def run():
device = 0 if torch.cuda.is_available() else -1
config = BaseConfig()
logging.info('%s_cross_entropy/ckpt.pth.tar' % config.result_dir)
if os.path.exists('%s_cross_entropy/ckpt.pth.tar' % config.result_dir):
return True
logging.info("Triplet Trainer Not Return")
create_dirs()
tr_data_loader, val_data_loader, te_data_loader = loaders.data_loaders(
shuffle=True)
model = getattr(models,
config.network)(num_classes=len(tr_data_loader.dataset.y))
model
criterion = CrossEntropyLoss()
if device == 0:
model.cuda()
criterion.cuda()
trainer = ModuleTrainer(model)
epochs = config.epochs
callbacks = [
EarlyStopping(monitor='val_acc', patience=20),
ModelCheckpoint('%s_cross_entropy' % config.result_dir,
save_best_only=True,
verbose=1),
CSVLogger("%s_cross_entropy/logger.csv" % config.result_dir)
]
metrics = [CategoricalAccuracy()]
trainer.compile(loss=criterion, optimizer='adam', metrics=metrics)
trainer.set_callbacks(callbacks)
trainer.fit_loader(tr_data_loader,
val_loader=val_data_loader,
num_epoch=epochs,
verbose=2,
cuda_device=device)
tr_loss = trainer.evaluate_loader(tr_data_loader, cuda_device=device)
logging.info(tr_loss)
val_loss = trainer.evaluate_loader(val_data_loader, cuda_device=device)
logging.info(val_loss)
te_loss = trainer.evaluate_loader(te_data_loader, cuda_device=device)
logging.info(te_loss)
with open('%s_cross_entropy' % config.log_path, "a") as f:
f.write('Train %s\nVal:%s\nTest:%s\n' %
(str(tr_loss), str(val_loss), te_loss))
def run():
from config import get_config
config = get_config()
load_model_epoch.run()
return True
print("Timer")
import models
from utils.make_dirs import create_dirs
from datasets import loaders
from torchsample.modules import ModuleTrainer
create_dirs()
cuda_device = -1
tr_data_loader, val_data_loader, te_data_loader = loaders.online_triplet_loaders(
)
model = getattr(models, config.network).get_network()(
channel=config.network_channel, embedding_size=config.embedding)
from losses.online_triplet import OnlineTripletLoss
from datasets.data_utils import AllTripletSelector, HardestNegativeTripletSelector, RandomNegativeTripletSelector, \
SemihardNegativeTripletSelector
margin = 1.
if args.selector == 'AllTripletSelector':
criterion = OnlineTripletLoss(margin, AllTripletSelector())
elif args.selector == 'HardestNegativeTripletSelector':
criterion = OnlineTripletLoss(margin,
HardestNegativeTripletSelector(margin))
elif args.selector == 'RandomNegativeTripletSelector':
criterion = OnlineTripletLoss(margin,
RandomNegativeTripletSelector(margin))
elif args.selector == 'SemihardNegativeTripletSelector':
criterion = OnlineTripletLoss(margin,
SemihardNegativeTripletSelector(margin))
if config.cuda:
model.cuda()
criterion.cuda()
trainer = ModuleTrainer(model)
trainer.compile(loss=criterion, optimizer='adam')
if config.cuda:
cuda_device = 0
trainer.evaluate_loader(tr_data_loader, verbose=2, cuda_device=cuda_device)
trainer.evaluate_loader(val_data_loader,
verbose=2,
cuda_device=cuda_device)
trainer.evaluate_loader(te_data_loader, verbose=2, cuda_device=cuda_device)
start_time = time.time()
trainer.fit_loader(tr_data_loader,
val_loader=val_data_loader,
num_epoch=1,
verbose=2,
cuda_device=cuda_device)
end_time = time.time()
with open("./times.log", mode="a") as f:
f.write("%s %s\n" % (config.result_dir, str(end_time - start_time)))
def run():
from config import get_config
config = get_config()
print("Timer")
import losses
import models
from utils.make_dirs import create_dirs
from datasets import loaders
from torchsample.modules import ModuleTrainer
create_dirs()
cuda_device = -1
tr_data_loader, val_data_loader, te_data_loader = getattr(
loaders, config.loader_name)(train=True)
model = getattr(models, config.network).get_network()(
channel=config.network_channel, embedding_size=config.embedding)
