-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathtrain.py
195 lines (166 loc) · 8.3 KB
/
train.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
import datetime
import logging
import math
import time
from os import path as osp
from data.realesrgan_dataset import RealESRGANDataset
from data.realesrgan_paired_dataset import RealESRGANPairedDataset
import paddle
from tqdm import tqdm
from data.dataset import build_dataloader#, build_dataset
from data.data_sampler import EnlargedSampler
from models.build_model import build_model
from utils.logger import get_root_logger, MessageLogger, AvgTimer
from utils.options import copy_opt_file, dict2str, parse_options
from utils.scandir import scandir
from utils.misc import check_resume, make_exp_dirs, mkdir_and_rename, get_time_str
# def init_tb_loggers(opt):
# tb_logger = None
# if opt['logger'].get('use_tb_logger') and 'debug' not in opt['name']:
# tb_logger = init_tb_logger(log_dir=osp.join(opt['root_path'], 'tb_logger', opt['name']))
# return tb_logger
def create_train_val_dataloader(opt, logger):
# create train and val dataloaders
train_loader, val_loaders = None, []
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
dataset_enlarge_ratio = dataset_opt.get('dataset_enlarge_ratio', 1)
# train_set = build_dataset(dataset_opt)
train_set = RealESRGANDataset(dataset_opt)
train_sampler = EnlargedSampler(train_set, opt['world_size'], opt['rank'], dataset_enlarge_ratio)
train_loader = build_dataloader(train_set,
dataset_opt,
num_gpu=opt['num_gpu'],
dist=False,
sampler=train_sampler,
seed=opt['manual_seed'])
num_iter_per_epoch = math.ceil(
len(train_set) * dataset_enlarge_ratio / (dataset_opt['batch_size_per_gpu'] * opt['world_size']))
total_iters = int(opt['train']['total_iter'])
total_epochs = math.ceil(total_iters / (num_iter_per_epoch))
logger.info('Training statistics:'
f'\n\tNumber of train images: {len(train_set)}'
f'\n\tDataset enlarge ratio: {dataset_enlarge_ratio}'
f'\n\tBatch size per gpu: {dataset_opt["batch_size_per_gpu"]}'
f'\n\tWorld size (gpu number): {opt["world_size"]}'
f'\n\tRequire iter number per epoch: {num_iter_per_epoch}'
f'\n\tTotal epochs: {total_epochs}; iters: {total_iters}.')
elif phase.split('_')[0] == 'val':
val_set = RealESRGANPairedDataset(dataset_opt, istrain=False)
val_loader = build_dataloader(
val_set, dataset_opt, num_gpu=opt['num_gpu'], dist=opt['dist'], sampler=None, seed=opt['manual_seed'])
logger.info(f'Number of val images/folders in {dataset_opt["name"]}: {len(val_set)}')
val_loaders.append(val_loader)
else:
raise ValueError(f'Dataset phase {phase} is not recognized.')
