import MultiPeriodDiscriminator
    from lib.infer.infer_libs.infer_pack.models import SynthesizerTrnMs256NSFsid as RVC_Model_f0
    from lib.infer.infer_libs.infer_pack.models import (
        SynthesizerTrnMs256NSFsid_nono as RVC_Model_nof0,
    )
else:
    from lib.infer.infer_libs.infer_pack.models import (
        SynthesizerTrnMs768NSFsid as RVC_Model_f0,
        SynthesizerTrnMs768NSFsid_nono as RVC_Model_nof0,
        MultiPeriodDiscriminatorV2 as MultiPeriodDiscriminator,
    )

from lib.infer.infer_libs.train.losses import (
    discriminator_loss,
    feature_loss,
    generator_loss,
    kl_loss,
)
from lib.infer.infer_libs.train.mel_processing import mel_spectrogram_torch, spec_to_mel_torch
from lib.infer.infer_libs.train.process_ckpt import savee

global_step = 0
import csv

class EpochRecorder:
    def __init__(self):
        self.last_time = ttime()

    def record(self):
        now_time = ttime()
        elapsed_time = now_time - self.last_time
        self.last_time = now_time
        elapsed_time_str = str(datetime.timedelta(seconds=elapsed_time))
        current_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        return f"[{current_time}] | ({elapsed_time_str})"

def reset_stop_flag():
    with open("lib/csvdb/stop.csv", "w+", newline="") as STOPCSVwrite:
        csv_writer = csv.writer(STOPCSVwrite, delimiter=",")
        csv_writer.writerow(["False"])

def create_model(hps, model_f0, model_nof0):
    filter_length_adjusted = hps.data.filter_length // 2 + 1
    segment_size_adjusted = hps.train.segment_size // hps.data.hop_length
    is_half = hps.train.fp16_run
    sr = hps.sample_rate

    model = model_f0 if hps.if_f0 == 1 else model_nof0

    return model(
        filter_length_adjusted,
        segment_size_adjusted,
        **hps.model,
        is_half=is_half,
        sr=sr
    )

def move_model_to_cuda_if_available(model, rank):
    if torch.cuda.is_available():
        return model.cuda(rank)
    else:
        return model

def create_optimizer(model, hps):
    return torch.optim.AdamW(
        model.parameters(),
        hps.train.learning_rate,
        betas=hps.train.betas,
        eps=hps.train.eps,
    )

def create_ddp_model(model, rank):
    if torch.cuda.is_available():
        return DDP(model, device_ids=[rank])
    else:
        return DDP(model)

def create_dataset(hps, if_f0=True):
    return TextAudioLoaderMultiNSFsid(hps.data.training_files, hps.data) if if_f0 else TextAudioLoader(hps.data.training_files, hps.data)

def create_sampler(dataset, batch_size, n_gpus, rank):
    return DistributedBucketSampler(
            dataset,
            batch_size * n_gpus,
            # [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200,1400],  # 16s
            [100, 200, 300, 400, 500, 600, 700, 800, 900],  # 16s
            num_replicas=n_gpus,
            rank=rank,
            shuffle=True,
        )

def set_collate_fn(if_f0=True):
    return TextAudioCollateMultiNSFsid() if if_f0 else TextAudioCollate()


def main():
    n_gpus = torch.cuda.device_count()

    if torch.cuda.is_available() == False and torch.backends.mps.is_available() == True:
        n_gpus = 1
    if n_gpus < 1:
        # patch to unblock people without gpus. there is probably a better way.
        logger.warn("NO GPU DETECTED: falling back to CPU - this may take a while")
        n_gpus = 1
    os.environ["MASTER_ADDR"] = "localhost"
    os.environ["MASTER_PORT"] = str(randint(20000, 55555))
    children = []
    for i in range(n_gpus):
        subproc = mp.Process(
            target=run,
            args=(
                i,
                n_gpus,
                hps,
            ),
        )
        children.append(subproc)
        subproc.start()

    for i in range(n_gpus):
        children[i].join()


def run(rank, n_gpus, hps):
    global global_step
    if rank == 0:
        logger = utils.get_logger(hps.model_dir)
        logger.info(hps)
        # utils.check_git_hash(hps.model_dir)
        writer = SummaryWriter(log_dir=hps.model_dir)
        writer_eval = SummaryWriter(log_dir=os.path.join(hps.model_dir, "eval"))

