-
Notifications
You must be signed in to change notification settings - Fork 3
/
specialize.py
835 lines (704 loc) · 32.3 KB
/
specialize.py
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
# code adapted from https://github.com/huggingface/diffusers/blob/v0.10.0/examples/dreambooth/train_dreambooth.py
import os
import argparse
import json
import hashlib
import itertools
import logging
import math
import numpy as np
from PIL import Image
try:
from torchvision.transforms import InterpolationMode
BICUBIC = InterpolationMode.BICUBIC
except ImportError:
BICUBIC = Image.BICUBIC
import warnings
from pathlib import Path
from typing import List, Optional, Tuple, Union
import torch
import torch.nn.functional as F
import torch.utils.checkpoint
from torch.utils.data import Dataset
import diffusers
import transformers
from accelerate import Accelerator
from accelerate.logging import get_logger
from accelerate.utils import set_seed
from diffusers import AutoencoderKL, DDPMScheduler, DiffusionPipeline, UNet2DConditionModel
from diffusers.optimization import get_scheduler
# from diffusers.utils import check_min_version
from diffusers.utils.import_utils import is_xformers_available
from huggingface_hub import HfFolder, Repository, whoami
from torchvision import transforms
from tqdm.auto import tqdm
from transformers import AutoTokenizer, PretrainedConfig
#%%
# Will error if the minimal version of diffusers is not installed. Remove at your own risks.
# check_min_version("0.10.0.dev0")
logger = get_logger(__name__)
def import_model_class_from_model_name_or_path(pretrained_model_name_or_path: str, revision: str):
text_encoder_config = PretrainedConfig.from_pretrained(
pretrained_model_name_or_path,
subfolder="text_encoder",
revision=revision,
)
model_class = text_encoder_config.architectures[0]
if model_class == "CLIPTextModel":
from transformers import CLIPTextModel
return CLIPTextModel
elif model_class == "RobertaSeriesModelWithTransformation":
from diffusers.pipelines.alt_diffusion.modeling_roberta_series import RobertaSeriesModelWithTransformation
return RobertaSeriesModelWithTransformation
else:
raise ValueError(f"{model_class} is not supported.")
def parse_args(input_args=None):
parser = argparse.ArgumentParser(description="Simple example of a training script.")
parser.add_argument(
"--pretrained_model_name_or_path",
type=str,
default="runwayml/stable-diffusion-v1-5",
required=False,
help="Path to pretrained model or model identifier from huggingface.co/models.",
)
parser.add_argument(
"--instance_data_dir",
type=str,
default=None,
required=True,
help="A folder containing the training data of training images.",
)
parser.add_argument(
"--instance_age_path",
type=str,
default=None,
required=True,
help="A numpy array that contains the initial ages of training images.",
)
parser.add_argument(
"--instance_prompt",
type=str,
default="photo of a person",
required=False,
help="The prompt with identifier specifying the instance",
)
parser.add_argument(
"--output_dir",
type=str,
default=None,
required=True,
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--finetune_mode",
type=str,
default='finetune_double_prompt',
required=False,
help="Specialization mode, 'finetune_double_prompt'|'finetune_single_prompt'",
)
#####
parser.add_argument(
"--revision",
type=str,
default=None,
required=False,
help=(
"Revision of pretrained model identifier from huggingface.co/models. Trainable model components should be"
" float32 precision."
),
)
parser.add_argument(
"--tokenizer_name",
type=str,
default=None,
help="Pretrained tokenizer name or path if not the same as model_name",
)
parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")
parser.add_argument(
"--resolution",
type=int,
default=512,
help=(
"The resolution for input images, all the images in the train/validation dataset will be resized to this"
" resolution"
),
)
parser.add_argument(
"--center_crop", action="store_true", help="Whether to center crop images before resizing to resolution"
)
parser.add_argument(
"--train_text_encoder",
action="store_true",
help="Whether to train the text encoder. If set, the text encoder should be float32 precision.",
)
parser.add_argument(
"--train_batch_size", type=int, default=1, help="Batch size (per device) for the training dataloader."
)
parser.add_argument(
"--sample_batch_size", type=int, default=4, help="Batch size (per device) for sampling images."
