## setup model, optim, loss_fn, summary_writer
model = models.resnet18().to(device)
optimizer = torch.optim.Adam(model.parameters(),
lr=0.0001,
weight_decay=0.01)
loss_fn = torch.nn.CrossEntropyLoss()
summary_writer = SummaryWriter(args.output + "/" +
args.experiment_name + "/" +
f"stage_{stage}")
best_test_acc = 0
test_acc_this_stage = []
for epoch in range(epochs):
train_loss = train(model,
train_loader,
optimizer,
loss_fn,
epoch,
device,
event_writer=summary_writer,
log_interval=50)
_, train_acc = test(model,
train_loader,
loss_fn,
epoch,
device,
event_writer=summary_writer,
test_type='train')
test_loss, test_acc = test(model,
test_loader,
loss_fn,
epoch,
device,
def run(args):
if args.train:
print(f"Training over {args.epochs} epochs")
elif args.test:
print("Running a full evaluation")
else:
print("Running inference speed test")
print("model:\t\t", args.model)
print("dataset:\t", args.dataset)
print("batch_size:\t", args.batch_size)
hook = sy.TorchHook(torch)
if args.websockets:
alice = DataCentricFLClient(hook, "ws://localhost:7600")
bob = DataCentricFLClient(hook, "ws://localhost:7601")
crypto_provider = DataCentricFLClient(hook, "ws://localhost:7602")
my_grid = sy.PrivateGridNetwork(alice, bob, crypto_provider)
sy.local_worker.object_store.garbage_delay = 1
else:
bob = sy.VirtualWorker(hook, id="bob")
alice = sy.VirtualWorker(hook, id="alice")
crypto_provider = sy.VirtualWorker(hook, id="crypto_provider")
workers = [alice, bob]
sy.local_worker.clients = workers
encryption_kwargs = dict(workers=workers,
crypto_provider=crypto_provider,
protocol=args.protocol)
kwargs = dict(
requires_grad=args.requires_grad,
precision_fractional=args.precision_fractional,
dtype=args.dtype,
**encryption_kwargs,
)
if args.preprocess:
build_prepocessing(args.model, args.dataset, args.batch_size, workers,
args)
private_train_loader, private_test_loader = get_data_loaders(args,
kwargs,
private=True)
public_train_loader, public_test_loader = get_data_loaders(args,
kwargs,
private=False)
model = get_model(args.model,
args.dataset,
out_features=get_number_classes(args.dataset))
if args.test and not args.train:
load_state_dict(model, args.model, args.dataset)
model.eval()
if torch.cuda.is_available():
sy.cuda_force = True
if not args.public:
model.encrypt(**kwargs)
if args.fp_only: # Just keep the (Autograd+) Fixed Precision feature
model.get()
if args.train:
for epoch in range(args.epochs):
optimizer = optim.SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum)
if not args.public:
optimizer = optimizer.fix_precision(
precision_fractional=args.precision_fractional,
dtype=args.dtype)
train_time = train(args, model, private_train_loader, optimizer,
epoch)
test_time, accuracy = test(args, model, private_test_loader)
else:
test_time, accuracy = test(args, model, private_test_loader)
if not args.test:
print(
f"{ 'Online' if args.preprocess else 'Total' } time (s):\t",
round(test_time / args.batch_size, 4),
)
else:
# Compare with clear text accuracy
print("Clear text accuracy is:")
model = get_model(args.model,
args.dataset,
out_features=get_number_classes(args.dataset))
load_state_dict(model, args.model, args.dataset)
test(args, model, public_test_loader)
if args.preprocess:
missing_items = [len(v) for k, v in sy.preprocessed_material.items()]
if sum(missing_items) > 0:
print("MISSING preprocessed material")
for key, value in sy.preprocessed_material.items():
print(f"'{key}':", value, ",")
def main(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
prepare_seed(args.rand_seed)
