def main(args):
# Create dir
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
student_n = [
set_policy(env, log, args, name="student", i_agent=i_agent)
for i_agent in range(args.n_student)
]
# Start train
train(student_n=student_n,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
if not os.path.exists("./saved_model"):
os.makedirs("./saved_model")
def main():
args = get_arguments()
SEED = args.seed
torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(SEED)
if (args.cuda):
torch.cuda.manual_seed(SEED)
if args.new_training:
model, optimizer, training_generator, val_generator, class_weight, Last_epoch = initialize_from_saved_model(args)
else:
model, optimizer, training_generator, val_generator, class_weight = initialize(args)
Last_epoch = 0
#print(model)
best_pred_loss = 0#lo cambie por balanced accuracy
scheduler = ReduceLROnPlateau(optimizer, factor=0.5, patience=3, min_lr=1e-5, verbose=True)
print('Checkpoint folder ', args.save)
# writer = SummaryWriter(log_dir='../runs/' + args.model, comment=args.model)
for epoch in range(1, args.nEpochs + 1):
train(args, model, training_generator, optimizer, Last_epoch+epoch, class_weight)
val_metrics, confusion_matrix = validation(args, model, val_generator, Last_epoch+epoch, class_weight)
BACC = BalancedAccuray(confusion_matrix.numpy())
val_metrics.replace({'bacc': BACC})
best_pred_loss = util.save_model(model, optimizer, args, val_metrics, Last_epoch+epoch, best_pred_loss, confusion_matrix)
print(confusion_matrix)
scheduler.step(val_metrics.avg_loss())
def main():
args = get_arguments()
SEED = args.seed
torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(SEED)
if (args.cuda):
torch.cuda.manual_seed(SEED)
model, optimizer, training_generator, val_generator, test_generator = initialize(
args)
print(model)
best_pred_loss = 1000.0
scheduler = ReduceLROnPlateau(optimizer,
factor=0.5,
patience=2,
min_lr=1e-5,
verbose=True)
print('Checkpoint folder ', args.save)
if args.tensorboard:
writer = SummaryWriter('./runs/' + util.datestr())
else:
writer = None
for epoch in range(1, args.nEpochs + 1):
train(args, model, training_generator, optimizer, epoch, writer)
val_metrics, confusion_matrix = validation(args, model, val_generator,
epoch, writer)
best_pred_loss = util.save_model(model, optimizer, args, val_metrics,
epoch, best_pred_loss,
confusion_matrix)
scheduler.step(val_metrics.avg_loss())
def main(args):
if args.central_train is True:
raise NotImplementedError("todo")
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
agents = [
set_policy(env, tb_writer, log, args, name="agent", i_agent=i_agent)
for i_agent in range(args.n_agent)
]
# Start train
train(agents=agents, env=env, log=log, tb_writer=tb_writer, args=args)
def objective(trial):
info = nvmlDeviceGetMemoryInfo(handle)
print("Total memory:", info.total)
print("Free memory:", info.free)
print("Used memory:", info.used)
model, training_generator, val_generator, test_generator = initialize(ARGS)
optim_name = trial.suggest_categorical("optimizer",
["Adam", "RMSprop", "SGD"])
weight_decay = trial.suggest_float("weight_decay", 1e-5, 1e-1, log=True)
lr = trial.suggest_float("learning_rate", 1e-7, 1e-5, log=True)
trial.set_user_attr("worker_id", WORKER_ID)
optimizer = util.select_optimizer(optim_name, model, lr, weight_decay)
scheduler = ReduceLROnPlateau(optimizer,
factor=0.5,
patience=2,
min_lr=1e-5,
verbose=True)
best_pred_loss = 1000.0
for epoch in range(1, EPOCHS + 1):
train(ARGS, model, training_generator, optimizer, epoch)
val_metrics, confusion_matrix = validation(ARGS, model, val_generator,
epoch)
scheduler.step(val_metrics._data.average.loss)
return val_metrics._data.average.recall_mean
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logging
log = set_log(args)
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
# Create env
env = make_env(args)
# Set seeds 0 seed is odd
env.seed(args.seed)
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
# Initialize policy
agent = set_policy(env, args.n_hidden, tb_writer, log, args)
# load agent
if args.mode == "test":
agent.load_weight("pytorch_models/", args.test_model)
test(agent=agent, env=env, log=log, tb_writer=tb_writer, args=args)
else:
train(agent=agent,
env=env,
log=log,
tb_writer=tb_writer,
num_samples=args.num_samples,
args=args)
def main(args):
try:
config = init_configs(flags=FLAGS)
if config.type == 'train':
train(config)
pass
elif config.type == 'predict':
pass
except ValueError as e:
print('Run is finished. Reason:')
print(e)
exit()
except Exception as e:
print('Run is finished. Reason:')
print(e)
exit()
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
# Note that only one teacher is considered in the one box push domain
# to transfer knowledge from agent $i$ to agent $k$ (Section 6.1)
workers = [
set_policy(env, tb_writer, log, args, name="worker", i_agent=i_agent)
for i_agent in range(args.n_worker)]
managers = [
set_policy(env, tb_writer, log, args, name="manager", i_agent=i_agent)
for i_agent in range(args.n_manager)]
temp_managers = [
set_policy(env, tb_writer, log, args, name="temp_manager", i_agent=i_agent)
for i_agent in range(args.n_manager)]
