Spaces:
V3N0M
/
Runtime error

File size: 16,250 Bytes
7bc29af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os, traceback
import glob
import sys
import argparse
import logging
import json
import subprocess
import numpy as np
from scipy.io.wavfile import read
import torch

MATPLOTLIB_FLAG = False

logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logger = logging


def load_checkpoint_d(checkpoint_path, combd, sbd, optimizer=None, load_opt=1):
    assert os.path.isfile(checkpoint_path)
    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")

    ##################
    def go(model, bkey):
        saved_state_dict = checkpoint_dict[bkey]
        if hasattr(model, "module"):
            state_dict = model.module.state_dict()
        else:
            state_dict = model.state_dict()
        new_state_dict = {}
        for k, v in state_dict.items():  # 模型需要的shape
            try:
                new_state_dict[k] = saved_state_dict[k]
                if saved_state_dict[k].shape != state_dict[k].shape:
                    print(
                        "shape-%s-mismatch|need-%s|get-%s"
                        % (k, state_dict[k].shape, saved_state_dict[k].shape)
                    )  #
                    raise KeyError
            except:
                # logger.info(traceback.format_exc())
                logger.info("%s is not in the checkpoint" % k)  # pretrain缺失的
                new_state_dict[k] = v  # 模型自带的随机值
        if hasattr(model, "module"):
            model.module.load_state_dict(new_state_dict, strict=False)
        else:
            model.load_state_dict(new_state_dict, strict=False)

    go(combd, "combd")
    go(sbd, "sbd")
    #############
    logger.info("Loaded model weights")

    iteration = checkpoint_dict["iteration"]
    learning_rate = checkpoint_dict["learning_rate"]
    if (
        optimizer is not None and load_opt == 1
    ):  ###加载不了,如果是空的的话,重新初始化,可能还会影响lr时间表的更新,因此在train文件最外围catch
        #   try:
        optimizer.load_state_dict(checkpoint_dict["optimizer"])
    #   except:
    #     traceback.print_exc()
    logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
    return model, optimizer, learning_rate, iteration


# def load_checkpoint(checkpoint_path, model, optimizer=None):
#   assert os.path.isfile(checkpoint_path)
#   checkpoint_dict = torch.load(checkpoint_path, map_location='cpu')
#   iteration = checkpoint_dict['iteration']
#   learning_rate = checkpoint_dict['learning_rate']
#   if optimizer is not None:
#     optimizer.load_state_dict(checkpoint_dict['optimizer'])
#   # print(1111)
#   saved_state_dict = checkpoint_dict['model']
#   # print(1111)
#
#   if hasattr(model, 'module'):
#     state_dict = model.module.state_dict()
#   else:
#     state_dict = model.state_dict()
#   new_state_dict= {}
#   for k, v in state_dict.items():
#     try:
#       new_state_dict[k] = saved_state_dict[k]
#     except:
#       logger.info("%s is not in the checkpoint" % k)
#       new_state_dict[k] = v
#   if hasattr(model, 'module'):
#     model.module.load_state_dict(new_state_dict)
#   else:
#     model.load_state_dict(new_state_dict)
#   logger.info("Loaded checkpoint '{}' (epoch {})" .format(
#     checkpoint_path, iteration))
#   return model, optimizer, learning_rate, iteration
def load_checkpoint(checkpoint_path, model, optimizer=None, load_opt=1):
    assert os.path.isfile(checkpoint_path)
    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")

    saved_state_dict = checkpoint_dict["model"]
    if hasattr(model, "module"):
        state_dict = model.module.state_dict()
    else:
        state_dict = model.state_dict()
    new_state_dict = {}
    for k, v in state_dict.items():  # 模型需要的shape
        try:
            new_state_dict[k] = saved_state_dict[k]
            if saved_state_dict[k].shape != state_dict[k].shape:
                print(
                    "shape-%s-mismatch|need-%s|get-%s"
                    % (k, state_dict[k].shape, saved_state_dict[k].shape)
                )  #
                raise KeyError
        except:
            # logger.info(traceback.format_exc())
            logger.info("%s is not in the checkpoint" % k)  # pretrain缺失的
            new_state_dict[k] = v  # 模型自带的随机值
    if hasattr(model, "module"):
        model.module.load_state_dict(new_state_dict, strict=False)
    else:
        model.load_state_dict(new_state_dict, strict=False)
    logger.info("Loaded model weights")

