def run(self, test):
"""Overrides to provide plugin hooks and defer all output to
the test result class.
"""
#from father class code
wrapper = self.config.plugins.prepareTest(test)
if wrapper is not None:
test = wrapper
wrapped = self.config.plugins.setOutputStream(self.stream)
if wrapped is not None:
self.stream = wrapped
result = self._makeResult()
start = time.time()
runtime = launcher.Runtime(self.config.options.config_file)
runtime.setup_environment()
runtime.start_test()
setattr(test.config, 'runtime', runtime)
test(result)
runtime.stop_test()
#from father class code
stop = time.time()
result.printErrors()
result.printSummary(start, stop)
self.config.plugins.finalize(result)
return result
def main(config):
# init loaders and base
loaders = ReIDLoaders(config)
base = Base(config)
# make directions
make_dirs(base.output_path)
# init logger
logger = Logger(os.path.join(config.output_path, 'log.txt'))
logger(config)
assert config.mode in ['train', 'test', 'visualize']
if config.mode == 'train': # train mode
# automatically resume model from the latest one
if config.auto_resume_training_from_lastest_steps:
start_train_epoch = base.resume_last_model()
# main loop
for current_epoch in range(start_train_epoch,
config.total_train_epochs):
# save model
base.save_model(current_epoch)
# train
_, results = train_an_epoch(config, base, loaders, current_epoch)
logger('Time: {}; Epoch: {}; {}'.format(time_now(),
current_epoch, results))
# test
base.save_model(config.total_train_epochs)
mAP, CMC, pres, recalls, thresholds = test(config, base, loaders)
logger('Time: {}; Test Dataset: {}, \nmAP: {} \nRank: {}'.format(
time_now(), config.test_dataset, mAP, CMC))
plot_prerecall_curve(config, pres, recalls, thresholds, mAP, CMC,
'none')
elif config.mode == 'test': # test mode
base.resume_from_model(config.resume_test_model)
mAP, CMC, pres, recalls, thresholds = test(config, base, loaders)
logger('Time: {}; Test Dataset: {}, \nmAP: {} \nRank: {}'.format(
time_now(), config.test_dataset, mAP, CMC))
logger(
'Time: {}; Test Dataset: {}, \nprecision: {} \nrecall: {}\nthresholds: {}'
.format(time_now(), config.test_dataset, mAP, CMC, pres, recalls,
thresholds))
plot_prerecall_curve(config, pres, recalls, thresholds, mAP, CMC,
'none')
elif config.mode == 'visualize': # visualization mode
base.resume_from_model(config.resume_visualize_model)
visualize(config, base, loaders)
def main(config):
# init loaders and base
loaders = ReIDLoaders(config)
base = Base(config)
# make directions
make_dirs(base.output_path)
# init logger
logger = Logger(os.path.join(config.output_path, 'log.txt'))
logger(config)
assert config.mode in ['train', 'test', 'visualize']
if config.mode == 'train': # train mode
# automatically resume model from the latest one
if config.auto_resume_training_from_lastest_steps:
print('resume', base.output_path)
start_train_epoch = base.resume_last_model()
#start_train_epoch = 0
# main loop
for current_epoch in range(start_train_epoch,
config.total_train_epochs + 1):
# save model
base.save_model(current_epoch)
# train
base.lr_scheduler.step(current_epoch)
_, results = train_an_epoch(config, base, loaders)
logger('Time: {}; Epoch: {}; {}'.format(time_now(),
current_epoch, results))
# test
base.save_model(config.total_train_epochs)
mAP, CMC = test(config, base, loaders)
logger('Time: {}; Test Dataset: {}, \nmAP: {} \nRank: {}'.format(
time_now(), config.test_dataset, mAP, CMC))
elif config.mode == 'test': # test mode
base.resume_from_model(config.resume_test_model)
mAP, CMC = test(config, base, loaders)
logger('Time: {}; Test Dataset: {}, \nmAP: {} \nRank: {} with len {}'.