    dist.init_process_group(
        backend="gloo", init_method="env://", world_size=n_gpus, rank=rank
    )
    torch.manual_seed(hps.train.seed)
    if torch.cuda.is_available():
        torch.cuda.set_device(rank)

    if hps.if_f0 == 1:
        train_dataset = TextAudioLoaderMultiNSFsid(hps.data.training_files, hps.data)
    else:
        train_dataset = TextAudioLoader(hps.data.training_files, hps.data)
    train_sampler = DistributedBucketSampler(
        train_dataset,
        hps.train.batch_size * n_gpus,
        # [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200,1400],  # 16s
        [100, 200, 300, 400, 500, 600, 700, 800, 900],  # 16s
        num_replicas=n_gpus,
        rank=rank,
        shuffle=True,
    )
    # It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
    # num_workers=8 -> num_workers=4
    if hps.if_f0 == 1:
        collate_fn = TextAudioCollateMultiNSFsid()
    else:
        collate_fn = TextAudioCollate()
    train_loader = DataLoader(
        train_dataset,
        num_workers=4,
        shuffle=False,
        pin_memory=True,
        collate_fn=collate_fn,
        batch_sampler=train_sampler,
        persistent_workers=True,
        prefetch_factor=8,
    )
    if hps.if_f0 == 1:
        net_g = RVC_Model_f0(
            hps.data.filter_length // 2 + 1,
            hps.train.segment_size // hps.data.hop_length,
            **hps.model,
            is_half=hps.train.fp16_run,
            sr=hps.sample_rate,
        )
    else:
        net_g = RVC_Model_nof0(
            hps.data.filter_length // 2 + 1,
            hps.train.segment_size // hps.data.hop_length,
            **hps.model,
            is_half=hps.train.fp16_run,
        )
    if torch.cuda.is_available():
        net_g = net_g.cuda(rank)
    net_d = MultiPeriodDiscriminator(hps.model.use_spectral_norm)
    if torch.cuda.is_available():
        net_d = net_d.cuda(rank)
    optim_g = torch.optim.AdamW(
        net_g.parameters(),
        hps.train.learning_rate,
        betas=hps.train.betas,
        eps=hps.train.eps,
    )
    optim_d = torch.optim.AdamW(
        net_d.parameters(),
        hps.train.learning_rate,
        betas=hps.train.betas,
        eps=hps.train.eps,
    )
    # net_g = DDP(net_g, device_ids=[rank], find_unused_parameters=True)
    # net_d = DDP(net_d, device_ids=[rank], find_unused_parameters=True)
    if hasattr(torch, "xpu") and torch.xpu.is_available():
        pass
    elif torch.cuda.is_available():
        net_g = DDP(net_g, device_ids=[rank])
        net_d = DDP(net_d, device_ids=[rank])
    else:
        net_g = DDP(net_g)
        net_d = DDP(net_d)

    try:  # 如果能加载自动resume
        _, _, _, epoch_str = utils.load_checkpoint(
            utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"), net_d, optim_d
        )  # D多半加载没事
        if rank == 0:
            logger.info("loaded D")
        # _, _, _, epoch_str = utils.load_checkpoint(utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"), net_g, optim_g,load_opt=0)
        _, _, _, epoch_str = utils.load_checkpoint(
            utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"), net_g, optim_g
        )
        global_step = (epoch_str - 1) * len(train_loader)
        # epoch_str = 1
        # global_step = 0
    except:  # 如果首次不能加载,加载pretrain
        os.system('cls' if os.name == 'nt' else 'clear')
        epoch_str = 1
        global_step = 0
        if hps.pretrainG != "":
            if rank == 0:
                logger.info("Loaded pretrained %s" % (hps.pretrainG))
            if hasattr(net_g, "module"):
                logger.info(
                    net_g.module.load_state_dict(
                        torch.load(hps.pretrainG, map_location="cpu")["model"]
                    )
                )  ##测试不加载优化器
            else:
                logger.info(
                    net_g.load_state_dict(
                        torch.load(hps.pretrainG, map_location="cpu")["model"]
                    )
                )  ##测试不加载优化器
        if hps.pretrainD != "":
            if rank == 0:
                logger.info("Loaded pretrained %s" % (hps.pretrainD))
            if hasattr(net_d, "module"):
                logger.info(
                    net_d.module.load_state_dict(
                        torch.load(hps.pretrainD, map_location="cpu")["model"]
                    )
                )
            else:
                logger.info(
                    net_d.load_state_dict(
                        torch.load(hps.pretrainD, map_location="cpu")["model"]
                    )
                )

