File size: 20,950 Bytes
6efc863
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
import torch
import pytorch_lightning as pl
import torch.nn.functional as F
from contextlib import contextmanager
from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
from packaging import version
import numpy as np
from ldm.modules.diffusionmodules.model import Encoder, Decoder
from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
from torch.optim.lr_scheduler import LambdaLR
from ldm.util import instantiate_from_config
from icecream import ic

class VQModel(pl.LightningModule):
    def __init__(self,
                 ddconfig,
                 lossconfig,
                 n_embed,
                 embed_dim,
                 ckpt_path=None,
                 ignore_keys=[],
                 image_key="image",
                 colorize_nlabels=None,
                 monitor=None,
                 batch_resize_range=None,
                 scheduler_config=None,
                 lr_g_factor=1.0,
                 remap=None,
                 sane_index_shape=False, # tell vector quantizer to return indices as bhw
                 use_ema=False
                 ):
        super().__init__()
        self.embed_dim = embed_dim
        self.n_embed = n_embed
        self.image_key = image_key
        self.encoder = Encoder(**ddconfig)
        self.decoder = Decoder(**ddconfig)
        self.loss = instantiate_from_config(lossconfig)
        self.quantize = VectorQuantizer(n_embed, embed_dim, beta=0.25,
                                        remap=remap,
                                        sane_index_shape=sane_index_shape)
        self.quant_conv = torch.nn.Conv2d(ddconfig["z_channels"], embed_dim, 1)
        self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
        if colorize_nlabels is not None:
            assert type(colorize_nlabels)==int
            self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
        if monitor is not None:
            self.monitor = monitor
        self.batch_resize_range = batch_resize_range
        if self.batch_resize_range is not None:
            print(f"{self.__class__.__name__}: Using per-batch resizing in range {batch_resize_range}.")

        self.use_ema = use_ema
        if self.use_ema:
            self.model_ema = LitEma(self)
            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")

        if ckpt_path is not None:
            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
        self.scheduler_config = scheduler_config
        self.lr_g_factor = lr_g_factor

    @contextmanager
    def ema_scope(self, context=None):
        if self.use_ema:
            self.model_ema.store(self.parameters())
            self.model_ema.copy_to(self)
            if context is not None:
                print(f"{context}: Switched to EMA weights")
        try:
            yield None
        finally:
            if self.use_ema:
                self.model_ema.restore(self.parameters())
                if context is not None:
                    print(f"{context}: Restored training weights")

    def init_from_ckpt(self, path, ignore_keys=list()):
        sd = torch.load(path, map_location="cpu")["state_dict"]
        keys = list(sd.keys())
        for k in keys:
            for ik in ignore_keys:
                if k.startswith(ik):
                    print("Deleting key {} from state_dict.".format(k))
                    del sd[k]
        missing, unexpected = self.load_state_dict(sd, strict=False)
        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
        if len(missing) > 0:
            print(f"Missing Keys: {missing}")
            print(f"Unexpected Keys: {unexpected}")

    def on_train_batch_end(self, *args, **kwargs):
        if self.use_ema:
            self.model_ema(self)

    def encode(self, x):
        h = self.encoder(x)
        h = self.quant_conv(h)
        quant, emb_loss, info = self.quantize(h)
        return quant, emb_loss, info

    def encode_to_prequant(self, x):
        h = self.encoder(x)
        h = self.quant_conv(h)
        return h

    def decode(self, quant):
        quant = self.post_quant_conv(quant)
        dec = self.decoder(quant)
        return dec

    def decode_code(self, code_b):
        quant_b = self.quantize.embed_code(code_b)
        dec = self.decode(quant_b)
        return dec

    def forward(self, input, return_pred_indices=False):
        quant, diff, (_,_,ind) = self.encode(input)
        dec = self.decode(quant)
        if return_pred_indices:
            return dec, diff, ind
        return dec, diff

    def get_input(self, batch, k):
        x = batch[k]
        if len(x.shape) == 3:
            x = x[..., None]
        x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float()
        if self.batch_resize_range is not None:
            lower_size = self.batch_resize_range[0]
            upper_size = self.batch_resize_range[1]
            if self.global_step <= 4:
                # do the first few batches with max size to avoid later oom
                new_resize = upper_size
            else:
                new_resize = np.random.choice(np.arange(lower_size, upper_size+16, 16))
            if new_resize != x.shape[2]:
                x = F.interpolate(x, size=new_resize, mode="bicubic")
            x = x.detach()
        return x