logstr = 'seed-{:}-time-{:}'.format(args.rand_seed, time_for_file())
logger = Logger(args.save_path, logstr)
logger.log('Main Function with logger : {:}'.format(logger))
logger.log('Arguments : -------------------------------')
for name, value in args._get_kwargs():
logger.log('{:16} : {:}'.format(name, value))
logger.log("Python version : {}".format(sys.version.replace('\n', ' ')))
logger.log("Pillow version : {}".format(PIL.__version__))
logger.log("PyTorch version : {}".format(torch.__version__))
logger.log("cuDNN version : {}".format(torch.backends.cudnn.version()))
# General Data Argumentation
mean_fill = tuple([int(x * 255) for x in [0.485, 0.456, 0.406]])
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
assert args.arg_flip == False, 'The flip is : {}, rotate is {}'.format(
args.arg_flip, args.rotate_max)
train_transform = [transforms.PreCrop(args.pre_crop_expand)]
train_transform += [
transforms.TrainScale2WH((args.crop_width, args.crop_height))
]
train_transform += [
transforms.AugScale(args.scale_prob, args.scale_min, args.scale_max)
]
#if args.arg_flip:
# train_transform += [transforms.AugHorizontalFlip()]
if args.rotate_max:
train_transform += [transforms.AugRotate(args.rotate_max)]
train_transform += [
transforms.AugCrop(args.crop_width, args.crop_height,
args.crop_perturb_max, mean_fill)
]
train_transform += [transforms.ToTensor(), normalize]
train_transform = transforms.Compose(train_transform)
eval_transform = transforms.Compose([
transforms.PreCrop(args.pre_crop_expand),
transforms.TrainScale2WH((args.crop_width, args.crop_height)),
transforms.ToTensor(), normalize
])
assert (
args.scale_min + args.scale_max
) / 2 == args.scale_eval, 'The scale is not ok : {},{} vs {}'.format(
args.scale_min, args.scale_max, args.scale_eval)
# Model Configure Load
model_config = load_configure(args.model_config, logger)
args.sigma = args.sigma * args.scale_eval
logger.log('Real Sigma : {:}'.format(args.sigma))
# Training Dataset
train_data = VDataset(train_transform, args.sigma, model_config.downsample,
args.heatmap_type, args.data_indicator,
args.video_parser)
train_data.load_list(args.train_lists, args.num_pts, True)
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
# Evaluation Dataloader
eval_loaders = []
if args.eval_vlists is not None:
for eval_vlist in args.eval_vlists:
eval_vdata = IDataset(eval_transform, args.sigma,
model_config.downsample, args.heatmap_type,
args.data_indicator)
eval_vdata.load_list(eval_vlist, args.num_pts, True)
eval_vloader = torch.utils.data.DataLoader(
eval_vdata,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=True)
eval_loaders.append((eval_vloader, True))
if args.eval_ilists is not None:
for eval_ilist in args.eval_ilists:
eval_idata = IDataset(eval_transform, args.sigma,
model_config.downsample, args.heatmap_type,
args.data_indicator)
eval_idata.load_list(eval_ilist, args.num_pts, True)
eval_iloader = torch.utils.data.DataLoader(
eval_idata,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=True)
eval_loaders.append((eval_iloader, False))
# Define network
lk_config = load_configure(args.lk_config, logger)
logger.log('model configure : {:}'.format(model_config))
logger.log('LK configure : {:}'.format(lk_config))
net = obtain_model(model_config, lk_config, args.num_pts + 1)
assert model_config.downsample == net.downsample, 'downsample is not correct : {} vs {}'.format(
model_config.downsample, net.downsample)
logger.log("=> network :\n {}".format(net))
logger.log('Training-data : {:}'.format(train_data))
for i, eval_loader in enumerate(eval_loaders):
