forked from Jacoo-ai/HIC-Yolov5
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test.py
555 lines (552 loc) · 30 KB
/
test.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
import utils.autoanchor as autoAC
new_anchors = autoAC.kmean_anchors('./data/VisDrone.yaml', 12, 640, 3.0, 1000, True)
print(new_anchors)
# print(torch.cuda.memory_summary(device=None, abbreviated=False))
# import argparse
# import logging
# import math
# import os
# import sys
# import time
# from distutils import dist
# from pathlib import Path
# from random import random
#
# import numpy as np
# import torch
# import yaml
# from optuna import trial
# from torch import optim, nn, amp
# from torch.optim import lr_scheduler, Adam, SGD
# from tqdm import tqdm
#
# import val
# from models.experimental import attempt_load
# from models.yolo import Model
# from train import train
# from utils import callbacks
# from utils.autoanchor import check_anchors
# from utils.callbacks import Callbacks
# from utils.datasets import create_dataloader
# from utils.downloads import attempt_download
# from utils.general import set_logging, print_args, check_git_status, check_requirements, get_latest_run, check_file, \
# check_yaml, increment_path, print_mutation, colorstr, check_suffix, init_seeds, check_dataset, check_img_size, \
# labels_to_class_weights, labels_to_image_weights, one_cycle, strip_optimizer
# from utils.loggers import Loggers
# from utils.loggers.wandb.wandb_utils import check_wandb_resume
# from utils.loss import ComputeLoss
# from utils.metrics import fitness
# from utils.plots import plot_evolve, plot_labels
# from utils.torch_utils import select_device, torch_distributed_zero_first, intersect_dicts, EarlyStopping, ModelEMA
#
# FILE = Path(__file__).resolve()
# ROOT = FILE.parents[0] # YOLOv5 root directory
# if str(ROOT) not in sys.path:
# sys.path.append(str(ROOT)) # add ROOT to PATH
# ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
#
# LOGGER = logging.getLogger(__name__)
# LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
# RANK = int(os.getenv('RANK', -1))
# WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
#
#
# def parse_opt(known=False):
# parser = argparse.ArgumentParser()
# parser.add_argument('--weights', type=str, default='C:/yolov5/yolov5-6.0/runs/train/exp18/weights/best.pt',
# help='initial weights path')
# parser.add_argument('--cfg', type=str, default=ROOT / 'models/yolov5x-trans.yaml', help='model.yaml path')
# parser.add_argument('--data', type=str, default=ROOT / 'data/VisDrone.yaml', help='dataset.yaml path')
# parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-high.yaml',
# help='hyperparameters path')
# parser.add_argument('--epochs', type=int, default=49)
# parser.add_argument('--batch-size', type=int, default=4, help='total batch size for all GPUs')
# parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
# parser.add_argument('--rect', action='store_true', help='rectangular training')
# parser.add_argument('--resume', nargs='?', const=True, default=True, help='resume most recent training')
# parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
# parser.add_argument('--noval', action='store_true', help='only validate final epoch')
# parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
# parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
# parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
# parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
# parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
# parser.add_argument('--device', default='1', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
# parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
# parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
# parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
# parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
# parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
# parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
# parser.add_argument('--name', default='exp', help='save to project/name')
# parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
# parser.add_argument('--quad', action='store_true', help='quad dataloader')
# parser.add_argument('--linear-lr', action='store_true', help='linear LR')
# parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
# parser.add_argument('--patience', type=int, default=4, help='EarlyStopping patience (epochs without improvement)')
# parser.add_argument('--freeze', type=int, default=0, help='Number of layers to freeze. backbone=10, all=24')
# parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
# parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
#
# # Weights & Biases arguments
# parser.add_argument('--entity', default=None, help='W&B: Entity')
# parser.add_argument('--upload_dataset', action='store_true', help='W&B: Upload dataset as artifact table')
# parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
# parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')
#
# opt = parser.parse_known_args()[0] if known else parser.parse_args()
# return opt
#
#
# def main(opt, callbacks=Callbacks()):
# # Checks
# set_logging(RANK)
# if RANK in [-1, 0]:
# print_args(FILE.stem, opt)
# check_git_status()
# check_requirements(exclude=['thop'])
#
# # Resume
# if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run
# ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
# assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
# with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
# opt = argparse.Namespace(**yaml.safe_load(f)) # replace
# opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate
# LOGGER.info(f'Resuming training from {ckpt}')
# else:
# opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
# check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks
# assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
# if opt.evolve:
# opt.project = str(ROOT / 'runs/evolve')
# opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume
# opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
#
# # DDP mode
# device = select_device(opt.device, batch_size=opt.batch_size)
# if LOCAL_RANK != -1:
# assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
# assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count'
# assert not opt.image_weights, '--image-weights argument is not compatible with DDP training'
# assert not opt.evolve, '--evolve argument is not compatible with DDP training'
# torch.cuda.set_device(LOCAL_RANK)
# device = torch.device('cuda', LOCAL_RANK)
# dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
#
# # Train
# if not opt.evolve:
# train(opt.hyp, opt, device, callbacks)
# if WORLD_SIZE > 1 and RANK == 0:
# LOGGER.info('Destroying process group... ')
# dist.destroy_process_group()
#
# # Evolve hyperparameters (optional)
# else:
# # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
# meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
# 'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
# 'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
# 'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
# 'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
# 'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
# 'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
# 'box': (1, 0.02, 0.2), # box loss gain
# 'cls': (1, 0.2, 4.0), # cls loss gain
# 'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
# 'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
# 'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
# 'iou_t': (0, 0.1, 0.7), # IoU training threshold
# 'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
# 'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
# 'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
# 'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
# 'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
# 'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
# 'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
# 'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
# 'scale': (1, 0.0, 0.9), # image scale (+/- gain)
# 'shear': (1, 0.0, 10.0), # image shear (+/- deg)
# 'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
# 'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
# 'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
# 'mosaic': (1, 0.0, 1.0), # image mixup (probability)
# 'mixup': (1, 0.0, 1.0), # image mixup (probability)
# 'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability)
#
# with open(opt.hyp, errors='ignore') as f:
# hyp = yaml.safe_load(f) # load hyps dict
# if 'anchors' not in hyp: # anchors commented in hyp.yaml
# hyp['anchors'] = 3
# opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch
# # ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
# evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
# if opt.bucket:
# os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # download evolve.csv if exists
#
# for _ in range(opt.evolve): # generations to evolve
# if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate
# # Select parent(s)
# parent = 'single' # parent selection method: 'single' or 'weighted'
# x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
# n = min(5, len(x)) # number of previous results to consider
# x = x[np.argsort(-fitness(x))][:n] # top n mutations
# w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0)
# if parent == 'single' or len(x) == 1:
# # x = x[random.randint(0, n - 1)] # random selection
# x = x[random.choices(range(n), weights=w)[0]] # weighted selection
# elif parent == 'weighted':
# x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
#
# # Mutate
# mp, s = 0.8, 0.2 # mutation probability, sigma
# npr = np.random
# npr.seed(int(time.time()))
# g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1
# ng = len(meta)
# v = np.ones(ng)
# while all(v == 1): # mutate until a change occurs (prevent duplicates)
# v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
# for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300)
# hyp[k] = float(x[i + 7] * v[i]) # mutate
# del i, k
#
# # Constrain to limits
# for k, v in meta.items():
# hyp[k] = max(hyp[k], v[1]) # lower limit
# hyp[k] = min(hyp[k], v[2]) # upper limit
# hyp[k] = round(hyp[k], 5) # significant digits
# del k, v
# # Train mutation
# results = train(hyp.copy(), opt, device, callbacks)
#
# # Write mutation results
# print_mutation(results, hyp.copy(), save_dir, opt.bucket)
#
# # Plot results
# plot_evolve(evolve_csv)
# print(f'Hyperparameter evolution finished\n'
# f"Results saved to {colorstr('bold', save_dir)}\n"
# f'Use best hyperparameters example: $ python train.py --hyp {evolve_yaml}')
#
#
# def objective(trial):
# opt = parse_opt()
# device = torch.device('cuda', LOCAL_RANK)
# save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze, = \
# Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
# opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze
# hyp = opt.hyp
#
# # # Generate the model.
# # Directories
# w = save_dir / 'weights' # weights dir
# (w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir
# last, best = w / 'last.pt', w / 'best.pt'
#
# # Hyperparameters
# if isinstance(hyp, str):
# with open(hyp, errors='ignore') as f:
# hyp = yaml.safe_load(f) # load hyps dict
# LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
#
# # Save run settings
# with open(save_dir / 'hyp.yaml', 'w') as f:
# yaml.safe_dump(hyp, f, sort_keys=False)
# with open(save_dir / 'opt.yaml', 'w') as f:
# yaml.safe_dump(vars(opt), f, sort_keys=False)
# data_dict = None
#
# # Loggers
# if RANK in [-1, 0]:
# loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
# if loggers.wandb:
# data_dict = loggers.wandb.data_dict
# # del resume
# if resume:
# # del weights
# weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp
#
# # Config
# plots = not evolve # create plots
# cuda = device.type != 'cpu'
# init_seeds(1 + RANK)
# with torch_distributed_zero_first(LOCAL_RANK):
# data_dict = data_dict or check_dataset(data) # check if None
# # del train_path,val_path,names,is_coco
# train_path, val_path = data_dict['train'], data_dict['val']
# nc = 1 if single_cls else int(data_dict['nc']) # number of classes
# names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
# assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}' # check
# is_coco = data.endswith('coco.yaml') and nc == 80 # COCO dataset
#
# # Model
# check_suffix(weights, '.pt') # check weights
# # del pretrained
# pretrained = weights.endswith('.pt') # 采用预训练
# if pretrained:
# with torch_distributed_zero_first(LOCAL_RANK):
# weights = attempt_download(weights) # download if not found locally
# ckpt = torch.load(weights, map_location=device) # load checkpoint
# # 创建模型
# model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
# exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys
# csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
# csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
# del exclude
# model.load_state_dict(csd, strict=False) # load
# LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report
# else:
# model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
#
# # # Generate the optimizers.
# # try Adam and SGD
# # optimizer_name = trial.suggest_categorical("optimizer", ["RMSprop", "SGD"])
# # momentum = trial.suggest_float("momentum", 0.0, 1.0)
# # lr = trial.suggest_float("lr", 1e-5, 1e-1, log=True)
# # optimizer = getattr(optim, optimizer_name)
# # (model.parameters(), lr=lr,momentum=momentum)
#
# # Resume
# # 初始化开始训练的epoch和最好的结果
# # best_fitness是以[0.0, 0.0, 0.1, 0.9]为系数并乘以[精确度, 召回率, mAP@0.5, mAP@0.5:0.95]再求和所得
# # 根据best_fitness来保存best.pt
# start_epoch, best_fitness = 0, 0.0
# if pretrained:
# # Epochs
# start_epoch = ckpt['epoch'] + 1
# if resume:
# assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.'
# if epochs < start_epoch:
# LOGGER.info(
# f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.")
# epochs += ckpt['epoch'] # finetune additional epochs
#
# # Image sizes
# gs = max(int(model.stride.max()), 32) # grid size (max stride)
# nl = model.model[-1].nl # number of detection layers (used for scaling hyp['obj'])
# imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple
#
# optimizer_name = trial.suggest_categorical("optimizer", ["Adam", "SGD"])
# lr = trial.suggest_float("lr", 1e-4, 1e-1, log=True)
# optimizer = getattr(optim, optimizer_name)
# # (model.parameters(), lr=lr)
# # batch_size=trial.suggest_int("batch_size", 64, 256,step=64)
# criterion = nn.CrossEntropyLoss()
#
# # Get the MNIST imagesset.
# train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls,
# hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=LOCAL_RANK,
# workers=workers, image_weights=opt.image_weights, quad=opt.quad,
#
# prefix=colorstr('train: '))
#
# # # Training of the model.
# mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max()) # max label class
# nb = len(train_loader) # number of batches
# assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
# del mlc
# # Process 0
# if RANK in [-1, 0]:
# val_loader = create_dataloader(val_path, imgsz, batch_size // WORLD_SIZE * 2, gs, single_cls,
# hyp=hyp, cache=None if noval else opt.cache, rect=True, rank=-1,
# workers=workers, pad=0.5,
# prefix=colorstr('val: '))[0]
#
# if not resume:
# # del labels
# labels = np.concatenate(dataset.labels, 0)
# # c = torch.tensor(labels[:, 0]) # classes
# # cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
# # model._initialize_biases(cf.to(device))
# if plots:
# plot_labels(labels, names, save_dir)
# del labels
# # Anchors
# if not opt.noautoanchor:
# check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
# model.half().float() # pre-reduce anchor precision
#
# callbacks.run('on_pretrain_routine_end')
#
# # Optimizer
# nbs = 64 # nominal batch size
# accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing
# hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay
# LOGGER.info(f"Scaled weight_decay = {hyp['weight_decay']}")
#
# # 将模型分成三组(weight、bn, bias, 其他所有参数)优化
# g0, g1, g2 = [], [], [] # optimizer parameter groups
# for v in model.modules():
# if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): # bias
# g2.append(v.bias)
# if isinstance(v, nn.BatchNorm2d): # weight (no decay)
# g0.append(v.weight)
# elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): # weight (with decay)
# g1.append(v.weight)
# del v
#
# # 选用优化器，并设置g0组的优化方式
# if opt.adam:
# optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum
# else:
# optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
# # 设置weight、bn的优化方式
# optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']}) # add g1 with weight_decay
# # 设置biases的优化方式