    scheduler_g = torch.optim.lr_scheduler.ExponentialLR(
        optim_g, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
    )
    scheduler_d = torch.optim.lr_scheduler.ExponentialLR(
        optim_d, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
    )

    scaler = GradScaler(enabled=hps.train.fp16_run)

    cache = []
    for epoch in range(epoch_str, hps.train.epochs + 1):
        if rank == 0:
            train_and_evaluate(
                rank,
                epoch,
                hps,
                [net_g, net_d],
                [optim_g, optim_d],
                [scheduler_g, scheduler_d],
                scaler,
                [train_loader, None],
                logger,
                [writer, writer_eval],
                cache,
            )
        else:
            train_and_evaluate(
                rank,
                epoch,
                hps,
                [net_g, net_d],
                [optim_g, optim_d],
                [scheduler_g, scheduler_d],
                scaler,
                [train_loader, None],
                None,
                None,
                cache,
            )
        scheduler_g.step()
        scheduler_d.step()


def train_and_evaluate(
    rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger, writers, cache
):
    net_g, net_d = nets
    optim_g, optim_d = optims
    train_loader, eval_loader = loaders
    if writers is not None:
        writer, writer_eval = writers

    train_loader.batch_sampler.set_epoch(epoch)
    global global_step

    net_g.train()
    net_d.train()

    # Prepare data iterator
    if hps.if_cache_data_in_gpu == True:
        # Use Cache
        data_iterator = cache
        if cache == []:
            # Make new cache
            for batch_idx, info in enumerate(train_loader):
                # Unpack
                if hps.if_f0 == 1:
                    (
                        phone,
                        phone_lengths,
                        pitch,
                        pitchf,
                        spec,
                        spec_lengths,
                        wave,
                        wave_lengths,
                        sid,
                    ) = info
                else:
                    (
                        phone,
                        phone_lengths,
                        spec,
                        spec_lengths,
                        wave,
                        wave_lengths,
                        sid,
                    ) = info
                # Load on CUDA
                if torch.cuda.is_available():
                    phone = phone.cuda(rank, non_blocking=True)
                    phone_lengths = phone_lengths.cuda(rank, non_blocking=True)
                    if hps.if_f0 == 1:
                        pitch = pitch.cuda(rank, non_blocking=True)
                        pitchf = pitchf.cuda(rank, non_blocking=True)
                    sid = sid.cuda(rank, non_blocking=True)
                    spec = spec.cuda(rank, non_blocking=True)
                    spec_lengths = spec_lengths.cuda(rank, non_blocking=True)
                    wave = wave.cuda(rank, non_blocking=True)
                    wave_lengths = wave_lengths.cuda(rank, non_blocking=True)
                # Cache on list
                if hps.if_f0 == 1:
                    cache.append(
                        (
                            batch_idx,
                            (
                                phone,
                                phone_lengths,
                                pitch,
                                pitchf,
                                spec,
                                spec_lengths,
                                wave,
                                wave_lengths,
                                sid,
                            ),
                        )
                    )
                else:
                    cache.append(
                        (
                            batch_idx,
                            (
                                phone,
                                phone_lengths,
                                spec,
                                spec_lengths,
                                wave,
                                wave_lengths,
                                sid,
                            ),
                        )
                    )
        else:
            # Load shuffled cache
            shuffle(cache)
    else:
        # Loader
        data_iterator = enumerate(train_loader)

    # Run steps
    epoch_recorder = EpochRecorder()
    for batch_idx, info in data_iterator:
        # Data
        ## Unpack
        if hps.if_f0 == 1:
            (
                phone,
                phone_lengths,
                pitch,
                pitchf,
                spec,
                spec_lengths,
                wave,
                wave_lengths,
                sid,
            ) = info
        else:
            phone, phone_lengths, spec, spec_lengths, wave, wave_lengths, sid = info
        ## Load on CUDA
        if (hps.if_cache_data_in_gpu == False) and torch.cuda.is_available():
            phone = phone.cuda(rank, non_blocking=True)
            phone_lengths = phone_lengths.cuda(rank, non_blocking=True)
            if hps.if_f0 == 1:
                pitch = pitch.cuda(rank, non_blocking=True)
                pitchf = pitchf.cuda(rank, non_blocking=True)
            sid = sid.cuda(rank, non_blocking=True)
            spec = spec.cuda(rank, non_blocking=True)
            spec_lengths = spec_lengths.cuda(rank, non_blocking=True)
            wave = wave.cuda(rank, non_blocking=True)
            # wave_lengths = wave_lengths.cuda(rank, non_blocking=True)