return train_loader, train_sampler, val_loaders, total_epochs, total_iters
def load_resume_state(opt):
resume_state_path = None
if opt['auto_resume']:
state_path = osp.join('experiments', opt['name'], 'training_states')
if osp.isdir(state_path):
states = list(scandir(state_path, suffix='state', recursive=False, full_path=False))
if len(states) != 0:
states = [float(v.split('.state')[0]) for v in states]
resume_state_path = osp.join(state_path, f'{max(states):.0f}.state')
opt['path']['resume_state'] = resume_state_path
else:
if opt['path'].get('resume_state'):
resume_state_path = opt['path']['resume_state']
if resume_state_path is None:
resume_state = None
else:
resume_state = paddle.load(resume_state_path)
check_resume(opt, resume_state['iter'])
return resume_state
def train_pipeline(root_path, ymlpath):
# parse options, set distributed setting, set ramdom seed
opt, args = parse_options(root_path,ymlpath, is_train=True)
opt['root_path'] = root_path
# load resume states if necessary
resume_state = load_resume_state(opt)
# mkdir for experiments and logger
if resume_state is None:
make_exp_dirs(opt)
if opt['logger'].get('use_tb_logger') and 'debug' not in opt['name'] and opt['rank'] == 0:
mkdir_and_rename(osp.join(opt['root_path'], 'tb_logger', opt['name']))
# copy the yml file to the experiment root
copy_opt_file(args.opt, opt['path']['experiments_root'])
# WARNING: should not use get_root_logger in the above codes, including the called functions
# Otherwise the logger will not be properly initialized
log_file = osp.join(opt['path']['log'], f"train_{opt['name']}_{get_time_str()}.log")
logger = get_root_logger(logger_name='basicsr', log_level=logging.INFO, log_file=log_file)
logger.info(dict2str(opt))
# tb_logger = init_tb_loggers(opt)
# create train and validation dataloaders
result = create_train_val_dataloader(opt, logger)
train_loader, train_sampler, val_loaders, total_epochs, total_iters = result
# create model
model = build_model(opt)
if resume_state: # resume training
model.resume_training(resume_state) # handle optimizers and schedulers
logger.info(f"Resuming training from epoch: {resume_state['epoch']}, " f"iter: {resume_state['iter']}.")
start_epoch = resume_state['epoch']
current_iter = resume_state['iter']
else:
start_epoch = 0
current_iter = 0
# create message logger (formatted outputs)
msg_logger = MessageLogger(opt, current_iter)
# training
logger.info(f'Start training from epoch: {start_epoch}, iter: {current_iter}')
data_timer, iter_timer = AvgTimer(), AvgTimer()
start_time = time.time()
for epoch in range(start_epoch, total_epochs + 1):
train_sampler.set_epoch(epoch)
# while train_data is not None:
for _, (train_data) in tqdm(enumerate(train_loader), total=len(train_loader)):
# print(i)
data_timer.record()
current_iter += 1
if current_iter > total_iters:
break
# update learning rate
model.update_learning_rate(current_iter, warmup_iter=opt['train'].get('warmup_iter', -1))
# training
model.feed_data(train_data)
model.optimize_parameters(current_iter)
iter_timer.record()
if current_iter == 1:
# reset start time in msg_logger for more accurate eta_time
# not work in resume mode
msg_logger.reset_start_time()
# log
if current_iter % opt['logger']['print_freq'] == 0:
log_vars = {'epoch': epoch, 'iter': current_iter}
log_vars.update({'lrs': model.get_current_learning_rate()})
log_vars.update({'time': iter_timer.get_avg_time(), 'data_time': data_timer.get_avg_time()})
log_vars.update(model.get_current_log())
msg_logger(log_vars)
# save models and training states
if current_iter % opt['logger']['save_checkpoint_freq'] == 0:
logger.info('Saving models and training states.')
model.save(epoch, current_iter)
# validation
if opt.get('val') is not None and (current_iter % opt['val']['val_freq'] == 0):
if len(val_loaders) > 1:
logger.warning('Multiple validation datasets are *only* supported by SRModel.')
for val_loader in val_loaders:
model.validation(val_loader, current_iter, opt['val']['save_img'])
data_timer.start()
iter_timer.start()
# end of iter
# end of epoch
consumed_time = str(datetime.timedelta(seconds=int(time.time() - start_time)))
logger.info(f'End of training. Time consumed: {consumed_time}')
logger.info('Save the latest model.')
model.save(epoch=-1, current_iter=-1) # -1 stands for the latest
if opt.get('val') is not None:
for val_loader in val_loaders:
model.validation(val_loader, current_iter, opt['val']['save_img'])
# if tb_logger:
# tb_logger.close()
if __name__ == '__main__':
ymlpath = '/options/train_realesrgan_x4plus.yml'
root_path = '/Real_ESRGAN_paddle'
train_pipeline(root_path, ymlpath)