)
parser.add_argument("--num_train_epochs", type=int, default=1)
parser.add_argument(
"--max_train_steps",
type=int,
default=150,
help="Total number of training steps to perform. If provided, overrides num_train_epochs.",
)
parser.add_argument(
"--checkpointing_steps",
type=int,
default=500,
help=(
"Save a checkpoint of the training state every X updates. These checkpoints can be used both as final"
" checkpoints in case they are better than the last checkpoint, and are also suitable for resuming"
" training using `--resume_from_checkpoint`."
),
)
parser.add_argument(
"--resume_from_checkpoint",
type=str,
default=None,
help=(
"Whether training should be resumed from a previous checkpoint. Use a path saved by"
' `--checkpointing_steps`, or `"latest"` to automatically select the last available checkpoint.'
),
)
parser.add_argument(
"--gradient_accumulation_steps",
type=int,
default=1,
help="Number of updates steps to accumulate before performing a backward/update pass.",
)
parser.add_argument(
"--gradient_checkpointing",
action="store_true",
help="Whether or not to use gradient checkpointing to save memory at the expense of slower backward pass.",
)
parser.add_argument(
"--learning_rate",
type=float,
default=5e-6,
help="Initial learning rate (after the potential warmup period) to use.",
)
parser.add_argument(
"--scale_lr",
action="store_true",
default=False,
help="Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.",
)
parser.add_argument(
"--lr_scheduler",
type=str,
default="constant",
help=(
'The scheduler type to use. Choose between ["linear", "cosine", "cosine_with_restarts", "polynomial",'
' "constant", "constant_with_warmup"]'
),
)
parser.add_argument(
"--lr_warmup_steps", type=int, default=500, help="Number of steps for the warmup in the lr scheduler."
)
parser.add_argument(
"--lr_num_cycles",
type=int,
default=1,
help="Number of hard resets of the lr in cosine_with_restarts scheduler.",
)
parser.add_argument("--lr_power", type=float, default=1.0, help="Power factor of the polynomial scheduler.")
parser.add_argument(
"--use_8bit_adam", action="store_true", help="Whether or not to use 8-bit Adam from bitsandbytes."
)
parser.add_argument("--adam_beta1", type=float, default=0.9, help="The beta1 parameter for the Adam optimizer.")
parser.add_argument("--adam_beta2", type=float, default=0.999, help="The beta2 parameter for the Adam optimizer.")
parser.add_argument("--adam_weight_decay", type=float, default=1e-2, help="Weight decay to use.")
parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer")
parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.")
parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.")
parser.add_argument("--hub_token", type=str, default=None, help="The token to use to push to the Model Hub.")
parser.add_argument(
"--hub_model_id",
type=str,
default=None,
help="The name of the repository to keep in sync with the local `output_dir`.",
)
parser.add_argument(
"--logging_dir",
type=str,
default="logs",
help=(
"[TensorBoard](https://www.tensorflow.org/tensorboard) log directory. Will default to"
" *output_dir/runs/**CURRENT_DATETIME_HOSTNAME***."
),
)
parser.add_argument(
"--allow_tf32",
action="store_true",
help=(
"Whether or not to allow TF32 on Ampere GPUs. Can be used to speed up training. For more information, see"
" https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices"
),
)
parser.add_argument(
"--report_to",
type=str,
default="tensorboard",
help=(
'The integration to report the results and logs to. Supported platforms are `"tensorboard"`'
' (default), `"wandb"` and `"comet_ml"`. Use `"all"` to report to all integrations.'
),
)
parser.add_argument(
"--mixed_precision",
type=str,
default=None,
choices=["no", "fp16", "bf16"],
help=(
"Whether to use mixed precision. Choose between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >="
" 1.10.and an Nvidia Ampere GPU. Default to the value of accelerate config of the current system or the"
" flag passed with the `accelerate.launch` command. Use this argument to override the accelerate config."
),
)
parser.add_argument(
"--prior_generation_precision",
type=str,
default=None,
choices=["no", "fp32", "fp16", "bf16"],
help=(
"Choose prior generation precision between fp32, fp16 and bf16 (bfloat16). Bf16 requires PyTorch >="
" 1.10.and an Nvidia Ampere GPU. Default to fp16 if a GPU is available else fp32."
),
)
parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank")
parser.add_argument(
"--enable_xformers_memory_efficient_attention", action="store_true", help="Whether or not to use xformers."