    iteration = checkpoint_dict["iteration"]
    learning_rate = checkpoint_dict["learning_rate"]
    if (
        optimizer is not None and load_opt == 1
    ):  ###加载不了,如果是空的的话,重新初始化,可能还会影响lr时间表的更新,因此在train文件最外围catch
        #   try:
        optimizer.load_state_dict(checkpoint_dict["optimizer"])
    #   except:
    #     traceback.print_exc()
    logger.info("Loaded checkpoint '{}' (epoch {})".format(checkpoint_path, iteration))
    return model, optimizer, learning_rate, iteration


def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
    logger.info(
        "Saving model and optimizer state at epoch {} to {}".format(
            iteration, checkpoint_path
        )
    )
    if hasattr(model, "module"):
        state_dict = model.module.state_dict()
    else:
        state_dict = model.state_dict()
    torch.save(
        {
            "model": state_dict,
            "iteration": iteration,
            "optimizer": optimizer.state_dict(),
            "learning_rate": learning_rate,
        },
        checkpoint_path,
    )


def save_checkpoint_d(combd, sbd, optimizer, learning_rate, iteration, checkpoint_path):
    logger.info(
        "Saving model and optimizer state at epoch {} to {}".format(
            iteration, checkpoint_path
        )
    )
    if hasattr(combd, "module"):
        state_dict_combd = combd.module.state_dict()
    else:
        state_dict_combd = combd.state_dict()
    if hasattr(sbd, "module"):
        state_dict_sbd = sbd.module.state_dict()
    else:
        state_dict_sbd = sbd.state_dict()
    torch.save(
        {
            "combd": state_dict_combd,
            "sbd": state_dict_sbd,
            "iteration": iteration,
            "optimizer": optimizer.state_dict(),
            "learning_rate": learning_rate,
        },
        checkpoint_path,
    )


def summarize(
    writer,
    global_step,
    scalars={},
    histograms={},
    images={},
    audios={},
    audio_sampling_rate=22050,
):
    for k, v in scalars.items():
        writer.add_scalar(k, v, global_step)
    for k, v in histograms.items():
        writer.add_histogram(k, v, global_step)
    for k, v in images.items():
        writer.add_image(k, v, global_step, dataformats="HWC")
    for k, v in audios.items():
        writer.add_audio(k, v, global_step, audio_sampling_rate)


def latest_checkpoint_path(dir_path, regex="G_*.pth"):
    f_list = glob.glob(os.path.join(dir_path, regex))
    f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
    x = f_list[-1]
    print(x)
    return x


def plot_spectrogram_to_numpy(spectrogram):
    global MATPLOTLIB_FLAG
    if not MATPLOTLIB_FLAG:
        import matplotlib

        matplotlib.use("Agg")
        MATPLOTLIB_FLAG = True
        mpl_logger = logging.getLogger("matplotlib")
        mpl_logger.setLevel(logging.WARNING)
    import matplotlib.pylab as plt
    import numpy as np

    fig, ax = plt.subplots(figsize=(10, 2))
    im = ax.imshow(spectrogram, aspect="auto", origin="lower", interpolation="none")
    plt.colorbar(im, ax=ax)
    plt.xlabel("Frames")
    plt.ylabel("Channels")
    plt.tight_layout()

    fig.canvas.draw()
    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
    plt.close()
    return data


def plot_alignment_to_numpy(alignment, info=None):
    global MATPLOTLIB_FLAG
    if not MATPLOTLIB_FLAG:
        import matplotlib