criterion = getattr(losses, config.loss)()
if config.cuda:
model.cuda()
criterion.cuda()
trainer = ModuleTrainer(model)
trainer.compile(loss=criterion, optimizer='adam')
if config.cuda:
cuda_device = 0
trainer.evaluate_loader(tr_data_loader, verbose=2, cuda_device=cuda_device)
trainer.evaluate_loader(val_data_loader,
verbose=2,
cuda_device=cuda_device)
trainer.evaluate_loader(te_data_loader, verbose=2, cuda_device=cuda_device)
start_time = time.time()
trainer.fit_loader(tr_data_loader,
val_loader=val_data_loader,
num_epoch=1,
verbose=2,
cuda_device=cuda_device)
end_time = time.time()
with open("./times.log", mode="a") as f:
f.write("%s %s\n" % (config.result_dir, str(end_time - start_time)))
def run():
from config import get_config
config = get_config()
print('%s/ckpt.pth.tar' % config.result_dir)
if os.path.exists('%s/ckpt.pth.tar' % config.result_dir):
return True
print("Contrastive Trainer Not Return")
import models
from utils.make_dirs import create_dirs
from datasets import loaders
from torchsample.callbacks import EarlyStopping, ModelCheckpoint, CSVLogger
from torchsample.metrics import CategoricalAccuracy
from torchsample.modules import ModuleTrainer
create_dirs()
cuda_device = -1
tr_data_loader, val_data_loader, te_data_loader = loaders.online_pair_loaders()
model = getattr(models, config.network).get_network()(channel=config.network_channel,
embedding_size=config.embedding)
from losses.online_cosine import OnlineCosineLoss
from datasets.data_utils import AllPositivePairSelector, HardNegativePairSelector
margin = 0.5
if args.selector == 'AllPositivePairSelector':
criterion = OnlineCosineLoss(margin, AllPositivePairSelector())
elif args.selector == 'HardNegativePairSelector':
criterion = OnlineCosineLoss(margin, HardNegativePairSelector())
if config.cuda:
model.cuda()
criterion.cuda()
trainer = ModuleTrainer(model)
epochs = config.epochs
callbacks = [EarlyStopping(monitor='val_loss', patience=50),
ModelCheckpoint(config.result_dir, save_best_only=True, verbose=1),
CSVLogger("%s/logger.csv" % config.result_dir)]
metrics = []
if config.loader_name == 'data_loaders' and 'Angle' not in config.loss:
metrics.append(CategoricalAccuracy(top_k=1))
trainer.compile(loss=criterion, optimizer='adam', metrics=metrics)
trainer.set_callbacks(callbacks)
if config.cuda:
cuda_device = 0
start_time = time.time()
trainer.fit_loader(tr_data_loader, val_loader=val_data_loader, num_epoch=epochs, verbose=2,
cuda_device=cuda_device)
end_time = time.time()
with open("%s/app.log" % config.result_dir, mode="a") as f:
f.write("%s\n" % str(model))
f.write("%s %s\n" % (config.loss, str(end_time - start_time)))
tr_loss = trainer.evaluate_loader(tr_data_loader, cuda_device=cuda_device)
print(tr_loss)
val_loss = trainer.evaluate_loader(val_data_loader, cuda_device=cuda_device)
te_loss = trainer.evaluate_loader(te_data_loader, cuda_device=cuda_device)
print(te_loss)
with open(config.log_path, "a") as f:
f.write('Train %s\nVal:%s\nTest:%s\n' % (str(tr_loss), str(val_loss), te_loss))
tr_data_loader, val_data_loader, te_data_loader = loaders.data_loaders(train=False, val=True)
tr_y_pred = trainer.predict_loader(tr_data_loader, cuda_device=cuda_device)
save_embeddings(tr_y_pred, '%s/train_embeddings.csv' % config.result_dir)
save_labels(tr_data_loader, '%s/train_labels.csv' % config.result_dir)
val_y_pred = trainer.predict_loader(val_data_loader, cuda_device=cuda_device)
save_embeddings(val_y_pred, '%s/val_embeddings.csv' % config.result_dir)
save_labels(val_data_loader, '%s/val_labels.csv' % config.result_dir)
te_y_pred = trainer.predict_loader(te_data_loader, cuda_device=cuda_device)
save_embeddings(te_y_pred, '%s/test_embeddings.csv' % config.result_dir)
save_labels(te_data_loader, '%s/test_labels.csv' % config.result_dir)
def main(args):
"""Simply redirrcts to the correct function."""