)
if input_args is not None:
args = parser.parse_args(input_args)
else:
args = parser.parse_args()
env_local_rank = int(os.environ.get("LOCAL_RANK", -1))
if env_local_rank != -1 and env_local_rank != args.local_rank:
args.local_rank = env_local_rank
return args
#%%
class DreamBoothDatasetAge(Dataset):
"""
return instance (img, token of 'photo of a xx year old person')
and (img, token of 'photo of a person')
"""
def __init__(
self,
instance_data_root,
instance_age_path, # numpy array that stores the age of training images
tokenizer,
instance_prompt="photo of a person",
size=512,
center_crop=False,
):
self.size = size
self.center_crop = center_crop
self.tokenizer = tokenizer
self.instance_data_root = Path(instance_data_root)
if not self.instance_data_root.exists():
raise ValueError("Instance images root doesn't exists.")
if self.instance_data_root.is_file():
self.instance_images_path = [Path(instance_data_root)]
else:
self.instance_images_path = [os.path.join(instance_data_root,filename) for filename in os.listdir(instance_data_root)]
self.num_instance_images = len(self.instance_images_path)
self.instance_prompt = instance_prompt
self._length = self.num_instance_images
self.age_labels = np.load(instance_age_path)
self.image_transforms = transforms.Compose(
[
transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
]
)
def __len__(self):
return self._length
def __getitem__(self, index):
example = {}
instance_image_path = self.instance_images_path[index % self.num_instance_images]
instance_image = Image.open(instance_image_path)
if not instance_image.mode == "RGB":
instance_image = instance_image.convert("RGB")
example["instance_images"] = self.image_transforms(instance_image)
example["instance_prompt"] = self.instance_prompt
example["instance_prompt_ids"] = self.tokenizer( # token(photo of a person)
self.instance_prompt,
truncation=True,
padding="max_length",
max_length=self.tokenizer.model_max_length,
return_tensors="pt",
).input_ids
instance_image_name = instance_image_path.split('/')[-1]
instance_image_age = int(self.age_labels[self.age_labels[:, 0] == instance_image_name][0, 1])
example["instance_image_age"] = instance_image_age
instance_age_prompt = self.instance_prompt.replace(" a ", f" a {instance_image_age} year old ")
example["instance_age_prompt"] = instance_age_prompt
example["instance_age_prompt_ids"] = self.tokenizer( # token(photo of a xx year old person)
instance_age_prompt,
truncation=True,
padding="max_length",
max_length=self.tokenizer.model_max_length,
return_tensors="pt",
).input_ids
example["blank_prompt_ids"] = self.tokenizer( # token("")
"",
truncation=True,
padding="max_length",
max_length=self.tokenizer.model_max_length,
return_tensors="pt",
).input_ids
return example
#%
def collate_fn(examples, finetune_mode="finetune_double_prompt"):
if len(examples)!=1:
raise ValueError("batchsize can only be 1..")
if finetune_mode == "finetune_double_prompt":
input_ids = [example["instance_prompt_ids"] for example in examples]
input_ids += [example["instance_age_prompt_ids"] for example in examples]
elif finetune_mode == "finetune_single_prompt":
input_ids = [example["instance_age_prompt_ids"] for example in examples]
input_ids += [example["instance_age_prompt_ids"] for example in examples]
# elif finetune_mode == "finetune_single_prompt_no_age":
# input_ids = [example["instance_prompt_ids"] for example in examples]
# input_ids += [example["instance_prompt_ids"] for example in examples]
#
# elif finetune_mode == "finetune_no_prompt":
# input_ids = [example["blank_prompt_ids"] for example in examples]
# input_ids += [example["blank_prompt_ids"] for example in examples]
else:
raise ValueError("invalid finetune_mode")
pixel_values = [example["instance_images"] for example in examples]
pixel_values += [example["instance_images"] for example in examples]
pixel_values_ages = [example["instance_image_age"] for example in examples]
pixel_values = torch.stack(pixel_values)
pixel_values = pixel_values.to(memory_format=torch.contiguous_format).float()
input_ids = torch.cat(input_ids, dim=0)
batch = {
"input_ids": input_ids,
"pixel_values": pixel_values,
"pixel_values_ages": pixel_values_ages,
}
return batch
def get_full_repo_name(model_id: str, organization: Optional[str] = None, token: Optional[str] = None):
if token is None:
token = HfFolder.get_token()
if organization is None:
username = whoami(token)["name"]
return f"{username}/{model_id}"
else:
return f"{organization}/{model_id}"
#%%
def main(args):
argparse_dict = vars(args)
argparse_json = json.dumps(argparse_dict, indent=4)
print("model configuration:\n", argparse_json)
os.makedirs(args.output_dir, exist_ok=True)
with open(os.path.join(args.output_dir, "model_config.json"), "w") as outfile:
outfile.write(argparse_json)
logging_dir = Path(args.output_dir, args.logging_dir)
accelerator = Accelerator(
gradient_accumulation_steps=args.gradient_accumulation_steps,
mixed_precision=args.mixed_precision,
log_with=args.report_to,
logging_dir=logging_dir,
)