# optimizer.add_param_group({'params': g2}) # add g2 (biases)
# LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
# f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias")
# del g0, g1, g2
#
# # 设置学习率衰减，这里为余弦退火方式进行衰减
# # Scheduler
# if opt.linear_lr:
# lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
# else:
# lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
# scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
#
# # EMA
# ema = ModelEMA(model) if RANK in [-1, 0] else None
#
# # Model parameters
# hyp['box'] *= 3. / nl # scale to layers
# hyp['cls'] *= nc / 80. * 3. / nl # scale to classes and layers
# hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl # scale to image size and layers
# hyp['label_smoothing'] = opt.label_smoothing
# model.nc = nc # attach number of classes to model
# model.hyp = hyp # attach hyperparameters to model
# model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
# model.names = names
# del names, nl
# # Start training
# # del t0
# t0 = time.time()
# nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations)
# # nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
# last_opt_step = -1
# maps = np.zeros(nc) # mAP per class
# results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
# scheduler.last_epoch = start_epoch - 1 # do not move
# scaler = amp.GradScaler(enabled=cuda)
# stopper = EarlyStopping(patience=opt.patience)
# compute_loss = ComputeLoss(model) # init loss class
# LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
# f'Using {train_loader.num_workers} dataloader workers\n'
# f"Logging results to {colorstr('bold', save_dir)}\n"
# f'Starting training for {epochs} epochs...')
#
# for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
# model.train()
#
# # Update image weights (optional, single-GPU only)
# if opt.image_weights:
# cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights
# iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights
# dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx
# del cw
# del iw
# # Update mosaic border (optional)
# # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
# # dataset.mosaic_border = [b - imgsz, -b] # height, width borders
#
# mloss = torch.zeros(3, device=device) # mean losses
# if RANK != -1:
# train_loader.sampler.set_epoch(epoch)
# pbar = enumerate(train_loader)
# LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
# if RANK in [-1, 0]:
# pbar = tqdm(pbar, total=nb) # progress bar 进度条
# optimizer.zero_grad()
#
# for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
# # del ni
# ni = i + nb * epoch # number integrated batches (since train start)
# imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
#
# # Warmup 热身训练（前nw次迭代）
# if ni <= nw:
# # del xi
# xi = [0, nw] # x interp
# # compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
# accumulate = max(1, np.interp(ni, xi, [1, 64 / batch_size]).round())
# for j, x in enumerate(optimizer.param_groups):
# # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
# x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
# if 'momentum' in x:
# x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
# del j, x
# # Multi-scale
# # 设置多尺度训练，从imgsz * 0.5, imgsz * 1.5 + gs随机选取尺寸
# if opt.multi_scale:
# # del sz
# sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size
# sf = sz / max(imgs.shape[2:]) # scale factor
# if sf != 1:
# ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
# imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
# del sz, sf
# # Forward
# with amp.autocast(enabled=cuda):
# # del pred, loss, loss_items
# pred = model(imgs) # forward 前向传播
# loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
# if RANK != -1:
# loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
# if opt.quad:
# loss *= 4.
# # Backward
# scaler.scale(loss).backward()
# # Optimize
# if ni - last_opt_step >= accumulate:
# scaler.step(optimizer) # optimizer.step
# scaler.update()
# optimizer.zero_grad()
# if ema:
# ema.update(model)
# last_opt_step = ni
# # Log
# if RANK in [-1, 0]:
# mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
# # del mem
# mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
# pbar.set_description(('%10s' * 2 + '%10.4g' * 5) % (
# f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
# callbacks.run('on_train_batch_end', ni, model, imgs, targets, paths, plots, opt.sync_bn)
# del mem
# del loss_items
# # end batch ------------------------------------------------------------------------------------------------
# if RANK in [-1, 0]:
# LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
# for f in last, best:
# if f.exists():
# strip_optimizer(f) # strip optimizers
# if f is best:
# LOGGER.info(f'\nValidating {f}...')
# results, _, _ = val.run(data_dict,
# batch_size=batch_size // WORLD_SIZE * 2,
# imgsz=imgsz,
# model=attempt_load(f, device).half(),
# iou_thres=0.65 if is_coco else 0.60, # best pycocotools results at 0.65
# single_cls=single_cls,
# dataloader=val_loader,
# save_dir=save_dir,
# save_json=is_coco,
# verbose=True,
# plots=True,
# callbacks=callbacks,
# compute_loss=compute_loss) # val best model with plots
# del f
# del data_dict
# del is_coco
# callbacks.run('on_train_end', last, best, plots, epoch)
# LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
# del plots
# del t0
# return results
# if __name__ == "__main__":
# study = optuna.create_study(direction='maximize')
# study.optimize(objective, n_trials=100)
# trial = study.best_trialprint('Accuracy: {}'.format(trial.value))
# print("Best hyperparameters: {}".format(trial.params))