def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args() # args通过解析获得的
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global') # 实例化一个记录器
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(
cfg, indent=4))) # 转变成json格式的文件，缩进4格
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True, anchors=cfg['anchors'])
else:
exit()
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda() # 模型转移到GPU上
dist_model = torch.nn.DataParallel(
model, list(range(torch.cuda.device_count()))).cuda() # 多GPU训练
if args.resume and args.start_epoch != 0: # 这是在干啥？蒙蔽了！！！！！
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args,
args.start_epoch) # 如何构建优化器和学习策略？？？
# optionally resume from a checkpoint
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(
model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(
model, list(range(torch.cuda.device_count()))).cuda()
logger.info(lr_scheduler)
logger.info('model prepare done')
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch,
cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
init_log('global', logging.INFO) # 返回一个logger对象,logging_INFO是日志的等级
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global') # 获取上面初始化的logger对象
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args) # 返回修改后的配置文件对象
logger.info("config \n{}".format(json.dumps(cfg, indent=4))) #json.loads()是将str转化成dict格式，json.dumps()是将dict转化成str格式。
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True, anchors=cfg['anchors'])
else:
exit()
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda()
dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
# optionally resume from a checkpoint
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
logger.info(lr_scheduler)
logger.info('model prepare done')
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch, cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
if args.arch == 'Custom':
model = Custom(anchors=cfg['anchors'])
elif args.arch == 'Custom_Sky':
model = Custom_Sky(anchors=cfg['anchors'])
else:
exit()
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
# print(summary(model=model, input_size=(3, 511, 511), batch_size=1))
model = model.cuda()
dist_model = torch.nn.DataParallel(model,
list(range(
torch.cuda.device_count()))).cuda()
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
# optionally resume from a checkpoint
if args.resume:
print(args.resume)
assert os.path.isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(
model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(
model, list(range(torch.cuda.device_count()))).cuda()
logger.info(lr_scheduler)
logger.info('model prepare done')
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch,
cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
logger.info("\n" + collect_env_info())
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True, anchors=cfg['anchors'])
else:
model = models.__dict__[args.arch](anchors=cfg['anchors'])
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda()
dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
logger.info(lr_scheduler)
# optionally resume from a checkpoint
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
epoch = args.start_epoch
if dist_model.module.features.unfix(epoch/args.epochs):
logger.info('unfix part model.')
optimizer, lr_scheduler = build_opt_lr(dist_model.module, cfg, args, epoch)
lr_scheduler.step(epoch)
cur_lr = lr_scheduler.get_cur_lr()
logger.info('epoch:{} resume lr {}'.format(epoch, cur_lr))
logger.info('model prepare done')
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch, cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
args = args_process(args)
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
args.img_size = int(cfg['train_datasets']['search_size'])
args.nms_threshold = float(cfg['train_datasets']['RPN_NMS'])
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True,
opts=args,
anchors=train_loader.dataset.anchors)
else:
exit()
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda()
dist_model = torch.nn.DataParallel(model,
list(range(
torch.cuda.device_count()))).cuda()
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
# optionally resume from a checkpoint
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(
model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(
model, list(range(torch.cuda.device_count()))).cuda()
logger.info(lr_scheduler)
logger.info('model prepare done')
global cur_lr
if not os.path.exists(args.save_dir): # makedir/save model
os.makedirs(args.save_dir)
num_per_epoch = len(train_loader.dataset) // args.batch
num_per_epoch_val = len(val_loader.dataset) // args.batch
for epoch in range(args.start_epoch, args.epochs):
lr_scheduler.step(epoch)
cur_lr = lr_scheduler.get_cur_lr()
logger = logging.getLogger('global')
train_avg = AverageMeter()
val_avg = AverageMeter()
if dist_model.module.features.unfix(epoch / args.epochs):
logger.info('unfix part model.')
optimizer, lr_scheduler = build_opt_lr(dist_model.module, cfg,
args, epoch)
train(train_loader, dist_model, optimizer, lr_scheduler, epoch, cfg,
train_avg, num_per_epoch)
if dist_model.module.features.unfix(epoch / args.epochs):
logger.info('unfix part model.')