        matplotlib.use("Agg")
        MATPLOTLIB_FLAG = True
        mpl_logger = logging.getLogger("matplotlib")
        mpl_logger.setLevel(logging.WARNING)
    import matplotlib.pylab as plt
    import numpy as np

    fig, ax = plt.subplots(figsize=(6, 4))
    im = ax.imshow(
        alignment.transpose(), aspect="auto", origin="lower", interpolation="none"
    )
    fig.colorbar(im, ax=ax)
    xlabel = "Decoder timestep"
    if info is not None:
        xlabel += "\n\n" + info
    plt.xlabel(xlabel)
    plt.ylabel("Encoder timestep")
    plt.tight_layout()

    fig.canvas.draw()
    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
    plt.close()
    return data


def load_wav_to_torch(full_path):
    sampling_rate, data = read(full_path)
    return torch.FloatTensor(data.astype(np.float32)), sampling_rate


def load_filepaths_and_text(filename, split="|"):
    with open(filename, encoding='utf-8') as f:
        filepaths_and_text = [line.strip().split(split) for line in f]
        filepaths_and_text = [item for item in filepaths_and_text if len(item) == 5]  # ensure there are 5 items.
    return filepaths_and_text


def get_hparams(init=True):
    """
    todo:
      结尾七人组:
        保存频率、总epoch                     done
        bs                                    done
        pretrainG、pretrainD                  done
        卡号:os.en["CUDA_VISIBLE_DEVICES"]   done
        if_latest                             done
      模型:if_f0                             done
      采样率:自动选择config                  done
      是否缓存数据集进GPU:if_cache_data_in_gpu done

      -m:
        自动决定training_files路径,改掉train_nsf_load_pretrain.py里的hps.data.training_files    done
      -c不要了
    """
    parser = argparse.ArgumentParser()
    # parser.add_argument('-c', '--config', type=str, default="configs/40k.json",help='JSON file for configuration')
    parser.add_argument(
        "-se",
        "--save_every_epoch",
        type=int,
        required=True,
        help="checkpoint save frequency (epoch)",
    )
    parser.add_argument(
        "-te", "--total_epoch", type=int, required=True, help="total_epoch"
    )
    parser.add_argument(
        "-pg", "--pretrainG", type=str, default="", help="Pretrained Discriminator path"
    )
    parser.add_argument(
        "-pd", "--pretrainD", type=str, default="", help="Pretrained Generator path"
    )
    parser.add_argument("-g", "--gpus", type=str, default="0", help="split by -")
    parser.add_argument(
        "-bs", "--batch_size", type=int, required=True, help="batch size"
    )
    parser.add_argument(
        "-e", "--experiment_dir", type=str, required=True, help="experiment dir"
    )  # -m
    parser.add_argument(
        "-sr", "--sample_rate", type=str, required=True, help="sample rate, 32k/40k/48k"
    )
    parser.add_argument(
        "-sw",
        "--save_every_weights",
        type=str,
        default="0",
        help="save the extracted model in weights directory when saving checkpoints",
    )
    parser.add_argument(
        "-v", "--version", type=str, required=True, help="model version"
    )
    parser.add_argument(
        "-f0",
        "--if_f0",
        type=int,
        required=True,
        help="use f0 as one of the inputs of the model, 1 or 0",
    )
    parser.add_argument(
        "-l",
        "--if_latest",
        type=int,
        required=True,
        help="if only save the latest G/D pth file, 1 or 0",
    )
    parser.add_argument(
        "-c",
        "--if_cache_data_in_gpu",
        type=int,
        required=True,
        help="if caching the dataset in GPU memory, 1 or 0",
    )
    parser.add_argument(
        "-li", "--log_interval", type=int, required=True, help="log interval"
    )

    args = parser.parse_args()
    name = args.experiment_dir
    experiment_dir = os.path.join("./logs", args.experiment_dir)