# Currently, it's not possible to do gradient accumulation when training two models with accelerate.accumulate
# This will be enabled soon in accelerate. For now, we don't allow gradient accumulation when training two models.
# TODO (patil-suraj): Remove this check when gradient accumulation with two models is enabled in accelerate.
if args.train_text_encoder and args.gradient_accumulation_steps > 1 and accelerator.num_processes > 1:
raise ValueError(
"Gradient accumulation is not supported when training the text encoder in distributed training. "
"Please set gradient_accumulation_steps to 1. This feature will be supported in the future."
)
# Make one log on every process with the configuration for debugging.
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO,
)
logger.info(accelerator.state, main_process_only=False)
if accelerator.is_local_main_process:
# datasets.utils.logging.set_verbosity_warning()
transformers.utils.logging.set_verbosity_warning()
diffusers.utils.logging.set_verbosity_info()
else:
# datasets.utils.logging.set_verbosity_error()
transformers.utils.logging.set_verbosity_error()
diffusers.utils.logging.set_verbosity_error()
# If passed along, set the training seed now.
if args.seed is not None:
set_seed(args.seed)
# Handle the repository creation
if accelerator.is_main_process:
if args.push_to_hub:
if args.hub_model_id is None:
repo_name = get_full_repo_name(Path(args.output_dir).name, token=args.hub_token)
else:
repo_name = args.hub_model_id
repo = Repository(args.output_dir, clone_from=repo_name)
with open(os.path.join(args.output_dir, ".gitignore"), "w+") as gitignore:
if "step_*" not in gitignore:
gitignore.write("step_*\n")
if "epoch_*" not in gitignore:
gitignore.write("epoch_*\n")
elif args.output_dir is not None:
os.makedirs(args.output_dir, exist_ok=True)
# Load the tokenizer
if args.tokenizer_name:
tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_name, revision=args.revision, use_fast=False)
elif args.pretrained_model_name_or_path:
tokenizer = AutoTokenizer.from_pretrained(
args.pretrained_model_name_or_path,
subfolder="tokenizer",
revision=args.revision,
use_fast=False,
)
# import correct text encoder class
text_encoder_cls = import_model_class_from_model_name_or_path(args.pretrained_model_name_or_path, args.revision)
# Load scheduler and models
noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
def pred_original_samples(samples: torch.FloatTensor,
noise: torch.FloatTensor,
timesteps: torch.IntTensor):
sqrt_alpha_prod = noise_scheduler.alphas_cumprod[timesteps] ** 0.5
sqrt_alpha_prod = sqrt_alpha_prod.flatten()
while len(sqrt_alpha_prod.shape) < len(samples.shape):
sqrt_alpha_prod = sqrt_alpha_prod.unsqueeze(-1)
sqrt_one_minus_alpha_prod = (1 - noise_scheduler.alphas_cumprod[timesteps]) ** 0.5
sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.flatten()
while len(sqrt_one_minus_alpha_prod.shape) < len(samples.shape):
sqrt_one_minus_alpha_prod = sqrt_one_minus_alpha_prod.unsqueeze(-1)
original_samples = (samples - sqrt_one_minus_alpha_prod * noise) / sqrt_alpha_prod
return original_samples
text_encoder = text_encoder_cls.from_pretrained(
args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision
)
vae = AutoencoderKL.from_pretrained(args.pretrained_model_name_or_path, subfolder="vae", revision=args.revision)
unet = UNet2DConditionModel.from_pretrained(
args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision
)
vae.requires_grad_(False)
if not args.train_text_encoder:
text_encoder.requires_grad_(False)
if args.enable_xformers_memory_efficient_attention:
if is_xformers_available():
unet.enable_xformers_memory_efficient_attention()
else:
raise ValueError("xformers is not available. Make sure it is installed correctly")
if args.gradient_checkpointing:
unet.enable_gradient_checkpointing()
if args.train_text_encoder:
text_encoder.gradient_checkpointing_enable()
# Enable TF32 for faster training on Ampere GPUs,
# cf https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices
if args.allow_tf32:
torch.backends.cuda.matmul.allow_tf32 = True
if args.scale_lr:
args.learning_rate = (
args.learning_rate * args.gradient_accumulation_steps * args.train_batch_size * accelerator.num_processes
)
# Use 8-bit Adam for lower memory usage or to fine-tune the model in 16GB GPUs
if args.use_8bit_adam:
try:
import bitsandbytes as bnb
except ImportError:
raise ImportError(
"To use 8-bit Adam, please install the bitsandbytes library: `pip install bitsandbytes`."