    def training_step(self, batch, batch_idx, optimizer_idx):
        # https://github.com/pytorch/pytorch/issues/37142
        # try not to fool the heuristics
        x = self.get_input(batch, self.image_key)
        xrec, qloss, ind = self(x, return_pred_indices=True)

        if optimizer_idx == 0:
            # autoencode
            aeloss, log_dict_ae = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
                                            last_layer=self.get_last_layer(), split="train",
                                            predicted_indices=ind)

            self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=True)
            return aeloss

        if optimizer_idx == 1:
            # discriminator
            discloss, log_dict_disc = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
                                            last_layer=self.get_last_layer(), split="train")
            self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=True)
            return discloss

    def validation_step(self, batch, batch_idx):
        log_dict = self._validation_step(batch, batch_idx)
        with self.ema_scope():
            log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema")
        return log_dict

    def _validation_step(self, batch, batch_idx, suffix=""):
        x = self.get_input(batch, self.image_key)
        xrec, qloss, ind = self(x, return_pred_indices=True)
        aeloss, log_dict_ae = self.loss(qloss, x, xrec, 0,
                                        self.global_step,
                                        last_layer=self.get_last_layer(),
                                        split="val"+suffix,
                                        predicted_indices=ind
                                        )

        discloss, log_dict_disc = self.loss(qloss, x, xrec, 1,
                                            self.global_step,
                                            last_layer=self.get_last_layer(),
                                            split="val"+suffix,
                                            predicted_indices=ind
                                            )
        rec_loss = log_dict_ae[f"val{suffix}/rec_loss"]
        self.log(f"val{suffix}/rec_loss", rec_loss,
                   prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
        self.log(f"val{suffix}/aeloss", aeloss,
                   prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
        if version.parse(pl.__version__) >= version.parse('1.4.0'):
            del log_dict_ae[f"val{suffix}/rec_loss"]
        self.log_dict(log_dict_ae)
        self.log_dict(log_dict_disc)
        return self.log_dict

    def test_step(self, batch, batch_idx):
        x = self.get_input(batch, self.image_key)
        xrec, qloss, ind = self(x, return_pred_indices=True)
        reconstructions = (xrec + 1)/2 # to mel scale
        test_ckpt_path = os.path.basename(self.trainer.tested_ckpt_path)
        savedir = os.path.join(self.trainer.log_dir,f'output_imgs_{test_ckpt_path}','fake_class')
        if not os.path.exists(savedir):
            os.makedirs(savedir)

        file_names = batch['f_name']
        # print(f"reconstructions.shape:{reconstructions.shape}",file_names)
        reconstructions = reconstructions.cpu().numpy().squeeze(1) # squuze channel dim
        for b in range(reconstructions.shape[0]):
            vname_num_split_index = file_names[b].rfind('_')# file_names[b]:video_name+'_'+num
            v_n,num = file_names[b][:vname_num_split_index],file_names[b][vname_num_split_index+1:]
            save_img_path = os.path.join(savedir,f'{v_n}_sample_{num}.npy')
            np.save(save_img_path,reconstructions[b])
        
        return None

    def configure_optimizers(self):
        lr_d = self.learning_rate
        lr_g = self.lr_g_factor*self.learning_rate
        print("lr_d", lr_d)
        print("lr_g", lr_g)
        opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
                                  list(self.decoder.parameters())+
                                  list(self.quantize.parameters())+
                                  list(self.quant_conv.parameters())+
                                  list(self.post_quant_conv.parameters()),
                                  lr=lr_g, betas=(0.5, 0.9))
        opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
                                    lr=lr_d, betas=(0.5, 0.9))

        if self.scheduler_config is not None:
            scheduler = instantiate_from_config(self.scheduler_config)

            print("Setting up LambdaLR scheduler...")
            scheduler = [
                {
                    'scheduler': LambdaLR(opt_ae, lr_lambda=scheduler.schedule),
                    'interval': 'step',
                    'frequency': 1
                },
                {
                    'scheduler': LambdaLR(opt_disc, lr_lambda=scheduler.schedule),
                    'interval': 'step',
                    'frequency': 1
                },
            ]
            return [opt_ae, opt_disc], scheduler
        return [opt_ae, opt_disc], []

