def restore_checkpoint(self,opt):
if opt.from_epoch!=0:
util.restore_checkpoint_from_epoch(opt,self,["network","optim","sched"])
elif opt.load is not None:
util.restore_checkpoint(opt,self,opt.load,["network","optim","sched"])
elif opt.imagenet_enc or opt.pretrained_dec is not None: pass
else:
print(util.magenta("training from scratch..."))
def main(device=torch.device('cuda:0')):
# CLI arguments
parser = arg.ArgumentParser(
description='We all know what we are doing. Fighting!')
parser.add_argument("--datasize",
"-d",
default="small",
type=str,
help="data size you want to use, small, medium, total")
# Parsing
args = parser.parse_args()
# Data loaders
datasize = args.datasize
pathname = "data/nyu.zip"
tr_loader, va_loader, te_loader = getTrainingValidationTestingData(
datasize, pathname, batch_size=config("unet.batch_size"))
# Model
model = Net()
# define loss function
# criterion = torch.nn.L1Loss()
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = util.restore_checkpoint(
model, util.config("unet.checkpoint"))
acc, loss = util.evaluate_model(model, te_loader, device)
# axes = util.make_training_plot()
print(f'Test Accuracy:{acc}')
print(f'Test Loss:{loss}')
def main(device=torch.device('cuda:0')):
"""Print performance metrics for model at specified epoch."""
# Data loaders
pathname = "data/nyu.zip"
tr_loader, va_loader, te_loader = getTrainingValidationTestingData(pathname,
batch_size=util.config("unet.batch_size"))
# Model
model = Net()
# define loss function
# criterion = torch.nn.L1Loss()
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = util.restore_checkpoint(model, util.config("unet.checkpoint"))
acc, loss = util.evaluate_model(model, te_loader, device)
# axes = util.make_training_plot()
print(f'Test Accuracy:{acc}')
print(f'Test Loss:{loss}')
def restore_checkpoint(self, opt):
util.restore_checkpoint(opt, self, opt.load, ["network"])
def main(device=torch.device('cuda:0')):
# CLI arguments
parser = arg.ArgumentParser(
description='We all know what we are doing. Fighting!')
parser.add_argument("--datasize",
"-d",
default="small",
type=str,
help="data size you want to use, small, medium, total")
# Parsing
args = parser.parse_args()
# Data loaders
datasize = args.datasize
pathname = "data/nyu.zip"
tr_loader, va_loader, te_loader = getTrainingValidationTestingData(
datasize, pathname, batch_size=config("unet.batch_size"))
# Model
model = Net()
# TODO: define loss function, and optimizer
learning_rate = util.config("unet.learning_rate")
criterion = DepthLoss(0.1)
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
number_of_epoches = 10
#
# print("Number of float-valued parameters:", util.count_parameters(model))
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = util.restore_checkpoint(
model, util.config("unet.checkpoint"))
# axes = utils.make_training_plot()
# Evaluate the randomly initialized model
# evaluate_epoch(
# axes, tr_loader, va_loader, te_loader, model, criterion, start_epoch, stats
# )
# loss = criterion()
# initial val loss for early stopping
# prev_val_loss = stats[0][1]
running_va_loss = []
running_va_acc = []
running_tr_loss = []
running_tr_acc = []
# TODO: define patience for early stopping
# patience = 1
# curr_patience = 0
#
tr_acc, tr_loss = util.evaluate_model(model, tr_loader, device)
acc, loss = util.evaluate_model(model, va_loader, device)
running_va_acc.append(acc)
running_va_loss.append(loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
# Loop over the entire dataset multiple times
# for epoch in range(start_epoch, config('cnn.num_epochs')):
epoch = start_epoch
# while curr_patience < patience:
while epoch < number_of_epoches:
# Train model
util.train_epoch(tr_loader, model, criterion, optimizer, device)
tr_acc, tr_loss = util.evaluate_model(model, tr_loader, device)
va_acc, va_loss = util.evaluate_model(model, va_loader, device)
running_va_acc.append(va_acc)
running_va_loss.append(va_loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
# Evaluate model
# evaluate_epoch(
# axes, tr_loader, va_loader, te_loader, model, criterion, epoch + 1, stats
# )
# Save model parameters
util.save_checkpoint(model, epoch + 1, util.config("unet.checkpoint"),
stats)
# update early stopping parameters
"""
curr_patience, prev_val_loss = early_stopping(
stats, curr_patience, prev_val_loss
)
"""
epoch += 1
print("Finished Training")
# Save figure and keep plot open
# utils.save_training_plot()
# utils.hold_training_plot()
util.make_plot(running_tr_loss, running_tr_acc, running_va_loss,
running_va_acc)
def main(device=torch.device('cuda:0')):
"""Train CNN and show training plots."""