start = default_timer()
args.cuda = not args.no_cuda and torch.cuda.is_available()
np.random.seed(args.seed)
torch.manual_seed(args.seed)
print("-------------------------------------------------")
if args.verbose > 0:
print("Ran on {}".format(time.strftime("%Y-%m-%d %H:%M")))
print()
print('Parameters: {}'.format(vars(args)))
print()
# PREPARES DATA
if args.verbose > 1:
print('Prepares data ...')
train, valid, test = train_valid_test_datasets(
args.dataset,
validSize=args.validation_size,
isHashingTrick=not args.dictionnary,
nFeaturesRange=args.num_features_range,
ngramRange=args.ngrams_range,
seed=args.seed,
num_words=args.num_embeding,
specificArgs={'dictionnary': ['num_words']})
num_classes = len(train.classes)
train = DataLoader(dataset=train,
batch_size=args.batch_size,
shuffle=not args.no_shuffle)
valid = DataLoader(dataset=valid,
batch_size=args.batch_size,
shuffle=not args.no_shuffle)
test = DataLoader(dataset=test,
batch_size=args.batch_size,
shuffle=not args.no_shuffle)
# PREPARES MODEL
if args.verbose > 1:
print('Prepares model ...')
Model = ModelNoDict if args.model == 'embed-softmax' else ModelDict
model = Model(args.num_embeding,
args.dim,
num_classes,
isHash=not args.no_hashembed,
seed=args.seed,
num_buckets=args.num_buckets,
append_weight=not args.no_append_weight,
aggregation_mode=args.agg_mode,
oldAlgorithm=args.old_hashembed)
if args.cuda:
model.cuda()
if args.verbose > 1:
model_parameters = filter(lambda p: p.requires_grad,
model.parameters())
nParams = sum([np.prod(p.size()) for p in model_parameters])
print('Num parameters in model: {}'.format(nParams))
print("Train on {} samples, validate on {} samples".format(
len(train), len(valid)))
# COMPILES
trainer = ModuleTrainer(model)
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters())
callbacks = []
callbackMetric = "val_loss" if args.val_loss_callback else "val_acc_metric"
if args.patience is not None:
callbacks.append(
EarlyStopping(patience=args.patience, monitor=callbackMetric))
if args.plateau_reduce_lr is not None:
callbacks.append(
ReduceLROnPlateau(factor=args.plateau_reduce_lr[1],
patience=args.plateau_reduce_lr[0],
monitor=callbackMetric))
if not args.no_checkpoint:
modelDir = os.path.join(parentddir, 'models')
filename = "{}.pth.tar".format(args.dataset)
callbacks.append(
ModelCheckpoint(modelDir,
filename=filename,
save_best_only=True,
max_save=1,
monitor=callbackMetric))
metrics = [CategoricalAccuracy()]
trainer.compile(loss=loss,
optimizer=optimizer,
callbacks=callbacks,
metrics=metrics)
# TRAINS
if args.verbose > 1:
print('Trains ...')
