for param in autoencoder.parameters():
param.data = param.double()
for param in classifier.parameters():
param.data = param.double()
prefix = f'{args.label}_' if args.label else ''
postfix = '_robust' if args.adversarial else ''
autoencoder.load_state_dict(
torch.load(path.join(
args.models_dir,
prefix + f'autoencoder_{args.epoch}' + postfix + '.pt'),
map_location=lambda storage, loc: storage))
classifier.load_state_dict(
torch.load(path.join(args.models_dir, prefix + f'classifier_{args.epoch}' +
postfix + '.pt'),
map_location=lambda storage, loc: storage))
encoder_layers = []
for layer in autoencoder.encoder_layers:
if isinstance(layer, nn.Sequential):
for sub_layer in layer:
encoder_layers += [sub_layer]
else:
encoder_layers += [layer]
all_l_inf, all_times = [], []
ver, corr = 0, 0
oracle = DL2_Oracle(learning_rate=DL2_LR,
def main():
args = parser.parse_args()
# seed everything to ensure reproducible results from different runs
if args.seed is not None:
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.backends.cudnn.deterministic = True
###########################################################################
# Model
###########################################################################
global best_acc1
# create model
if args.arch == 'LogisticRegression':
model = LogisticRegression(input_size=13, n_classes=args.classes)
elif args.arch == 'NeuralNet':
model = NeuralNet(input_size=13, hidden_size=[32, 16], n_classes=args.classes) #hidden_size=[64, 32]
if args.gpu is not None:
print("Use GPU: {} for training".format(args.gpu))
torch.cuda.set_device(args.gpu)
torch.backends.cudnn.benchmark = True
model = model.cuda(args.gpu)
# print(model)
if args.train_file:
print(30 * '=')
print(summary(model, input_size=(1, 13),
batch_size=args.batch_size, device='cpu'))
print(30 * '=')
###########################################################################
# save directory
###########################################################################
save_dir = os.path.join(os.getcwd(), args.save_dir)
save_dir += ('/arch[{}]_optim[{}]_lr[{}]_lrsch[{}]_batch[{}]_'
'WeightedSampling[{}]').format(args.arch,
args.optim,
args.lr,
args.lr_scheduler,
args.batch_size,
args.weighted_sampling)
if args.suffix:
save_dir += '_{}'.format(args.suffix)
save_dir = save_dir[:]
if not os.path.exists(save_dir):
os.makedirs(save_dir)
###########################################################################
# Criterion and optimizer
###########################################################################
# Initialise criterion and optimizer
if args.gpu is not None:
criterion = nn.CrossEntropyLoss().cuda(args.gpu)
else:
criterion = nn.CrossEntropyLoss()
# define optimizer
print("=> using '{}' optimizer".format(args.optim))
if args.optim == 'sgd':
optimizer = torch.optim.SGD(model.parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay,
nesterov=True)
else: # default is adam
optimizer = torch.optim.Adam(model.parameters(), args.lr,
betas=(0.9, 0.999), eps=1e-08,
weight_decay=args.weight_decay,
amsgrad=False)
###########################################################################
# Resume training and load a checkpoint
###########################################################################
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
if args.gpu is None:
checkpoint = torch.load(args.resume)
else:
# Map model to be loaded to specified single gpu.
loc = 'cuda:{}'.format(args.gpu)
checkpoint = torch.load(args.resume, map_location=loc)
args.start_epoch = checkpoint['epoch']
best_acc1 = checkpoint['best_acc1']
if args.gpu is not None:
# best_acc1 may be from a checkpoint from a different GPU
best_acc1 = best_acc1.to(args.gpu)
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded checkpoint '{}' (epoch {})"
.format(args.resume, checkpoint['epoch']))
else:
print("=> no checkpoint found at '{}'".format(args.resume))
###########################################################################
# Data Augmentation
###########################################################################
# TODO
###########################################################################
# Learning rate scheduler
###########################################################################
print("=> using '{}' initial learning rate (lr)".format(args.lr))
# define learning rate scheduler
scheduler = args.lr_scheduler
if args.lr_scheduler == 'reduce':
print("=> using '{}' lr_scheduler".format(args.lr_scheduler))
# Reduce learning rate when a metric has stopped improving.
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
mode='min',
factor=0.5,
patience=10)
elif args.lr_scheduler == 'cyclic':
print("=> using '{}' lr_scheduler".format(args.lr_scheduler))
scheduler = torch.optim.lr_scheduler.CyclicLR(optimizer,
base_lr=0.00005,
max_lr=0.005)
elif args.lr_scheduler == 'cosine':
print("=> using '{}' lr_scheduler".format(args.lr_scheduler))
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer,
T_max=100,
eta_min=0,
last_epoch=-1)
###########################################################################
# load train data
###########################################################################
if args.train_file:
train_dataset = HeartDiseaseDataset(csv=args.train_file, label_names=LABELS)
if args.weighted_sampling:
train_sampler = torch.utils.data.WeightedRandomSampler(train_dataset.sample_weights,
len(train_dataset),
replacement=True)
else:
train_sampler = None
###########################################################################
# update criterion
print('class_sample_count ', train_dataset.class_sample_count)
print('class_probability ', train_dataset.class_probability)
print('class_weights ', train_dataset.class_weights)
print('sample_weights ', train_dataset.sample_weights)
if args.weighted_loss:
if args.gpu is not None:
criterion = nn.CrossEntropyLoss(weight=train_dataset.class_weights).cuda(args.gpu)
else:
criterion = nn.CrossEntropyLoss(weight=train_dataset.class_weights)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=args.batch_size, shuffle=(train_sampler is None),
num_workers=args.workers, pin_memory=True, sampler=train_sampler)
###########################################################################
# load validation data
###########################################################################
if args.valid_file:
valid_dataset = HeartDiseaseDataset(csv=args.valid_file, label_names=LABELS)
val_loader = torch.utils.data.DataLoader(valid_dataset,
batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True)
if args.evaluate:
# retrieve correct save path from saved model
save_dir = os.path.split(args.resume)[0]
validate(val_loader, model, criterion, save_dir, args)
return
###########################################################################
# Train the model
###########################################################################
for epoch in range(args.start_epoch, args.epochs):
# adjust_learning_rate(optimizer, epoch, args)
print_learning_rate(optimizer, epoch)
# train for one epoch
train(train_loader, model, criterion, optimizer,
scheduler, epoch, args)
# evaluate on validation set
acc1 = validate(val_loader, model, criterion, save_dir, args)
# update learning rate based on lr_scheduler
if args.lr_scheduler == 'reduce':
scheduler.step(acc1)
elif args.lr_scheduler == 'cosine':
scheduler.step()
# remember best acc@1 and save checkpoint
is_best = acc1 >= best_acc1
best_acc1 = max(acc1, best_acc1)
print("Saving model [{}]...".format(save_dir))
save_checkpoint({'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_acc1': best_acc1,
'optimizer': optimizer.state_dict(),
'criterion': criterion, },
is_best,
save_dir=save_dir)
print(30 * '=')