eval_loader, is_video = eval_loader
logger.log('The [{:2d}/{:2d}]-th testing-data [{:}] = {:}'.format(
i, len(eval_loaders), 'video' if is_video else 'image',
eval_loader.dataset))
logger.log('arguments : {:}'.format(args))
opt_config = load_configure(args.opt_config, logger)
if hasattr(net, 'specify_parameter'):
net_param_dict = net.specify_parameter(opt_config.LR, opt_config.Decay)
else:
net_param_dict = net.parameters()
optimizer, scheduler, criterion = obtain_optimizer(net_param_dict,
opt_config, logger)
logger.log('criterion : {:}'.format(criterion))
net, criterion = net.cuda(), criterion.cuda()
net = torch.nn.DataParallel(net)
last_info = logger.last_info()
if last_info.exists():
logger.log("=> loading checkpoint of the last-info '{:}' start".format(
last_info))
last_info = torch.load(last_info)
start_epoch = last_info['epoch'] + 1
checkpoint = torch.load(last_info['last_checkpoint'])
assert last_info['epoch'] == checkpoint[
'epoch'], 'Last-Info is not right {:} vs {:}'.format(
last_info, checkpoint['epoch'])
net.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
scheduler.load_state_dict(checkpoint['scheduler'])
logger.log("=> load-ok checkpoint '{:}' (epoch {:}) done".format(
logger.last_info(), checkpoint['epoch']))
elif args.init_model is not None:
init_model = Path(args.init_model)
assert init_model.exists(), 'init-model {:} does not exist'.format(
init_model)
checkpoint = torch.load(init_model)
checkpoint = remove_module_dict(checkpoint['state_dict'], True)
net.module.detector.load_state_dict(checkpoint)
logger.log("=> initialize the detector : {:}".format(init_model))
start_epoch = 0
else:
logger.log("=> do not find the last-info file : {:}".format(last_info))
start_epoch = 0
detector = torch.nn.DataParallel(net.module.detector)
eval_results = eval_all(args, eval_loaders, detector, criterion,
'start-eval', logger, opt_config)
if args.eval_once:
logger.log("=> only evaluate the model once")
logger.close()
return
# Main Training and Evaluation Loop
start_time = time.time()
epoch_time = AverageMeter()
for epoch in range(start_epoch, opt_config.epochs):
scheduler.step()
need_time = convert_secs2time(
epoch_time.avg * (opt_config.epochs - epoch), True)
epoch_str = 'epoch-{:03d}-{:03d}'.format(epoch, opt_config.epochs)
LRs = scheduler.get_lr()
logger.log(
'\n==>>{:s} [{:s}], [{:s}], LR : [{:.5f} ~ {:.5f}], Config : {:}'.
format(time_string(), epoch_str, need_time, min(LRs), max(LRs),
opt_config))
# train for one epoch
train_loss = train(args, train_loader, net, criterion, optimizer,
epoch_str, logger, opt_config, lk_config,
epoch >= lk_config.start)
# log the results
logger.log('==>>{:s} Train [{:}] Average Loss = {:.6f}'.format(
time_string(), epoch_str, train_loss))
# remember best prec@1 and save checkpoint
save_path = save_checkpoint(
{
'epoch': epoch,
'args': deepcopy(args),
'arch': model_config.arch,
'state_dict': net.state_dict(),
'detector': detector.state_dict(),
'scheduler': scheduler.state_dict(),
'optimizer': optimizer.state_dict(),
},
logger.path('model') /
'{:}-{:}.pth'.format(model_config.arch, epoch_str), logger)
last_info = save_checkpoint(
{
'epoch': epoch,
'last_checkpoint': save_path,
}, logger.last_info(), logger)
eval_results = eval_all(args, eval_loaders, detector, criterion,
epoch_str, logger, opt_config)
# measure elapsed time
epoch_time.update(time.time() - start_time)
start_time = time.time()
logger.close()
def main(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
prepare_seed(args.rand_seed)