optimizer, lr_scheduler = build_opt_lr(dist_model.module, cfg,
args, epoch)
if (epoch + 1) % args.save_freq == 0:
save_checkpoint(
{
'epoch': epoch,
'arch': args.arch,
'state_dict': dist_model.module.state_dict(),
'best_acc': best_acc,
'optimizer': optimizer.state_dict(),
'anchor_cfg': cfg['anchors']
}, False,
os.path.join(args.save_dir, 'checkpoint_e%d.pth' % (epoch)),
os.path.join(args.save_dir, 'best.pth'))
validation(val_loader, dist_model, epoch, cfg, val_avg,
num_per_epoch_val)
def main():
"""
基础网络的训练
:return:
"""
global args, best_acc, tb_writer, logger
args = parser.parse_args()
# 初始化日志信息
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
# 获取log信息
logger = logging.getLogger('global')
logger.info("\n" + collect_env_info())
logger.info(args)
# 获取配置信息
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# 构建数据集
train_loader, val_loader = build_data_loader(cfg)
# 加载训练网络
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True, anchors=cfg['anchors'])
else:
exit()
logger.info(model)
# 加载预训练网络
if args.pretrained:
model = load_pretrain(model, args.pretrained)
# GPU版本
# model = model.cuda()
# dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
# 网络模型
dist_model = torch.nn.DataParallel(model)
# 模型参数的更新比例
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
# 获取优化器和学习率的更新策略
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
# optionally resume from a checkpoint 加载模型
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(
model, optimizer, args.resume)
# GPU
# dist_model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
dist_model = torch.nn.DataParallel(model)
logger.info(lr_scheduler)
logger.info('model prepare done')
# 模型训练
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch,
cfg)
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
print("Init logger")
logger = logging.getLogger('global')
print(44)
#logger.info("\n" + collect_env_info())
print(99)
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
print(2)
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
print(3)
path = "/usr4/alg504/cliao25/siammask/experiments/siammask_base/snapshot/checkpoint_e{}.pth"
for epoch in range(1,21):
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True, anchors=cfg['anchors'])
else:
exit()
print(4)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda()
#model.features.unfix((epoch - 1) / 20)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, epoch)
filepath = path.format(epoch)
assert os.path.isfile(filepath)
model, _, _, _, _ = restore_from(model, optimizer, filepath)
#model = load_pretrain(model, filepath)
model = torch.nn.DataParallel(model, list(range(torch.cuda.device_count()))).cuda()
model.train()
device = torch.device('cuda')
model = model.to(device)
valid(val_loader, model, cfg)
print("Done")
def main():
global args, best_acc, tb_writer, logger
args = parser.parse_args()
args = args_process(args)
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info("\n" + collect_env_info())
logger.info(args)
cfg = load_config(args)
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
if args.log_dir:
tb_writer = SummaryWriter(args.log_dir)
else:
tb_writer = Dummy()
# build dataset
train_loader, val_loader = build_data_loader(cfg)
args.img_size = int(cfg['train_datasets']['search_size'])
args.nms_threshold = float(cfg['train_datasets']['RPN_NMS'])
if args.arch == 'Custom':
from custom import Custom
model = Custom(pretrain=True,
opts=args,
anchors=train_loader.dataset.anchors)
else:
exit()
logger.info(model)
if args.pretrained:
model = load_pretrain(model, args.pretrained)
model = model.cuda()
dist_model = torch.nn.DataParallel(model,
list(range(
torch.cuda.device_count()))).cuda()
if args.resume and args.start_epoch != 0:
model.features.unfix((args.start_epoch - 1) / args.epochs)
optimizer, lr_scheduler = build_opt_lr(model, cfg, args, args.start_epoch)
# optionally resume from a checkpoint
if args.resume:
assert os.path.isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model, optimizer, args.start_epoch, best_acc, arch = restore_from(
model, optimizer, args.resume)
dist_model = torch.nn.DataParallel(
model, list(range(torch.cuda.device_count()))).cuda()
logger.info(lr_scheduler)
logger.info('model prepare done')
train(train_loader, dist_model, optimizer, lr_scheduler, args.start_epoch,
cfg)