teacher = set_policy(env, tb_writer, log, args, name="teacher", i_agent=0)
assert len(workers) == len(managers), "The two number must be same"
assert len(managers) == len(temp_managers), "The two number must be same"
# Start train
train(
workers=workers, managers=managers,
temp_managers=temp_managers, teacher=teacher,
env=env, log=log, tb_writer=tb_writer, args=args)
def main(args):
# Create dir
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
predator_agents = [
set_policy(env, tb_writer, log, args, name="predator", i_agent=i_agent)
for i_agent in range(args.n_predator)
]
prey_agents = [
set_policy(env, tb_writer, log, args, name="prey", i_agent=i_agent)
for i_agent in range(args.n_prey)
]
# Start training
train(predator_agents=predator_agents,
prey_agents=prey_agents,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
agent = set_policy(env, tb_writer, log, args, name="agent")
# Start train
train(agent=agent, env=env, log=log, tb_writer=tb_writer, args=args)
path = Path.cwd().absolute() / 'data' / dataset_name
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
transform = T.Compose([
T.RandomTranslate(0.01),
T.RandomRotate(15, axis=0),
T.RandomRotate(15, axis=1),
T.RandomRotate(15, axis=2)
])
pre_transform = T.NormalizeScale()
train_dataset, test_dataset = load_dataset(path,
transform,
pre_transform,
category=category)
train_loader, test_loader = load_dataloader(train_dataset, test_dataset)
model = eval(model_name)(train_dataset.num_classes, k=30).to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=20,
gamma=0.8)
writer = SummaryWriter()
pbar = trange(1, 31, desc='Epoch', unit='epoch')
for epoch in pbar:
train(train_loader, model, optimizer, scheduler, epoch, device, writer)
iou = test(test_loader, model, device)
pbar.set_postfix_str(f'test_IoU={iou}')
def main(_):
train.train(FLAGS)
def main():
# Training settings
parser = argparse.ArgumentParser(description='Image Classification')
parser.add_argument('--batch-size',
type=int,
default=64,
metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--epochs',
type=int,
default=10,
metavar='N',
help='number of epochs to train (default: 20)')
parser.add_argument('--lr',
type=float,
default=1e-5,
metavar='LR',
help='learning rate (default: 1.0)')
parser.add_argument('--gamma',
type=float,
default=0.1,
metavar='M',
help='Learning rate step gamma (default: 0.1)')
parser.add_argument('--seed',
type=int,
default=123,
metavar='S',
help='random seed (default: 1)')
parser.add_argument('--save-model',
action='store_true',
default=True,
help='For Saving the current Model')
parser.add_argument('--retrain-base',
type=bool,
default=True,
help='whether retrain the base classifier')
parser.add_argument(
'--log-interval',
type=int,
default=4,
metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
torch.manual_seed(args.seed)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
kwargs = {'batch_size': args.batch_size, 'shuffle': True}
if torch.cuda.is_available():
kwargs.update({'num_workers': 1, 'pin_memory': True}, )
# load train/test data
train_set = HornetDataset()
test_set = HornetTestDataset()
train_loader = DataLoader(train_set, **kwargs)
test_loader = DataLoader(test_set, shuffle=False)
print("Finish loading training data.")
# imgshow(test_loader)
# train base model
if args.retrain_base:
model = models.alexnet(pretrained=True).to(device)
model.classifier[6] = nn.Linear(4096, 2).to(device)
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
# scheduler = ReduceLROnPlateau(optimizer)
for epoch in range(1, args.epochs + 1):
train(args.log_interval, model, device, train_loader, optimizer,
epoch)
# val_loss = test(model, device, test_loader)
# scheduler.step(val_loss)
torch.save(model.state_dict(), "saved/model/alex_hornet.pt")
print("Model saved.")
# load weights and do experiments
model = models.alexnet(pretrained=True).to(device)
model.classifier[6] = nn.Linear(4096, 2).to(device)
model.load_state_dict(torch.load("saved/model/alex_hornet.pt"))
model.eval()
print("Finish loading weights.")
# directly test on photos
print("Directly test on photos")
predict(model, device, test_loader, test_set)
import yaml
import os
from trainer.train import train
config = yaml.load(open('config.yml'))
os.environ["CUDA_VISIBLE_DEVICES"] = str(config[config['task']]['gpu'])
train(config)
if __name__ == "__main__":
""" 主函数，解析参数并启动 """
parser = argparse.ArgumentParser(description='shoeprint recognition')
parser.add_argument('action',
choices=['train', 'test', 'docs'],
help='action type (train/test)')
parser.add_argument('--resume', action='store_true', help='恢复已有模型继续训练')
parser.add_argument('--no-gpu', action='store_true', help='不使用 GPU')
parser.add_argument('--use-cache',
action='store_true',
help='使用已有的 sample cache')
args = parser.parse_args()
CONFIG.train.resume = args.resume or CONFIG.train.resume
CONFIG.test.use_cache = args.use_cache or CONFIG.test.use_cache
CONFIG.gpu.enable = not args.no_gpu or not CONFIG.gpu.enable
if args.action == "train":
from trainer.train import train
train()
elif args.action == "test":
from infer.test import test
test()
elif args.action == "docs":
from docs import docs_dev
docs_dev()
else:
print("can not parse arg {}".format(args.action))