# Data loaders
"""
if check_for_augmented_data("./data"):
tr_loader, va_loader, te_loader, _ = get_train_val_test_loaders(
task="target", batch_size=config("cnn.batch_size"), augment=True
)
else:
tr_loader, va_loader, te_loader, _ = get_train_val_test_loaders(
task="target",
batch_size=config("cnn.batch_size"),
)
"""
# pathname = "data/nyu_depth.zip"
pathname = "data/nyu_small.zip"
tr_loader, va_loader, te_loader = getTrainingValidationTestingData(pathname,
batch_size=util.config("unet.batch_size"))
# Model
model = Net()
# TODO: define loss function, and optimizer
learning_rate = util.config("unet.learning_rate")
criterion = DepthLoss(0.1)
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
number_of_epoches = 10
#
# print("Number of float-valued parameters:", util.count_parameters(model))
# Attempts to restore the latest checkpoint if exists
print("Loading unet...")
model, start_epoch, stats = util.restore_checkpoint(model, util.config("unet.checkpoint"))
# axes = utils.make_training_plot()
# Evaluate the randomly initialized model
# evaluate_epoch(
# axes, tr_loader, va_loader, te_loader, model, criterion, start_epoch, stats
# )
# loss = criterion()
# initial val loss for early stopping
# prev_val_loss = stats[0][1]
running_va_loss = []
running_va_acc = []
running_tr_loss = []
running_tr_acc = []
# TODO: define patience for early stopping
# patience = 1
# curr_patience = 0
#
tr_acc, tr_loss = util.evaluate_model(model, tr_loader, device)
acc, loss = util.evaluate_model(model, va_loader, device)
running_va_acc.append(acc)
running_va_loss.append(loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
# Loop over the entire dataset multiple times
# for epoch in range(start_epoch, config('cnn.num_epochs')):
epoch = start_epoch
# while curr_patience < patience:
while epoch < number_of_epoches:
# Train model
util.train_epoch(tr_loader, model, criterion, optimizer)
tr_acc, tr_loss = util.evaluate_model(model, tr_loader, device)
va_acc, va_loss = util.evaluate_model(model, va_loader, device)
running_va_acc.append(va_acc)
running_va_loss.append(va_loss)
running_tr_acc.append(tr_acc)
running_tr_loss.append(tr_loss)
# Evaluate model
# evaluate_epoch(
# axes, tr_loader, va_loader, te_loader, model, criterion, epoch + 1, stats
# )
# Save model parameters
util.save_checkpoint(model, epoch + 1, util.config("unet.checkpoint"), stats)
# update early stopping parameters
"""
curr_patience, prev_val_loss = early_stopping(
stats, curr_patience, prev_val_loss
)
"""
epoch += 1
print("Finished Training")
# Save figure and keep plot open
# utils.save_training_plot()
# utils.hold_training_plot()
util.make_plot(running_tr_loss, running_tr_acc, running_va_loss, running_va_acc)
resumable = args.resume and util.is_resumable(args.exp_dir)
os.makedirs(args.exp_dir, exist_ok=True)
if not resumable:
util.save_args(args, args.exp_dir)
# Seed
random = np.random.RandomState(args.seed)
dataloaders, pos_prop = wrappers.load_data(args,
random_state=random,
use_random_transpose=True)
model, optimizer, loss = wrappers.build_mvae(args, pos_prop=pos_prop)
# If resume, load metrics; otherwise init metrics
if resumable:
util.restore_checkpoint(model, optimizer, args.exp_dir)
metrics = util.load_metrics(args.exp_dir)
start_epoch = metrics['current_epoch'] + 1
print("Resuming from epoch {}".format(metrics['current_epoch']))
else:
metrics = init_metrics()
start_epoch = 1
if start_epoch > args.epochs:
raise RuntimeError("start_epoch {} > total epochs {}".format(
start_epoch, args.epochs))
# Enumerate subsampled modality combinations
m_combos = enumerate_combinations(args.n_tracks)