format(time_now(), config.test_dataset, mAP, CMC, len(CMC)))
elif config.mode == 'visualize': # visualization mode
base.resume_from_model(config.resume_visualize_model)
visualize(config, base, loaders)
def get_key(self, event):
global serialNumber
if event.char in '0123456789':
self.serial += event.char
elif event.keysym == 'Return' and len(self.serial) > 2:
serialNumber = self.serial
result = test(self.serial)
enregistrer(self.serial, result)
if result == "pass":
level = logging.INFO
elif result == "lackOfTest":
level = logging.WARNING
elif result == "abort":
level = logging.ERROR
elif result == "unexpected":
level = logging.ERROR
else:
level = logging.CRITICAL
logger.log(level, self.serial + " " + result)
self.form.resultat.set(result)
self.serial = ''
def main(config):
loader = Loader(config)
base = Base(config, loader)
make_dirs(base.output_path)
make_dirs(base.save_logs_path)
make_dirs(base.save_model_path)
logger = Logger(os.path.join(base.save_logs_path, 'log.txt'))
logger(config)
if config.mode == 'train':
if config.resume_train_epoch >= 0:
base.resume_model(config.resume_train_epoch)
start_train_epoch = config.resume_train_epoch
else:
start_train_epoch = 0
if config.auto_resume_training_from_lastest_step:
root, _, files = os_walk(base.save_model_path)
if len(files) > 0:
indexes = []
for file in files:
indexes.append(int(
file.replace('.pkl', '').split('_')[-1]))
indexes = sorted(list(set(indexes)), reverse=False)
base.resume_model(indexes[-1])
start_train_epoch = indexes[-1]
logger(
'Time: {}, automatically resume training from the latest step (model {})'
.format(time_now(), indexes[-1]))
for current_epoch in range(start_train_epoch,
config.total_train_epoch):
base.save_model(current_epoch)
if current_epoch < config.use_graph:
_, result = train_meta_learning(base, loader)
logger('Time: {}; Epoch: {}; {}'.format(
time_now(), current_epoch, result))
if current_epoch + 1 >= 1 and (current_epoch + 1) % 40 == 0:
mAP, CMC = test(config, base, loader)
logger(
'Time: {}; Test on Target Dataset: {}, \nmAP: {} \n Rank: {}'
.format(time_now(), config.target_dataset, mAP, CMC))
else:
_, result = train_with_graph(config, base, loader)
logger('Time: {}; Epoch: {}; {}'.format(
time_now(), current_epoch, result))
if current_epoch + 1 >= 1 and (current_epoch + 1) % 5 == 0:
mAP, CMC = test_with_graph(config, base, loader)
logger(
'Time: {}; Test on Target Dataset: {}, \nmAP: {} \n Rank: {}'
.format(time_now(), config.target_dataset, mAP, CMC))
elif config.mode == 'test':
base.resume_model(config.resume_test_model)
mAP, CMC = test_with_graph(config, base, loader)
logger('Time: {}; Test on Target Dataset: {}, \nmAP: {} \n Rank: {}'.
format(time_now(), config.target_dataset, mAP, CMC))
def boucle():
while (True):
os.system('color 0B')
os.system('cls')
print("=" * 80)
print("\n\n\t\t\t")
ascii_banner = pyfiglet.figlet_format("PRET : DOUCHER")
print(ascii_banner)
print("\n\n\n" + "=" * 80)
inputUser = ""
while inputUser == "":
inputUser = str(input())
resultat = test(inputUser)
if resultat == "pass":
os.system('color 2E')
ascii_banner = pyfiglet.figlet_format("PASS")
print(ascii_banner)
elif resultat == "lackOfTest":
os.system('color 5E')
ascii_banner = pyfiglet.figlet_format("REPASSER TEST")
print(ascii_banner)
elif resultat == "abort":
os.system('color E0')
ascii_banner = pyfiglet.figlet_format("TEST ABORTED")
print(ascii_banner)
elif resultat == "unexpected":
os.system('color F0')
ascii_banner = pyfiglet.figlet_format("UNEXPECTED")
print(ascii_banner)
else:
os.system('color CE')
ascii_banner = pyfiglet.figlet_format("FAIL")
print(ascii_banner)
print(resultat)
enregistrer(inputUser, resultat)
time.sleep(0.45)
def test(self):
"""
ready = request.test()
if ( request.test() ):
print 'Nonblocking Send/Recv Operation completed!'