trainer.fit_loader(train,
val_loader=valid,
num_epoch=args.epochs,
verbose=args.verbose,
cuda_device=0 if args.cuda else -1)
# EVALUATES
print()
evalTest = trainer.evaluate_loader(test,
verbose=args.verbose,
cuda_device=0 if args.cuda else -1)
evalValid = trainer.evaluate_loader(valid,
verbose=args.verbose,
cuda_device=0 if args.cuda else -1)
print("Last Model. Validation - Loss: {}, Accuracy: {}".format(
evalValid['val_loss'], evalValid['val_acc_metric']))
print("Last Model. Test - Loss: {}, Accuracy: {}".format(
evalTest['val_loss'], evalTest['val_acc_metric']))
if not args.no_checkpoint:
checkpoint = torch.load(os.path.join(modelDir, filename))
model.load_state_dict(checkpoint["state_dict"])
evalTest = trainer.evaluate_loader(test,
verbose=args.verbose,
cuda_device=0 if args.cuda else -1)
evalValid = trainer.evaluate_loader(valid,
verbose=args.verbose,
cuda_device=0 if args.cuda else -1)
print("Best Model. Validation - Loss: {}, Accuracy: {}".format(
evalValid['val_loss'], evalValid['val_acc_metric']))
print("Best Model. Test - Loss: {}, Accuracy: {}".format(
evalTest['val_loss'], evalTest['val_acc_metric']))
if args.verbose > 1:
print('Finished after {:.1f} min.'.format(
(default_timer() - start) / 60))
def run():
from config import get_config
config = get_config()
print('%s/train_embeddings.csv' % config.result_dir)
result_dir = config.result_dir
print('%s/train_embeddings.csv' % result_dir)
if os.path.exists(
'%s/train_embeddings.csv' % result_dir) and os.path.exists(
'%s/test_embeddings.csv' % result_dir):
return True
if not os.path.exists(result_dir):
os.makedirs(result_dir)
print("Saved Module Trainer Not Return")
import losses
import models
from utils.make_dirs import create_dirs
from datasets import loaders
from torchsample.modules import ModuleTrainer
create_dirs()
cuda_device = -1
model = getattr(models, config.network).get_network()(
channel=config.network_channel, embedding_size=config.embedding)
check_point = os.path.join(config.result_dir, "ckpt.pth.tar")
if os.path.isfile(check_point):
print("=> loading checkpoint '{}'".format(check_point))
checkpoint = torch.load(check_point)
model.load_state_dict(checkpoint['state_dict'])
print("=> loaded checkpoint '{}' (epoch {})".format(
check_point, checkpoint['epoch']))
else:
print("=> no checkpoint found at '{}'".format(check_point))
criterion = getattr(losses, config.loss)()
if config.cuda:
model.cuda()
criterion.cuda()
trainer = ModuleTrainer(model)
metrics = []
if config.loader_name == 'data_loaders':
metrics.append(CategoricalAccuracy(top_k=1))
trainer.compile(loss=criterion, optimizer='adam', metrics=metrics)
if config.cuda:
cuda_device = 0
tr_data_loader, val_data_loader, te_data_loader = getattr(
loaders, config.loader_name)(train=False, val=True)
tr_loss = trainer.evaluate_loader(tr_data_loader, cuda_device=cuda_device)
val_loss = trainer.evaluate_loader(val_data_loader,
cuda_device=cuda_device)
te_loss = trainer.evaluate_loader(te_data_loader, cuda_device=cuda_device)
tr_y_pred = trainer.predict_loader(tr_data_loader, cuda_device=cuda_device)
save_embeddings(tr_y_pred, '%s/train_embeddings.csv' % result_dir)
save_labels(tr_data_loader, '%s/train_labels.csv' % result_dir)
val_y_pred = trainer.predict_loader(val_data_loader,
cuda_device=cuda_device)
save_embeddings(val_y_pred, '%s/val_embeddings.csv' % result_dir)
save_labels(val_data_loader, '%s/val_labels.csv' % result_dir)
te_y_pred = trainer.predict_loader(te_data_loader, cuda_device=cuda_device)
save_embeddings(te_y_pred, '%s/test_embeddings.csv' % result_dir)
save_labels(te_data_loader, '%s/test_labels.csv' % result_dir)
with open(config.log_path.replace("results", "best_results"), "a") as f:
f.write('Best Train %s\nBest Val:%s\nBest Test:%s\n' %
(str(tr_loss), str(val_loss), te_loss))