)
optimizer_class = bnb.optim.AdamW8bit
else:
optimizer_class = torch.optim.AdamW
# Optimizer creation
params_to_optimize = (
itertools.chain(unet.parameters(), text_encoder.parameters()) if args.train_text_encoder else unet.parameters()
)
optimizer = optimizer_class(
params_to_optimize,
lr=args.learning_rate,
betas=(args.adam_beta1, args.adam_beta2),
weight_decay=args.adam_weight_decay,
eps=args.adam_epsilon,
)
train_dataset = DreamBoothDatasetAge(
instance_data_root = args.instance_data_dir,
instance_age_path = args.instance_age_path,
tokenizer = tokenizer,
instance_prompt=args.instance_prompt,
size=args.resolution,
center_crop=args.center_crop,
)
train_dataloader = torch.utils.data.DataLoader(
train_dataset,
batch_size=args.train_batch_size,
shuffle=False,
collate_fn=lambda examples: collate_fn(examples, args.finetune_mode),
num_workers=1,
)
# Scheduler and math around the number of training steps.
overrode_max_train_steps = False
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
if args.max_train_steps is None:
args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
overrode_max_train_steps = True
lr_scheduler = get_scheduler(
args.lr_scheduler,
optimizer=optimizer,
num_warmup_steps=args.lr_warmup_steps * args.gradient_accumulation_steps,
num_training_steps=args.max_train_steps * args.gradient_accumulation_steps,
# num_cycles=args.lr_num_cycles,
# power=args.lr_power,
)
# Prepare everything with our `accelerator`.
if args.train_text_encoder:
unet, text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
unet, text_encoder, optimizer, train_dataloader, lr_scheduler
)
else:
unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
unet, optimizer, train_dataloader, lr_scheduler
)
# For mixed precision training we cast the text_encoder and vae weights to half-precision
# as these models are only used for inference, keeping weights in full precision is not required.
weight_dtype = torch.float32
if accelerator.mixed_precision == "fp16":
weight_dtype = torch.float16
elif accelerator.mixed_precision == "bf16":
weight_dtype = torch.bfloat16
# Move vae and text_encoder to device and cast to weight_dtype
vae.to(accelerator.device, dtype=weight_dtype)
if not args.train_text_encoder:
text_encoder.to(accelerator.device, dtype=weight_dtype)
low_precision_error_string = (
"Please make sure to always have all model weights in full float32 precision when starting training - even if"
" doing mixed precision training. copy of the weights should still be float32."
)
if unet.dtype != torch.float32:
raise ValueError(f"Unet loaded as datatype {unet.dtype}. {low_precision_error_string}")
if args.train_text_encoder and text_encoder.dtype != torch.float32:
raise ValueError(f"Text encoder loaded as datatype {text_encoder.dtype}. {low_precision_error_string}")
# We need to recalculate our total training steps as the size of the training dataloader may have changed.
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
if overrode_max_train_steps:
args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
# Afterwards we recalculate our number of training epochs
args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
# We need to initialize the trackers we use, and also store our configuration.
# The trackers initializes automatically on the main process.
if accelerator.is_main_process:
accelerator.init_trackers("dreambooth", config=vars(args))