"""
# It's important to note that requests are only valid
# until the communication operation that they represent
# completes.
# A call to the C test() routine with an invalid
# request ID will crash.
if( self.valid ):
if( core.test( self.id ) ):
self.valid = False
return True
else:
return False
else:
return True
def main_worker(options):
torch.manual_seed(options['seed'])
os.environ['CUDA_VISIBLE_DEVICES'] = options['gpu']
use_gpu = torch.cuda.is_available()
if options['use_cpu']: use_gpu = False
if use_gpu:
print("Currently using GPU: {}".format(options['gpu']))
cudnn.benchmark = True
torch.cuda.manual_seed_all(options['seed'])
else:
print("Currently using CPU")
# Dataset
print("{} Preparation".format(options['dataset']))
if 'mnist' in options['dataset']:
Data = MNIST_OSR(known=options['known'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
trainloader, testloader, outloader = Data.train_loader, Data.test_loader, Data.out_loader
elif 'cifar10' == options['dataset']:
Data = CIFAR10_OSR(known=options['known'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
trainloader, testloader, outloader = Data.train_loader, Data.test_loader, Data.out_loader
elif 'svhn' in options['dataset']:
Data = SVHN_OSR(known=options['known'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
trainloader, testloader, outloader = Data.train_loader, Data.test_loader, Data.out_loader
elif 'cifar100' in options['dataset']:
Data = CIFAR10_OSR(known=options['known'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
trainloader, testloader = Data.train_loader, Data.test_loader
out_Data = CIFAR100_OSR(known=options['unknown'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
outloader = out_Data.test_loader
else:
Data = Tiny_ImageNet_OSR(known=options['known'], dataroot=options['dataroot'], batch_size=options['batch_size'], img_size=options['img_size'])
trainloader, testloader, outloader = Data.train_loader, Data.test_loader, Data.out_loader
options['num_classes'] = Data.num_classes
# Model
print("Creating model: {}".format(options['model']))
if options['cs']:
net = classifier32ABN(num_classes=options['num_classes'])
else:
net = classifier32(num_classes=options['num_classes'])
feat_dim = 128
if options['cs']:
print("Creating GAN")
nz, ns = options['nz'], 1
if 'tiny_imagenet' in options['dataset']:
netG = gan.Generator(1, nz, 64, 3)
netD = gan.Discriminator(1, 3, 64)
else:
netG = gan.Generator32(1, nz, 64, 3)
netD = gan.Discriminator32(1, 3, 64)
fixed_noise = torch.FloatTensor(64, nz, 1, 1).normal_(0, 1)
criterionD = nn.BCELoss()
# Loss
options.update(
{
'feat_dim': feat_dim,
'use_gpu': use_gpu
}
)
Loss = importlib.import_module('loss.'+options['loss'])
criterion = getattr(Loss, options['loss'])(**options)
if use_gpu:
net = nn.DataParallel(net).cuda()
criterion = criterion.cuda()
if options['cs']:
netG = nn.DataParallel(netG, device_ids=[i for i in range(len(options['gpu'].split(',')))]).cuda()
netD = nn.DataParallel(netD, device_ids=[i for i in range(len(options['gpu'].split(',')))]).cuda()
fixed_noise.cuda()
model_path = os.path.join(options['outf'], 'models', options['dataset'])
if not os.path.exists(model_path):
os.makedirs(model_path)
if options['dataset'] == 'cifar100':
model_path += '_50'
file_name = '{}_{}_{}_{}_{}'.format(options['model'], options['loss'], 50, options['item'], options['cs'])
else:
file_name = '{}_{}_{}_{}'.format(options['model'], options['loss'], options['item'], options['cs'])
if options['eval']:
net, criterion = load_networks(net, model_path, file_name, criterion=criterion)
results = test(net, criterion, testloader, outloader, epoch=0, **options)
print("Acc (%): {:.3f}\t AUROC (%): {:.3f}\t OSCR (%): {:.3f}\t".format(results['ACC'], results['AUROC'], results['OSCR']))
return results
params_list = [{'params': net.parameters()},
{'params': criterion.parameters()}]
if options['dataset'] == 'tiny_imagenet':
optimizer = torch.optim.Adam(params_list, lr=options['lr'])
else:
optimizer = torch.optim.SGD(params_list, lr=options['lr'], momentum=0.9, weight_decay=1e-4)
if options['cs']:
