def train():
from models import model_factory
from dataloaders import dataloader_factory
from trainers import trainer_factory
from pruners import pruner_factory
from utils import *
from utils import scatterplot
from torch.utils.tensorboard import SummaryWriter
from torchvision import datasets, transforms
export_root = setup_train(args)
test_result_root = 'experiments/testresults'
test_result_title = export_root[12:]
test_result_title += '.txt'
model = model_factory(args)
train_loader, val_loader, test_loader = dataloader_factory(args)
pruner = pruner_factory(args, model)
trainer = trainer_factory(args, model, train_loader, val_loader,
test_loader, export_root, pruner)
#load_pretrained_weights(model, './experiments/ml-1m.pth')
trainer.train()
trainer.test()
if args.prune:
trainer.prune()
#pruner.print_mask(model)
#pruner.print_percentage(model)
i = 0
test_result = trainer.test()
save_test_result(export_root, test_result)
save_test_result(test_result_root, test_result, test_result_title)
print(test_result_root)
def train():
export_root = setup_train(args)
train_loader, val_loader, test_loader = dataloader_factory(args)
model = model_factory(args)
trainer = trainer_factory(args, model, train_loader, val_loader,
test_loader, export_root)
trainer.train()
def train(args):
local_export_root, remote_export_root, communicator = setup_train(args, MACHINE_IS_HOST)
assert (communicator is None and MACHINE_IS_HOST) or (communicator is not None and not MACHINE_IS_HOST)
if communicator:
communicator.close() # close station because it might lose connection during long training
train_loader, val_loader, test_loader = dataloader_factory(args)
model = model_factory(args)
trainer = trainer_factory(args, model, train_loader, val_loader, test_loader, local_export_root)
status_file = os.path.join(local_export_root, 'status.txt')
error_log_file = os.path.join(local_export_root, 'error_log.txt')
open(status_file, 'w').write(STATUS_RUNNING)
try:
trainer.train()
open(status_file, 'w').write(STATUS_FINISHED)
if not MACHINE_IS_HOST and args.experiment_group != 'test':
communicator = Communicator(HOST, PORT, USERNAME, PASSWORD)
communicator.upload_dir(local_export_root, remote_export_root)
communicator.close()
except Exception as err:
# recover
if args.experiment_group == 'test':
raise
if not os.path.exists(os.path.join(local_export_root, 'tables', 'val_log.csv')):
print('Removing empty local export root')
shutil.rmtree(local_export_root)
raise
open(status_file, 'w').write(STATUS_RECOVERY)
open(error_log_file, 'w').write(str(err))
if not MACHINE_IS_HOST and args.experiment_group != 'test':
print('Uploading recovery file')
communicator = Communicator(HOST, PORT, USERNAME, PASSWORD)
communicator.upload_dir(local_export_root, remote_export_root)
communicator.close()
raise
def train(model_args):
export_root = setup_train(model_args)
train_loader, val_loader, test_loader = dataloader_factory(model_args)
model = model_factory(model_args)
trainer = trainer_factory(model_args, model, train_loader, val_loader,
test_loader, export_root)
if model_args.mode == 'train':
trainer.train()
trainer.test()
def train():
export_root = setup_train(args)
fix_random_seed_as(args.model_init_seed)
train_loader, val_loader, test_loader = dataloader_factory(args)
model = model_factory(args)
trainer = trainer_factory(args, model, train_loader, val_loader,
test_loader, export_root)
trainer.train()
def validate(args, mode='val'): local_export_root, remote_export_root, communicator = setup_train(args, MACHINE_IS_HOST) if communicator: communicator.close() train_loader, val_loader, test_loader = dataloader_factory(args) model = model_factory(args) if args.pretrained_weights is not None: model.load(args.pretrained_weights) trainer = trainer_factory(args, model, train_loader, val_loader, test_loader, local_export_root) trainer.just_validate(mode)
def train():
export_root = setup_train(args)
train_loader, val_loader, test_loader = dataloader_factory(args)
model = model_factory(args)
trainer = trainer_factory(args, model, train_loader, val_loader, test_loader, export_root)
trainer.train()
test_model = (input('Test model with test dataset? y/[n]: ') == 'y')
if test_model:
trainer.test()
def train():
export_root = setup_train(args)
model = model_factory(args)
train_loader, val_loader, test_loader = dataloader_factory(args)
pruner = pruner_factory(args, model)
trainer = trainer_factory(args, model, train_loader, val_loader,
test_loader, export_root, pruner)
#trainer.train()
print("Model's state_dict:")
for param_tensor in model.bert.state_dict():
print(param_tensor, "\t", model.bert.state_dict()[param_tensor].size())
# Print optimizer's state_dict
print("Optimizer's state_dict:")
for var_name in trainer.optimizer.state_dict():
print(var_name, "\t", trainer.optimizer.state_dict()[var_name])
torch.save(model, './initmodel.pth')
def evaluate():
export_root = setup_train(args)
meta, train_loader, val_loader, test_loader = dataloader_factory(args)
model = model_factory(args, meta)
trainer = trainer_factory(args, model, train_loader, val_loader,
test_loader, export_root)
path = args.eval_model_path
load_pretrained_weights(model, path)
average_meter_set = AverageMeterSet()
for batch in test_loader:
with torch.no_grad():
batch = [x.to(trainer.device) for x in batch]
metrics = trainer.calculate_metrics(batch)
for k, v in metrics.items():
average_meter_set.update(k, v)
print(average_meter_set.averages())