# Train!
total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
logger.info("***** Running training *****")
logger.info(f" Num examples = {len(train_dataset)}")
logger.info(f" Num batches each epoch = {len(train_dataloader)}")
logger.info(f" Num Epochs = {args.num_train_epochs}")
logger.info(f" Instantaneous batch size per device = {args.train_batch_size}")
logger.info(f" Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}")
logger.info(f" Gradient Accumulation steps = {args.gradient_accumulation_steps}")
logger.info(f" Total optimization steps = {args.max_train_steps}")
global_step = 0
first_epoch = 0
# Potentially load in the weights and states from a previous save
if args.resume_from_checkpoint:
if args.resume_from_checkpoint != "latest":
path = os.path.basename(args.resume_from_checkpoint)
else:
# Get the mos recent checkpoint
dirs = os.listdir(args.output_dir)
dirs = [d for d in dirs if d.startswith("checkpoint")]
dirs = sorted(dirs, key=lambda x: int(x.split("-")[1]))
path = dirs[-1]
accelerator.print(f"Resuming from checkpoint {path}")
accelerator.load_state(os.path.join(args.output_dir, path))
global_step = int(path.split("-")[1])
resume_global_step = global_step * args.gradient_accumulation_steps
first_epoch = resume_global_step // num_update_steps_per_epoch
resume_step = resume_global_step % num_update_steps_per_epoch
# Only show the progress bar once on each machine.
progress_bar = tqdm(range(global_step, args.max_train_steps), disable=not accelerator.is_local_main_process)
progress_bar.set_description("Steps")
for epoch in range(first_epoch, args.num_train_epochs):
unet.train()
if args.train_text_encoder:
text_encoder.train()
for step, batch in enumerate(train_dataloader):
# Skip steps until we reach the resumed step
if args.resume_from_checkpoint and epoch == first_epoch and step < resume_step:
if step % args.gradient_accumulation_steps == 0:
progress_bar.update(1)
continue
with accelerator.accumulate(unet):
# Convert images to latent space
latents = vae.encode(batch["pixel_values"].to(dtype=weight_dtype)).latent_dist.sample()
latents = latents * 0.18215
# Sample noise that we'll add to the latents
noise = torch.randn_like(latents)
noise_single = torch.randn_like(latents[0])
bsz = latents.shape[0]
noise = torch.cat([noise_single.unsqueeze(0)] * bsz, dim=0)
# Sample a random timestep for each image
timesteps = torch.randint(0, noise_scheduler.config.num_train_timesteps, (bsz,), device=latents.device)
timesteps = timesteps.long()
# Add noise to the latents according to the noise magnitude at each timestep
# (this is the forward diffusion process)
noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
# Get the text embedding for conditioning
encoder_hidden_states = text_encoder(batch["input_ids"])[0]
# Predict the noise residual
model_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
# Get the target for loss depending on the prediction type
if noise_scheduler.config.prediction_type == "epsilon":
target = noise
elif noise_scheduler.config.prediction_type == "v_prediction":
target = noise_scheduler.get_velocity(latents, noise, timesteps)
else:
raise ValueError(f"Unknown prediction type {noise_scheduler.config.prediction_type}")
pred_denoised_latents = pred_original_samples(samples = noisy_latents,
noise = model_pred,
timesteps = timesteps)
# noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
pred_noisy_latents = noise_scheduler.add_noise(latents, model_pred.to(dtype=weight_dtype), timesteps)
loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
instance_loss = loss
# Checks if the accelerator has performed an optimization step behind the scenes
if accelerator.sync_gradients:
progress_bar.update(1)
global_step += 1
if global_step % args.checkpointing_steps == 0:
if accelerator.is_main_process:
save_path = os.path.join(args.output_dir, f"checkpoint-{global_step}")
accelerator.save_state(save_path)
logger.info(f"Saved state to {save_path}")
logs = {"loss": loss.detach().item(),
"instance_loss": instance_loss.detach().item(),
"lr": lr_scheduler.get_last_lr()[0]}
progress_bar.set_postfix(**logs)
accelerator.log(logs, step=global_step)
if global_step >= args.max_train_steps:
break
# Create the pipeline using using the trained modules and save it.
accelerator.wait_for_everyone()
if accelerator.is_main_process:
pipeline = DiffusionPipeline.from_pretrained(
args.pretrained_model_name_or_path,
unet=accelerator.unwrap_model(unet),
text_encoder=accelerator.unwrap_model(text_encoder),
revision=args.revision,
)
pipeline.save_pretrained(args.output_dir)
if args.push_to_hub:
repo.push_to_hub(commit_message="End of training", blocking=False, auto_lfs_prune=True)
accelerator.end_training()
if __name__ == "__main__":
args = parse_args()
# args.instance_data_dir = 'specialization_data/training_images'
# args.instance_age_path = 'specialization_data/training_ages.npy'
#
# args.output_dir = 'specialized_models/tmp'
main(args)