optimizerD = torch.optim.Adam(netD.parameters(), lr=options['gan_lr'], betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(netG.parameters(), lr=options['gan_lr'], betas=(0.5, 0.999))
if options['stepsize'] > 0:
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=[30,60,90,120])
start_time = time.time()
for epoch in range(options['max_epoch']):
print("==> Epoch {}/{}".format(epoch+1, options['max_epoch']))
if options['cs']:
train_cs(net, netD, netG, criterion, criterionD,
optimizer, optimizerD, optimizerG,
trainloader, epoch=epoch, **options)
train(net, criterion, optimizer, trainloader, epoch=epoch, **options)
if options['eval_freq'] > 0 and (epoch+1) % options['eval_freq'] == 0 or (epoch+1) == options['max_epoch']:
print("==> Test", options['loss'])
results = test(net, criterion, testloader, outloader, epoch=epoch, **options)
print("Acc (%): {:.3f}\t AUROC (%): {:.3f}\t OSCR (%): {:.3f}\t".format(results['ACC'], results['AUROC'], results['OSCR']))
save_networks(net, model_path, file_name, criterion=criterion)
if options['stepsize'] > 0: scheduler.step()
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
print("Finished. Total elapsed time (h:m:s): {}".format(elapsed))
return results
def main(config):
# loaders and base
loaders = Loaders(config)
base = Base(config, loaders)
# make dirs
make_dirs(config.save_images_path)
make_dirs(config.save_models_path)
make_dirs(config.save_features_path)
# logger
logger = Logger(os.path.join(config.output_path, 'log.txt'))
logger(config)
if config.mode == 'train':
# automatically resume model from the latest one
start_train_epoch = 0
root, _, files = os_walk(config.save_models_path)
if len(files) > 0:
# get indexes of saved models
indexes = []
for file in files:
indexes.append(int(file.replace('.pkl', '').split('_')[-1]))
# remove the bad-case and get available indexes
model_num = len(base.model_list)
available_indexes = copy.deepcopy(indexes)
for element in indexes:
if indexes.count(element) < model_num:
available_indexes.remove(element)
available_indexes = sorted(list(set(available_indexes)),
reverse=True)
unavailable_indexes = list(
set(indexes).difference(set(available_indexes)))
if len(available_indexes
) > 0: # resume model from the latest model
base.resume_model(available_indexes[0])
start_train_epoch = available_indexes[0] + 1
logger(
'Time: {}, automatically resume training from the latest step (model {})'
.format(time_now(), available_indexes[0]))
else: #
logger('Time: {}, there are no available models')
# main loop
for current_epoch in range(
start_train_epoch, config.warmup_reid_epoches +
config.warmup_gan_epoches + config.train_epoches):
# test
if current_epoch % 10 == 0 and current_epoch > config.warmup_reid_epoches + config.warmup_gan_epoches:
results = test(config, base, loaders, brief=True)
for key in results.keys():
logger('Time: {}\n Setting: {}\n {}'.format(
time_now(), key, results[key]))
# visualize generated images
if current_epoch % 10 == 0 or current_epoch <= 10:
visualize(config, loaders, base, current_epoch)
# train
if current_epoch < config.warmup_reid_epoches: # warmup reid model
results = train_an_epoch(config,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=True,
train_pixel=False,
optimize_sl_enc=True)
elif current_epoch < config.warmup_reid_epoches + config.warmup_gan_epoches: # warmup GAN model
results = train_an_epoch(config,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=False,
train_pixel=False,
optimize_sl_enc=False)
else: # joint train
results = train_an_epoch(config,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=True,
train_pixel=True,
optimize_sl_enc=True)
logger('Time: {}; Epoch: {}; {}'.format(time_now(),
current_epoch, results))
# save model
base.save_model(current_epoch)
# test
results = test(config, base, loaders, brief=False)
for key in results.keys():
logger('Time: {}\n Setting: {}\n {}'.format(
time_now(), key, results[key]))
elif config.mode == 'test':
# resume from pre-trained model and test
base.resume_model_from_path(config.pretrained_model_path,
config.pretrained_model_epoch)
