def main(opt):
torch.manual_seed(opt.seed)
torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
# torch.backends.cudnn.enabled = False
Dataset = get_dataset(opt.dataset, opt.task)
opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
print(opt)
logger = Logger(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')
print('Creating model...')
model = create_model(opt.arch, opt.heads, opt.head_conv, opt.houghnet,
opt.region_num, opt.vote_field_size)
optimizer = torch.optim.Adam(model.parameters(), opt.lr)
start_epoch = 0
if opt.load_model != '':
model, optimizer, start_epoch = load_model(model, opt.load_model,
optimizer, opt.resume,
opt.lr, opt.lr_step)
Trainer = train_factory[opt.task]
trainer = Trainer(opt, model, optimizer)
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
print('Setting up data...')
val_loader = torch.utils.data.DataLoader(Dataset(opt, 'val'),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True)
if opt.test:
_, preds = trainer.val(0, val_loader)
val_loader.dataset.run_eval(preds, opt.save_dir)
return
train_loader = torch.utils.data.DataLoader(
Dataset(opt, 'train'), #train
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True)
print('Starting training...')
best = 1e10
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else 'last'
log_dict_train, _ = trainer.train(epoch, train_loader)
logger.write('epoch: {} |'.format(epoch))
for k, v in log_dict_train.items():
logger.scalar_summary('train_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
epoch, model, optimizer)
with torch.no_grad():
log_dict_val, preds = trainer.val(epoch, val_loader)
for k, v in log_dict_val.items():
logger.scalar_summary('val_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if log_dict_val[opt.metric] < best:
best = log_dict_val[opt.metric]
save_model(os.path.join(opt.save_dir, 'model_best.pth'), epoch,
model)
else:
save_model(os.path.join(opt.save_dir, 'model_last.pth'), epoch,
model, optimizer)
logger.write('\n')
if epoch in opt.lr_step:
save_model(
os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
epoch, model, optimizer)
lr = opt.lr * (0.1**(opt.lr_step.index(epoch) + 1))
print('Drop LR to', lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
logger.close()
def main(opt):
torch.manual_seed(opt.seed)
torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
print('Setting up data...')
Dataset = get_dataset(opt.dataset, opt.task)
f = open(opt.data_cfg)
data_config = json.load(f)
trainset_paths = data_config['train']
dataset_root = data_config['root']
f.close()
transforms = T.Compose([T.ToTensor()])
dataset = Dataset(opt,
dataset_root,
trainset_paths, (1088, 608),
augment=True,
transforms=transforms)
opt = opts().update_dataset_info_and_set_heads(opt, dataset)
print(opt)
logger = Logger(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')
print('Creating model...')
model = create_model(opt.arch, opt.heads, opt.head_conv)
optimizer = torch.optim.Adam(model.parameters(), opt.lr)
start_epoch = 0
# Get dataloader
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True)
print('Starting training...')
Trainer = train_factory[opt.task]
trainer = Trainer(opt, model, optimizer)
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
if opt.load_model != '':
model, optimizer, start_epoch = load_model(model, opt.load_model,
trainer.optimizer,
opt.resume, opt.lr,
opt.lr_step)
best = 1e10
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else 'last'
log_dict_train, _ = trainer.train(epoch, train_loader)
logger.write('epoch: {} |'.format(epoch))
for k, v in log_dict_train.items():
logger.scalar_summary('train_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
epoch, model, optimizer)
else:
save_model(os.path.join(opt.save_dir, 'model_last.pth'), epoch,
model, optimizer)
logger.write('\n')
if epoch in opt.lr_step:
save_model(
os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
epoch, model, optimizer)
lr = opt.lr * (0.1**(opt.lr_step.index(epoch) + 1))
print('Drop LR to', lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
if epoch % 5 == 0 or epoch >= 25:
save_model(
os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
epoch, model, optimizer)
logger.close()
def main(opt):
torch.manual_seed(
opt.seed
) # opt.seed: default=317 ；加上torch.manual_seed这个函数调用的话，打印出来的随机数每次都一样。
torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
Dataset = get_dataset(
opt.dataset, opt.task
) # opt.dataset = coco, opt.task = ctdet (| ddd | multi_pose | exdet)
opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
print(opt)
logger = Logger(opt)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')
print('Creating model...')
model = create_model(opt.arch, opt.heads, opt.head_conv)
optimizer = torch.optim.Adam(model.parameters(), opt.lr)
start_epoch = 0
if opt.load_model != '':
model, optimizer, start_epoch = load_model(model, opt.load_model,
optimizer, opt.resume,
opt.lr, opt.lr_step)
Trainer = train_factory[opt.task]
trainer = Trainer(opt, model, optimizer)
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
print('Setting up data...')