    def get_last_layer(self):
        return self.decoder.conv_out.weight

    def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs):
        log = dict()
        x = self.get_input(batch, self.image_key)
        x = x.to(self.device)
        if only_inputs:
            log["inputs"] = x
            return log
        xrec, _ = self(x)
        if x.shape[1] > 3:
            # colorize with random projection
            assert xrec.shape[1] > 3
            x = self.to_rgb(x)
            xrec = self.to_rgb(xrec)
        log["inputs"] = x
        log["reconstructions"] = xrec
        if plot_ema:
            with self.ema_scope():
                xrec_ema, _ = self(x)
                if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema)
                log["reconstructions_ema"] = xrec_ema
        return log

    def to_rgb(self, x):
        assert self.image_key == "segmentation"
        if not hasattr(self, "colorize"):
            self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
        x = F.conv2d(x, weight=self.colorize)
        x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
        return x


class VQModelInterface(VQModel):
    def __init__(self, embed_dim, *args, **kwargs):
        super().__init__(embed_dim=embed_dim, *args, **kwargs)
        self.embed_dim = embed_dim

    def encode(self, x):# VQModel的quantize写在encoder里,VQModelInterface则将其写在decoder里
        h = self.encoder(x)
        h = self.quant_conv(h)
        return h

    def decode(self, h, force_not_quantize=False):
        # also go through quantization layer
        if not force_not_quantize:
            quant, emb_loss, info = self.quantize(h)
        else:
            quant = h
        quant = self.post_quant_conv(quant)
        dec = self.decoder(quant)
        return dec


class AutoencoderKL(pl.LightningModule):
    def __init__(self,
                 ddconfig,
                 lossconfig,
                 embed_dim,
                 ckpt_path=None,
                 ignore_keys=[],
                 image_key="image",
                 colorize_nlabels=None,
                 monitor=None,
                 ):
        super().__init__()
        self.to_1d = False
        print(f"to_1d is {self.to_1d} in AUTOENCODER")
        self.image_key = image_key
        self.encoder = Encoder(**ddconfig)
        self.decoder = Decoder(**ddconfig)
        self.loss = instantiate_from_config(lossconfig)
        assert ddconfig["double_z"]
        self.quant_conv = torch.nn.Conv2d(2*ddconfig["z_channels"], 2*embed_dim, 1)
        self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
        self.embed_dim = embed_dim
        if colorize_nlabels is not None:
            assert type(colorize_nlabels)==int
            self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
        if monitor is not None:
            self.monitor = monitor
        if ckpt_path is not None:
            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
        # self.automatic_optimization = False # hjw for debug

    def init_from_ckpt(self, path, ignore_keys=list()):
        sd = torch.load(path, map_location="cpu")["state_dict"]
        keys = list(sd.keys())
        for k in keys:
            for ik in ignore_keys:
                if k.startswith(ik):
                    print("Deleting key {} from state_dict.".format(k))
                    del sd[k]
        self.load_state_dict(sd, strict=False)
        print(f"Restored from {path}")

    def encode(self, x):
        if self.to_1d and len(x.shape)==3:
            x = x.unsqueeze(1)
        h = self.encoder(x)
        moments = self.quant_conv(h)
        if self.to_1d:
            b,c,h,w = moments.shape
            moments = moments.reshape(b,c*h,w)
        posterior = DiagonalGaussianDistribution(moments)
        return posterior

    def decode(self, z):
        if self.to_1d:
            b,c_h,w = z.shape
            c = self.post_quant_conv.in_channels
            z = z.reshape(b,c,-1,w)
        z = self.post_quant_conv(z)
        dec = self.decoder(z)
        return dec

    def forward(self, input, sample_posterior=True):
        posterior = self.encode(input)
        if sample_posterior:
            z = posterior.sample()
        else:
            z = posterior.mode()
        dec = self.decode(z)
        return dec, posterior

    def get_input(self, batch, k):
        x = batch[k]
        if len(x.shape) == 3:
            x = x[..., None]
        x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float()
        return x

    def training_step(self, batch, batch_idx, optimizer_idx):
        inputs = self.get_input(batch, self.image_key)
        reconstructions, posterior = self(inputs)