results = test(config, base, loaders, brief=False)
for key in results.keys():
logger('Time: {}\n Setting: {}\n {}'.format(
time_now(), key, results[key]))
tgt_data_loader_test = get_data_loader(params.tgt_dataset, train=False)
# init models
classifier = init_model(net=Classifier(), restore=params.c_model_restore)
generator = init_model(net=Generator(), restore=params.g_model_restore)
critic = init_model(net=Discriminator(input_dims=params.d_input_dims,
hidden_dims=params.d_hidden_dims,
output_dims=params.d_output_dims),
restore=params.d_model_restore)
# train models
print("=== Training models ===")
print(">>> Classifier <<<")
print(classifier)
print(">>> Generator <<<")
print(generator)
print(">>> Critic <<<")
print(critic)
if not (params.eval_only and classifier.restored and generator.restored
and critic.restored):
classifier, generator = train(classifier, generator, critic,
src_data_loader, tgt_data_loader)
# evaluate models
print("=== Evaluating models ===")
print(">>> on source domain <<<")
test(classifier, generator, src_data_loader, params.src_dataset)
print(">>> on target domain <<<")
test(classifier, generator, tgt_data_loader, params.tgt_dataset)
def main(config):
# loaders and base
loaders = Loaders(config)
base = Base(config, loaders)
# make dirs
make_dirs(config.save_images_path)
make_dirs(config.save_wp_models_path)
make_dirs(config.save_st_models_path)
make_dirs(config.save_features_path)
logger = setup_logger('adaptation_reid', config.output_path, if_train=True)
if config.mode == 'train':
if config.resume:
# automatically resume model from the latest one
if config.resume_epoch_num == 0:
start_train_epoch = 0
root, _, files = os_walk(config.save_models_path)
if len(files) > 0:
# get indexes of saved models
indexes = []
for file in files:
indexes.append(
int(file.replace('.pkl', '').split('_')[-1]))
# remove the bad-case and get available indexes
model_num = len(base.model_list)
available_indexes = copy.deepcopy(indexes)
for element in indexes:
if indexes.count(element) < model_num:
available_indexes.remove(element)
available_indexes = sorted(list(set(available_indexes)),
reverse=True)
unavailable_indexes = list(
set(indexes).difference(set(available_indexes)))
if len(available_indexes
) > 0: # resume model from the latest model
base.resume_model(available_indexes[0])
start_train_epoch = available_indexes[0] + 1
logger.info(
'Time: {}, automatically resume training from the latest step (model {})'
.format(time_now(), available_indexes[0]))
else: #
logger.info('Time: {}, there are no available models')
else:
start_train_epoch = config.resume_epoch_num
else:
start_train_epoch = 0
# main loop
for current_epoch in range(
start_train_epoch, config.warmup_reid_epoches +
config.warmup_gan_epoches + config.warmup_adaptation_epoches):
# train
if current_epoch < config.warmup_reid_epoches: # warmup reid model
results = train_an_epoch(config,
0,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=True,
self_training=False,
optimize_sl_enc=True,
train_adaptation=False)
elif current_epoch < config.warmup_reid_epoches + config.warmup_gan_epoches: # warmup GAN model
results = train_an_epoch(config,
0,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=False,
self_training=False,
optimize_sl_enc=False,
train_adaptation=False) # joint train
elif current_epoch < config.warmup_reid_epoches + config.warmup_gan_epoches + config.warmup_adaptation_epoches: #warmup adaptation
results = train_an_epoch(config,
0,
loaders,
base,
current_epoch,
train_gan=True,
train_reid=False,
self_training=False,
optimize_sl_enc=False,
train_adaptation=True)
print("another epoch")
logger.info('Time: {}; Epoch: {}; {}'.format(
time_now(), current_epoch, results))
# save model
if current_epoch % config.save_model_interval == 0:
base.save_model(current_epoch, True)
if current_epoch % config.test_model_interval == 0:
visualize(config, loaders, base, current_epoch)
test(config, base, loaders, epoch=0, brief=False)
total_wp_epoches = config.warmup_reid_epoches + config.warmup_gan_epoches
for iter_n in range(config.iteration_number):