        # Calculate
        with autocast(enabled=hps.train.fp16_run):
            if hps.if_f0 == 1:
                (
                    y_hat,
                    ids_slice,
                    x_mask,
                    z_mask,
                    (z, z_p, m_p, logs_p, m_q, logs_q),
                ) = net_g(phone, phone_lengths, pitch, pitchf, spec, spec_lengths, sid)
            else:
                (
                    y_hat,
                    ids_slice,
                    x_mask,
                    z_mask,
                    (z, z_p, m_p, logs_p, m_q, logs_q),
                ) = net_g(phone, phone_lengths, spec, spec_lengths, sid)
            mel = spec_to_mel_torch(
                spec,
                hps.data.filter_length,
                hps.data.n_mel_channels,
                hps.data.sampling_rate,
                hps.data.mel_fmin,
                hps.data.mel_fmax,
            )
            y_mel = commons.slice_segments(
                mel, ids_slice, hps.train.segment_size // hps.data.hop_length
            )
            with autocast(enabled=False):
                y_hat_mel = mel_spectrogram_torch(
                    y_hat.float().squeeze(1),
                    hps.data.filter_length,
                    hps.data.n_mel_channels,
                    hps.data.sampling_rate,
                    hps.data.hop_length,
                    hps.data.win_length,
                    hps.data.mel_fmin,
                    hps.data.mel_fmax,
                )
            if hps.train.fp16_run == True:
                y_hat_mel = y_hat_mel.float()
            wave = commons.slice_segments(
                wave, ids_slice * hps.data.hop_length, hps.train.segment_size
            )  # slice

            # Discriminator
            y_d_hat_r, y_d_hat_g, _, _ = net_d(wave, y_hat.detach())
            with autocast(enabled=False):
                loss_disc, losses_disc_r, losses_disc_g = discriminator_loss(
                    y_d_hat_r, y_d_hat_g
                )
        optim_d.zero_grad()
        scaler.scale(loss_disc).backward()
        scaler.unscale_(optim_d)
        grad_norm_d = commons.clip_grad_value_(net_d.parameters(), None)
        scaler.step(optim_d)

        with autocast(enabled=hps.train.fp16_run):
            # Generator
            y_d_hat_r, y_d_hat_g, fmap_r, fmap_g = net_d(wave, y_hat)
            with autocast(enabled=False):
                loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
                loss_kl = kl_loss(z_p, logs_q, m_p, logs_p, z_mask) * hps.train.c_kl
                loss_fm = feature_loss(fmap_r, fmap_g)
                loss_gen, losses_gen = generator_loss(y_d_hat_g)
                loss_gen_all = loss_gen + loss_fm + loss_mel + loss_kl
        optim_g.zero_grad()
        scaler.scale(loss_gen_all).backward()
        scaler.unscale_(optim_g)
        grad_norm_g = commons.clip_grad_value_(net_g.parameters(), None)
        scaler.step(optim_g)
        scaler.update()

        if rank == 0:
            if global_step % hps.train.log_interval == 0:
                lr = optim_g.param_groups[0]["lr"]
                logger.info(
                    "Train Epoch: {} [{:.0f}%]".format(
                        epoch, 100.0 * batch_idx / len(train_loader)
                    )
                )
                # Amor For Tensorboard display
                if loss_mel > 75:
                    loss_mel = 75
                if loss_kl > 9:
                    loss_kl = 9

                logger.info([global_step, lr])
                logger.info(
                    f"[loss_disc={loss_disc:.3f}] | [loss_gen={loss_gen:.3f}] | [loss_fm={loss_fm:.3f}] | [loss_mel={loss_mel:.3f}] | [loss_kl={loss_kl:.3f}]"
                )
                scalar_dict = {
                    "loss/g/total": loss_gen_all,
                    "loss/d/total": loss_disc,
                    "learning_rate": lr,
                    "grad_norm_d": grad_norm_d,
                    "grad_norm_g": grad_norm_g,
                }
                scalar_dict.update(
                    {
                        "loss/g/fm": loss_fm,
                        "loss/g/mel": loss_mel,
                        "loss/g/kl": loss_kl,
                    }
                )