logstr = 'seed-{:}-time-{:}'.format(args.rand_seed, time_for_file())
logger = Logger(args.save_path, logstr)
logger.log('Main Function with logger : {:}'.format(logger))
logger.log('Arguments : -------------------------------')
for name, value in args._get_kwargs():
logger.log('{:16} : {:}'.format(name, value))
logger.log("Python version : {}".format(sys.version.replace('\n', ' ')))
logger.log("Pillow version : {}".format(PIL.__version__))
logger.log("PyTorch version : {}".format(torch.__version__))
logger.log("cuDNN version : {}".format(torch.backends.cudnn.version()))
# General Data Argumentation
mean_fill = tuple( [int(x*255) for x in [0.485, 0.456, 0.406] ] )
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
assert args.arg_flip == False, 'The flip is : {}, rotate is {}'.format(args.arg_flip, args.rotate_max)
train_transform = [transforms.PreCrop(args.pre_crop_expand)]
train_transform += [transforms.TrainScale2WH((args.crop_width, args.crop_height))]
train_transform += [transforms.AugScale(args.scale_prob, args.scale_min, args.scale_max)]
#if args.arg_flip:
# train_transform += [transforms.AugHorizontalFlip()]
if args.rotate_max:
train_transform += [transforms.AugRotate(args.rotate_max)]
train_transform += [transforms.AugCrop(args.crop_width, args.crop_height, args.crop_perturb_max, mean_fill)]
train_transform += [transforms.ToTensor(), normalize]
train_transform = transforms.Compose( train_transform )
eval_transform = transforms.Compose([transforms.PreCrop(args.pre_crop_expand), transforms.TrainScale2WH((args.crop_width, args.crop_height)), transforms.ToTensor(), normalize])
assert (args.scale_min+args.scale_max) / 2 == args.scale_eval, 'The scale is not ok : {},{} vs {}'.format(args.scale_min, args.scale_max, args.scale_eval)
# Model Configure Load
model_config = load_configure(args.model_config, logger)
args.sigma = args.sigma * args.scale_eval
logger.log('Real Sigma : {:}'.format(args.sigma))
# Training Dataset
train_data = Dataset(train_transform, args.sigma, model_config.downsample, args.heatmap_type, args.data_indicator)
train_data.load_list(args.train_lists, args.num_pts, True)
train_loader = torch.utils.data.DataLoader(train_data, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
# Evaluation Dataloader
eval_loaders = []
if args.eval_vlists is not None:
for eval_vlist in args.eval_vlists:
eval_vdata = Dataset(eval_transform, args.sigma, model_config.downsample, args.heatmap_type, args.data_indicator)
eval_vdata.load_list(eval_vlist, args.num_pts, True)
eval_vloader = torch.utils.data.DataLoader(eval_vdata, batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True)
eval_loaders.append((eval_vloader, True))
if args.eval_ilists is not None:
for eval_ilist in args.eval_ilists:
eval_idata = Dataset(eval_transform, args.sigma, model_config.downsample, args.heatmap_type, args.data_indicator)
eval_idata.load_list(eval_ilist, args.num_pts, True)
eval_iloader = torch.utils.data.DataLoader(eval_idata, batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True)
eval_loaders.append((eval_iloader, False))
# Define network
logger.log('configure : {:}'.format(model_config))
net = obtain_model(model_config, args.num_pts + 1)
assert model_config.downsample == net.downsample, 'downsample is not correct : {} vs {}'.format(model_config.downsample, net.downsample)
logger.log("=> network :\n {}".format(net))
logger.log('Training-data : {:}'.format(train_data))
for i, eval_loader in enumerate(eval_loaders):
eval_loader, is_video = eval_loader