src_dataset, src_dataloader, trg_dataset, trg_dataloader = loaders.get_self_train_loaders(
)
trg_labeled_dataloader = generate_labeled_dataset(
base, iter_n, src_dataset, src_dataloader, trg_dataset,
trg_dataloader)
for epoch in range(total_wp_epoches + 1, config.self_train_epoch):
results = train_an_epoch(
config,
iter_n,
loaders,
base,
epoch,
train_gan=True,
train_reid=False,
self_training=True,
optimize_sl_enc=True,
trg_labeled_loader=trg_labeled_dataloader)
logger.info('Time: {}; Epoch: {}; {}'.format(
time_now(), current_epoch, results))
if epoch % config.save_model_interval == 0:
base.save_model(iter_n * config.self_train_epoch + epoch,
False)
elif config.mode == 'test':
# resume from pre-trained model and test
base.resume_model_from_path(config.pretrained_model_path,
config.pretrained_model_epoch)
cmc, map = test(config, base, loaders, epoch=100, brief=False)
import importlib
import core
def clsr():
core.os.system("cls")
core.detect_face()
inp = -1
while inp != 3:
clsr()
print("Recognizer App")
print("=================")
print("1. Face Recognition")
print("2. Live Recognition lock")
print("3. Live Recognition unlock")
print("3. Exit")
print(">> ", end="")
inp = int(input())
if (inp == 1):
clsr()
core.test()
elif (inp == 2):
clsr()
core.live('lock')
elif (inp == 3):
clsr()
core.live('unlock')
def main():
torch.manual_seed(options['seed'])
os.environ['CUDA_VISIBLE_DEVICES'] = options['gpu']
use_gpu = torch.cuda.is_available()
if options['use_cpu']: use_gpu = False
feat_dim = 2 if 'cnn' in options['model'] else 512
options.update(
{
'feat_dim': feat_dim,
'use_gpu': use_gpu
}
)
if use_gpu:
print("Currently using GPU: {}".format(options['gpu']))
cudnn.benchmark = True
torch.cuda.manual_seed_all(options['seed'])
else:
print("Currently using CPU")
dataset = datasets.create(options['dataset'], **options)
out_dataset = datasets.create(options['out_dataset'], **options)
trainloader, testloader = dataset.trainloader, dataset.testloader
outloader = out_dataset.testloader
options.update(
{
'num_classes': dataset.num_classes
}
)
print("Creating model: {}".format(options['model']))
if 'cnn' in options['model']:
net = ConvNet(num_classes=dataset.num_classes)
else:
if options['cs']:
net = resnet34ABN(num_classes=dataset.num_classes, num_bns=2)
else:
net = ResNet34(dataset.num_classes)
if options['cs']:
print("Creating GAN")
nz = options['nz']
netG = gan.Generator32(1, nz, 64, 3) # ngpu, nz, ngf, nc
netD = gan.Discriminator32(1, 3, 64) # ngpu, nc, ndf
fixed_noise = torch.FloatTensor(64, nz, 1, 1).normal_(0, 1)
criterionD = nn.BCELoss()
Loss = importlib.import_module('loss.'+options['loss'])
criterion = getattr(Loss, options['loss'])(**options)
if use_gpu:
net = nn.DataParallel(net, device_ids=[i for i in range(len(options['gpu'].split(',')))]).cuda()
criterion = criterion.cuda()
if options['cs']:
netG = nn.DataParallel(netG, device_ids=[i for i in range(len(options['gpu'].split(',')))]).cuda()
netD = nn.DataParallel(netD, device_ids=[i for i in range(len(options['gpu'].split(',')))]).cuda()
fixed_noise.cuda()
model_path = os.path.join(options['outf'], 'models', options['dataset'])
file_name = '{}_{}_{}_{}_{}'.format(options['model'], options['dataset'], options['loss'], str(options['weight_pl']), str(options['cs']))
if options['eval']:
net, criterion = load_networks(net, model_path, file_name, criterion=criterion)
results = test(net, criterion, testloader, outloader, epoch=0, **options)
print("Acc (%): {:.3f}\t AUROC (%): {:.3f}\t OSCR (%): {:.3f}\t".format(results['ACC'], results['AUROC'], results['OSCR']))
return
params_list = [{'params': net.parameters()},
{'params': criterion.parameters()}]
optimizer = torch.optim.Adam(params_list, lr=options['lr'])
if options['cs']:
optimizerD = torch.optim.Adam(netD.parameters(), lr=options['gan_lr'], betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(netG.parameters(), lr=options['gan_lr'], betas=(0.5, 0.999))
if options['stepsize'] > 0:
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=[30, 60, 90, 120])
start_time = time.time()
score_now = 0.0