        if optimizer_idx == 0:
            # train encoder+decoder+logvar
            aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
                                            last_layer=self.get_last_layer(), split="train")
            self.log("aeloss", aeloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
            self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=False)
            # print(optimizer_idx,log_dict_ae)
            return aeloss

        if optimizer_idx == 1:
            # train the discriminator
            discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
                                                last_layer=self.get_last_layer(), split="train")

            self.log("discloss", discloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
            self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=False)
            # print(optimizer_idx,log_dict_disc)
            return discloss

    def validation_step(self, batch, batch_idx):
        inputs = self.get_input(batch, self.image_key)
        reconstructions, posterior = self(inputs)
        aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, 0, self.global_step,
                                        last_layer=self.get_last_layer(), split="val")

        discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, 1, self.global_step,
                                            last_layer=self.get_last_layer(), split="val")

        self.log("val/rec_loss", log_dict_ae["val/rec_loss"])
        self.log_dict(log_dict_ae)
        self.log_dict(log_dict_disc)
        return self.log_dict

    def test_step(self, batch, batch_idx):
        inputs = self.get_input(batch, self.image_key)# inputs shape:(b,mel_len,T)
        reconstructions, posterior = self(inputs)# reconstructions:(b,mel_len,T)
        mse_loss = torch.nn.functional.mse_loss(reconstructions,inputs)
        self.log('test/mse_loss',mse_loss)
          
        test_ckpt_path = os.path.basename(self.trainer.tested_ckpt_path)
        savedir = os.path.join(self.trainer.log_dir,f'output_imgs_{test_ckpt_path}','fake_class')
        if batch_idx == 0:
            print(f"save_path is: {savedir}")
        if not os.path.exists(savedir):
            os.makedirs(savedir)
            print(f"save_path is: {savedir}")

        file_names = batch['f_name']
        # print(f"reconstructions.shape:{reconstructions.shape}",file_names)
        # reconstructions = (reconstructions + 1)/2 # to mel scale  
        reconstructions = reconstructions.cpu().numpy().squeeze(1) # squeeze channel dim
        for b in range(reconstructions.shape[0]):
            vname_num_split_index = file_names[b].rfind('_')# file_names[b]:video_name+'_'+num
            v_n,num = file_names[b][:vname_num_split_index],file_names[b][vname_num_split_index+1:]
            save_img_path = os.path.join(savedir, f'{v_n}.npy') # f'{v_n}_sample_{num}.npy'   f'{v_n}.npy'
            np.save(save_img_path,reconstructions[b])
        
        return None
        
    def configure_optimizers(self):
        lr = self.learning_rate
        opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
                                  list(self.decoder.parameters())+
                                  list(self.quant_conv.parameters())+
                                  list(self.post_quant_conv.parameters()),
                                  lr=lr, betas=(0.5, 0.9))
        opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
                                    lr=lr, betas=(0.5, 0.9))
        return [opt_ae, opt_disc], []

    def get_last_layer(self):
        return self.decoder.conv_out.weight

    @torch.no_grad()
    def log_images(self, batch, only_inputs=False,save_dir = 'mel_result_ae13_26_debug/fake_class', **kwargs): # 在main.py的on_validation_batch_end中调用
        log = dict()
        x = self.get_input(batch, self.image_key)
        x = x.to(self.device)
        if not only_inputs:
            xrec, posterior = self(x)
            if x.shape[1] > 3:
                # colorize with random projection
                assert xrec.shape[1] > 3
                x = self.to_rgb(x)
                xrec = self.to_rgb(xrec)
            log["samples"] = self.decode(torch.randn_like(posterior.sample()))
            log["reconstructions"] = xrec
        log["inputs"] = x
        return log

    def to_rgb(self, x):
        assert self.image_key == "segmentation"
        if not hasattr(self, "colorize"):
            self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
        x = F.conv2d(x, weight=self.colorize)
        x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
        return x


class IdentityFirstStage(torch.nn.Module):
    def __init__(self, *args, vq_interface=False, **kwargs):
        self.vq_interface = vq_interface  # TODO: Should be true by default but check to not break older stuff
        super().__init__()

    def encode(self, x, *args, **kwargs):
        return x

    def decode(self, x, *args, **kwargs):
        return x

    def quantize(self, x, *args, **kwargs):
        if self.vq_interface:
            return x, None, [None, None, None]
        return x

    def forward(self, x, *args, **kwargs):
        return x