logger.log('The [{:2d}/{:2d}]-th testing-data [{:}] = {:}'.format(i, len(eval_loaders), 'video' if is_video else 'image', eval_loader.dataset))
logger.log('arguments : {:}'.format(args))
opt_config = load_configure(args.opt_config, logger)
if hasattr(net, 'specify_parameter'):
net_param_dict = net.specify_parameter(opt_config.LR, opt_config.Decay)
else:
net_param_dict = net.parameters()
optimizer, scheduler, criterion = obtain_optimizer(net_param_dict, opt_config, logger)
logger.log('criterion : {:}'.format(criterion))
net, criterion = net.cuda(), criterion.cuda()
net = torch.nn.DataParallel(net)
last_info = logger.last_info()
if last_info.exists():
logger.log("=> loading checkpoint of the last-info '{:}' start".format(last_info))
last_info = torch.load(last_info)
start_epoch = last_info['epoch'] + 1
checkpoint = torch.load(last_info['last_checkpoint'])
assert last_info['epoch'] == checkpoint['epoch'], 'Last-Info is not right {:} vs {:}'.format(last_info, checkpoint['epoch'])
net.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
scheduler.load_state_dict(checkpoint['scheduler'])
logger.log("=> load-ok checkpoint '{:}' (epoch {:}) done" .format(logger.last_info(), checkpoint['epoch']))
else:
logger.log("=> do not find the last-info file : {:}".format(last_info))
start_epoch = 0
if args.eval_once:
logger.log("=> only evaluate the model once")
eval_results = eval_all(args, eval_loaders, net, criterion, 'eval-once', logger, opt_config)
logger.close() ; return
# Main Training and Evaluation Loop
start_time = time.time()
epoch_time = AverageMeter()
for epoch in range(start_epoch, opt_config.epochs):
scheduler.step()
need_time = convert_secs2time(epoch_time.avg * (opt_config.epochs-epoch), True)
epoch_str = 'epoch-{:03d}-{:03d}'.format(epoch, opt_config.epochs)
LRs = scheduler.get_lr()
logger.log('\n==>>{:s} [{:s}], [{:s}], LR : [{:.5f} ~ {:.5f}], Config : {:}'.format(time_string(), epoch_str, need_time, min(LRs), max(LRs), opt_config))
# train for one epoch
train_loss, train_nme = train(args, train_loader, net, criterion, optimizer, epoch_str, logger, opt_config)
# log the results
logger.log('==>>{:s} Train [{:}] Average Loss = {:.6f}, NME = {:.2f}'.format(time_string(), epoch_str, train_loss, train_nme*100))
# remember best prec@1 and save checkpoint
save_path = save_checkpoint({
'epoch': epoch,
'args' : deepcopy(args),
'arch' : model_config.arch,
'state_dict': net.state_dict(),
'scheduler' : scheduler.state_dict(),
'optimizer' : optimizer.state_dict(),
}, logger.path('model') / '{:}-{:}.pth'.format(model_config.arch, epoch_str), logger)
last_info = save_checkpoint({
'epoch': epoch,
'last_checkpoint': save_path,
}, logger.last_info(), logger)
eval_results = eval_all(args, eval_loaders, net, criterion, epoch_str, logger, opt_config)
# measure elapsed time
epoch_time.update(time.time() - start_time)
start_time = time.time()
logger.close()
criterion = torch.nn.BCEWithLogitsLoss()
print('[start triaing]')
best_acc = 0.0
best_roc_auc = 0.0
with tqdm(range(args.n_epochs),
desc='[Epoch]',
position=0,
leave=True,
disable=('DISABLE_TQDM' in os.environ)) as pbar:
for epoch in pbar:
# trainloader.sampler.set_epoch(epoch)
train(
model=model,
dataloader=trainloader,
optimizer=optimizer,
criterion=criterion,
device=args.device,
args=args # this is so bad
)
roc_auc, accuracy, loss = evaluate(model=model,
dataloader=valloader,
criterion=criterion,
device=args.device)
if roc_auc > best_roc_auc:
torch.save(
{
'epoch': epoch,
'accuracy': accuracy,
'roc_auc': roc_auc,
'model': model.module.state_dict(),
'optimizer': optimizer.state_dict()