# val_loader = torch.utils.data.DataLoader(Dataset(opt, 'val'), batch_size=1, shuffle=False, num_workers=1,pin_memory=True) # modified by zy
val_loader = torch.utils.data.DataLoader(Dataset(opt, 'test'),
batch_size=1,
shuffle=False,
num_workers=1,
pin_memory=True)
if opt.test:
_, preds = trainer.val(0, val_loader)
val_loader.dataset.run_eval(preds, opt.save_dir)
return
train_loader = torch.utils.data.DataLoader(Dataset(opt, 'train'),
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True)
output_choice_log = '/home/zy/zy/2new_network/CenterNet-master/output_choice.log'
if os.path.exists(output_choice_log):
os.remove(output_choice_log)
print('Starting training...')
best = 1e10
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else 'last'
try:
log_dict_train, _ = trainer.train(
epoch, train_loader
) # !!!!!!!! train = self.run_epoch('train', epoch, data_loader)
except Exception as e: # 如果发生异常，那就返回预设的loss值
print('Error_train!!!', e)
print(traceback.format_exc())
continue
logger.write('epoch: {} |'.format(epoch))
for k, v in log_dict_train.items():
logger.scalar_summary('train_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
epoch, model, optimizer)
with torch.no_grad():
try:
log_dict_val, preds = trainer.val(epoch, val_loader)
except Exception as e: # 如果发生异常，那就返回预设的loss值
print('Error_train!!!', e)
print(traceback.format_exc())
continue
for k, v in log_dict_val.items():
logger.scalar_summary('val_{}'.format(k), v, epoch)
logger.write('{} {:8f} | '.format(k, v))
if log_dict_val[opt.metric] < best:
best = log_dict_val[opt.metric]
save_model(os.path.join(opt.save_dir, 'model_best.pth'), epoch,
model)
else:
save_model(os.path.join(opt.save_dir, 'model_last.pth'), epoch,
model, optimizer)
logger.write('\n')
if epoch in opt.lr_step:
save_model(
os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
epoch, model, optimizer)
lr = opt.lr * (0.1**(opt.lr_step.index(epoch) + 1))
print('Drop LR to', lr)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
logger.close()
def main(opt):
torch.manual_seed(opt.seed)
torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
Dataset = get_dataset(opt.dataset)
opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
print(opt)
if not opt.not_set_cuda_env:
os.environ["CUDA_VISIBLE_DEVICES"] = opt.gpus_str
opt.device = torch.device("cuda" if opt.gpus[0] >= 0 else "cpu")
logger = Logger(opt)
print("Creating model...")
model = create_model(opt.arch, opt.heads, opt.head_conv, opt=opt)
optimizer = get_optimizer(opt, model)
start_epoch = 0
if opt.load_model != "":
model, optimizer, start_epoch = load_model(model, opt.load_model, opt, optimizer)
trainer = Trainer(opt, model, optimizer)
trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)
if opt.val_intervals < opt.num_epochs or opt.test:
print("Setting up validation data...")
val_loader = torch.utils.data.DataLoader(
Dataset(opt, "val"), batch_size=1, shuffle=False, num_workers=1, pin_memory=True
)
if opt.test:
_, preds = trainer.val(0, val_loader)
val_loader.dataset.run_eval(preds, opt.save_dir)
return
print("Setting up train data...")
train_loader = torch.utils.data.DataLoader(
Dataset(opt, "train"),
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
pin_memory=True,
drop_last=True,
)
print("Starting training...")
for epoch in range(start_epoch + 1, opt.num_epochs + 1):
mark = epoch if opt.save_all else "last"
log_dict_train, _ = trainer.train(epoch, train_loader)
logger.write("epoch: {} |".format(epoch))
for k, v in log_dict_train.items():
logger.scalar_summary("train_{}".format(k), v, epoch)
logger.write("{} {:8f} | ".format(k, v))
if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
save_model(os.path.join(opt.save_dir, "model_{}.pth".format(mark)), epoch, model, optimizer)
with torch.no_grad():
log_dict_val, preds = trainer.val(epoch, val_loader)
if opt.eval_val:
val_loader.dataset.run_eval(preds, opt.save_dir)
for k, v in log_dict_val.items():
logger.scalar_summary("val_{}".format(k), v, epoch)
logger.write("{} {:8f} | ".format(k, v))
else:
save_model(os.path.join(opt.save_dir, "model_last.pth"), epoch, model, optimizer)
logger.write("\n")
if epoch in opt.save_point:
save_model(os.path.join(opt.save_dir, "model_{}.pth".format(epoch)), epoch, model, optimizer)
if epoch in opt.lr_step:
lr = opt.lr * (0.1 ** (opt.lr_step.index(epoch) + 1))
print("Drop LR to", lr)
for param_group in optimizer.param_groups:
param_group["lr"] = lr
logger.close()