                scalar_dict.update(
                    {"loss/g/{}".format(i): v for i, v in enumerate(losses_gen)}
                )
                scalar_dict.update(
                    {"loss/d_r/{}".format(i): v for i, v in enumerate(losses_disc_r)}
                )
                scalar_dict.update(
                    {"loss/d_g/{}".format(i): v for i, v in enumerate(losses_disc_g)}
                )
                image_dict = {
                    "slice/mel_org": utils.plot_spectrogram_to_numpy(
                        y_mel[0].data.cpu().numpy()
                    ),
                    "slice/mel_gen": utils.plot_spectrogram_to_numpy(
                        y_hat_mel[0].data.cpu().numpy()
                    ),
                    "all/mel": utils.plot_spectrogram_to_numpy(
                        mel[0].data.cpu().numpy()
                    ),
                }
                utils.summarize(
                    writer=writer,
                    global_step=global_step,
                    images=image_dict,
                    scalars=scalar_dict,
                )
        global_step += 1
    # /Run steps

    if epoch % hps.save_every_epoch == 0 and rank == 0:
        if hps.if_latest == 0:
            utils.save_checkpoint(
                net_g,
                optim_g,
                hps.train.learning_rate,
                epoch,
                os.path.join(hps.model_dir, "G_{}.pth".format(global_step)),
            )
            utils.save_checkpoint(
                net_d,
                optim_d,
                hps.train.learning_rate,
                epoch,
                os.path.join(hps.model_dir, "D_{}.pth".format(global_step)),
            )
        else:
            utils.save_checkpoint(
                net_g,
                optim_g,
                hps.train.learning_rate,
                epoch,
                os.path.join(hps.model_dir, "G_{}.pth".format(2333333)),
            )
            utils.save_checkpoint(
                net_d,
                optim_d,
                hps.train.learning_rate,
                epoch,
                os.path.join(hps.model_dir, "D_{}.pth".format(2333333)),
            )
        if rank == 0 and hps.save_every_weights == "1":
            if hasattr(net_g, "module"):
                ckpt = net_g.module.state_dict()
            else:
                ckpt = net_g.state_dict()
            logger.info(
                "saving ckpt %s_e%s:%s"
                % (
                    hps.name,
                    epoch,
                    savee(
                        ckpt,
                        hps.sample_rate,
                        hps.if_f0,
                        hps.name + "_e%s_s%s" % (epoch, global_step),
                        epoch,
                        hps.version,
                        hps,
                    ),
                )
            )
    
    stopbtn = False
    try:
        with open("lib/csvdb/stop.csv", 'r') as csv_file:
            stopbtn_str = next(csv.reader(csv_file), [None])[0]
            if stopbtn_str is not None: stopbtn = stopbtn_str.lower() == 'true'
    except (ValueError, TypeError, FileNotFoundError, IndexError) as e:
        print(f"Handling exception: {e}")
        stopbtn = False

    if stopbtn:
        logger.info("Stop Button was pressed. The program is closed.")
        ckpt = net_g.module.state_dict() if hasattr(net_g, "module") else net_g.state_dict()
        logger.info(
            "saving final ckpt:%s"
            % (
                savee(
                    ckpt, hps.sample_rate, hps.if_f0, hps.name, epoch, hps.version, hps
                )
            )
        )
        sleep(1)
        reset_stop_flag()
        os._exit(2333333)

    if rank == 0:
        logger.info("Epoch: {} {}".format(epoch, epoch_recorder.record()))
    if epoch >= hps.total_epoch and rank == 0:
        logger.info("Training successfully completed, closing the program...")

        if hasattr(net_g, "module"):
            ckpt = net_g.module.state_dict()
        else:
            ckpt = net_g.state_dict()
        logger.info(
            "Saving final ckpt... %s"
            % (
                savee(
                    ckpt, hps.sample_rate, hps.if_f0, hps.name, epoch, hps.version, hps
                )
            )
        )
        sleep(1)
        os._exit(2333333)


if __name__ == "__main__":
    torch.multiprocessing.set_start_method("spawn")
    main()