    if not os.path.exists(experiment_dir):
        os.makedirs(experiment_dir)

    if args.version == "v1" or args.sample_rate == "40k":
        config_path = "configs/%s.json" % args.sample_rate
    else:
        config_path = "configs/%s_v2.json" % args.sample_rate
    config_save_path = os.path.join(experiment_dir, "config.json")
    if init:
        with open(config_path, "r") as f:
            data = f.read()
        with open(config_save_path, "w") as f:
            f.write(data)
    else:
        with open(config_save_path, "r") as f:
            data = f.read()
    config = json.loads(data)

    hparams = HParams(**config)
    hparams.model_dir = hparams.experiment_dir = experiment_dir
    hparams.save_every_epoch = args.save_every_epoch
    hparams.name = name
    hparams.total_epoch = args.total_epoch
    hparams.pretrainG = args.pretrainG
    hparams.pretrainD = args.pretrainD
    hparams.version = args.version
    hparams.gpus = args.gpus
    hparams.train.batch_size = args.batch_size
    hparams.sample_rate = args.sample_rate
    hparams.if_f0 = args.if_f0
    hparams.if_latest = args.if_latest
    hparams.save_every_weights = args.save_every_weights
    hparams.if_cache_data_in_gpu = args.if_cache_data_in_gpu
    hparams.data.training_files = "%s/filelist.txt" % experiment_dir

    hparams.train.log_interval = args.log_interval

    # Update log_interval in the 'train' section of the config dictionary
    config["train"]["log_interval"] = args.log_interval

    # Save the updated config back to the config_save_path
    with open(config_save_path, "w") as f:
        json.dump(config, f, indent=4)

    return hparams


def get_hparams_from_dir(model_dir):
    config_save_path = os.path.join(model_dir, "config.json")
    with open(config_save_path, "r") as f:
        data = f.read()
    config = json.loads(data)

    hparams = HParams(**config)
    hparams.model_dir = model_dir
    return hparams


def get_hparams_from_file(config_path):
    with open(config_path, "r") as f:
        data = f.read()
    config = json.loads(data)

    hparams = HParams(**config)
    return hparams


def check_git_hash(model_dir):
    source_dir = os.path.dirname(os.path.realpath(__file__))
    if not os.path.exists(os.path.join(source_dir, ".git")):
        logger.warn(
            "{} is not a git repository, therefore hash value comparison will be ignored.".format(
                source_dir
            )
        )
        return

    cur_hash = subprocess.getoutput("git rev-parse HEAD")

    path = os.path.join(model_dir, "githash")
    if os.path.exists(path):
        saved_hash = open(path).read()
        if saved_hash != cur_hash:
            logger.warn(
                "git hash values are different. {}(saved) != {}(current)".format(
                    saved_hash[:8], cur_hash[:8]
                )
            )
    else:
        open(path, "w").write(cur_hash)


def get_logger(model_dir, filename="train.log"):
    global logger
    logger = logging.getLogger(os.path.basename(model_dir))
    logger.setLevel(logging.DEBUG)

    formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
    if not os.path.exists(model_dir):
        os.makedirs(model_dir)
    h = logging.FileHandler(os.path.join(model_dir, filename))
    h.setLevel(logging.DEBUG)
    h.setFormatter(formatter)
    logger.addHandler(h)
    return logger


class HParams:
    def __init__(self, **kwargs):
        for k, v in kwargs.items():
            if type(v) == dict:
                v = HParams(**v)
            self[k] = v

    def keys(self):
        return self.__dict__.keys()

    def items(self):
        return self.__dict__.items()

    def values(self):
        return self.__dict__.values()

    def __len__(self):
        return len(self.__dict__)

    def __getitem__(self, key):
        return getattr(self, key)

    def __setitem__(self, key, value):
        return setattr(self, key, value)

    def __contains__(self, key):
        return key in self.__dict__

    def __repr__(self):
        return self.__dict__.__repr__()