for epoch in range(options['max_epoch']):
print("==> Epoch {}/{}".format(epoch+1, options['max_epoch']))
if options['cs']:
train_cs(net, netD, netG, criterion, criterionD,
optimizer, optimizerD, optimizerG,
trainloader, epoch=epoch, **options)
train(net, criterion, optimizer, trainloader, epoch=epoch, **options)
if options['eval_freq'] > 0 and (epoch+1) % options['eval_freq'] == 0 or (epoch+1) == options['max_epoch']:
print("==> Test")
results = test(net, criterion, testloader, outloader, epoch=epoch, **options)
print("Acc (%): {:.3f}\t AUROC (%): {:.3f}\t OSCR (%): {:.3f}\t".format(results['ACC'], results['AUROC'], results['OSCR']))
save_networks(net, model_path, file_name, criterion=criterion)
if options['cs']:
save_GAN(netG, netD, model_path, file_name)
fake = netG(fixed_noise)
GAN_path = os.path.join(model_path, 'samples')
mkdir_if_missing(GAN_path)
vutils.save_image(fake.data, '%s/gan_samples_epoch_%03d.png'%(GAN_path, epoch), normalize=True)
if options['stepsize'] > 0: scheduler.step()
elapsed = round(time.time() - start_time)
elapsed = str(datetime.timedelta(seconds=elapsed))
print("Finished. Total elapsed time (h:m:s): {}".format(elapsed))
def main(config):
# init loaders and base
loaders = Loaders(config)
base = Base(config, loaders)
# make directions
make_dirs(base.output_path)
make_dirs(base.save_model_path)
make_dirs(base.save_logs_path)
make_dirs(base.save_visualize_market_path)
make_dirs(base.save_visualize_duke_path)
# init logger
logger = Logger(
os.path.join(os.path.join(config.output_path, 'logs/'), 'log.txt'))
logger('\n' * 3)
logger(config)
if config.mode == 'train': # train mode
# resume model from the resume_train_epoch
if config.resume_train_epoch >= 0:
base.resume_model(config.resume_train_epoch)
start_train_epoch = config.resume_train_epoch
else:
start_train_epoch = 0
# automatically resume model from the latest one
if config.auto_resume_training_from_lastest_steps:
root, _, files = os_walk(base.save_model_path)
if len(files) > 0:
# get indexes of saved models
indexes = []
for file in files:
indexes.append(int(
file.replace('.pkl', '').split('_')[-1]))
indexes = sorted(list(set(indexes)), reverse=False)
# resume model from the latest model
base.resume_model(indexes[-1])
#
start_train_epoch = indexes[-1]
logger(
'Time: {}, automatically resume training from the latest step (model {})'
.format(time_now(), indexes[-1]))
# main loop
for current_epoch in range(start_train_epoch,
config.total_train_epochs):
# save model
base.save_model(current_epoch)
# train
base.lr_scheduler.step(current_epoch)
_, results = train_an_epoch(config, base, loaders)
logger('Time: {}; Epoch: {}; {}'.format(time_now(),
current_epoch, results))
# test
if (current_epoch + 1) % 40 == 0 and current_epoch + 1 >= 0:
market_map, market_rank = test(config, base, loaders, 'market')
duke_map, duke_rank = test(config, base, loaders, 'duke')
logger(
'Time: {}, Dataset: Market \nmAP: {} \nRank: {}'.format(
time_now(), market_map, market_rank))
logger('Time: {}, Dataset: Duke \nmAP: {} \nRank: {}'.format(
time_now(), duke_map, duke_rank))
logger('')
elif config.mode == 'test': # test mode
# resume from the resume_test_epoch
if config.resume_test_epoch >= 0:
base.resume_model(config.resume_test_epoch)
# test
market_map, market_rank = test(config, base, loaders, 'market')
duke_map, duke_rank = test(config, base, loaders, 'duke')
logger('Time: {}, Dataset: Market \nmAP: {} \nRank: {}'.format(
time_now(), market_map, market_rank))
logger('Time: {}, Dataset: Duke \nmAP: {} \nRank: {}'.format(
time_now(), duke_map, duke_rank))
logger('')
elif config.mode == 'visualize': # visualization mode
# resume from the resume_visualize_epoch
if config.resume_visualize_epoch >= 0:
base.resume_model(config.resume_visualize_epoch)
# visualization
visualize_ranking_list(config, base, loaders, 'market')
visualize_ranking_list(config, base, loaders, 'duke')
'pascalvoc12',
transform=transform,
target_transform=target_transform,
custom_type='B')
tasks.append(t1)
tasks.append(t2)
prev_tasks = []
task_loss_after_each_train = []
if opt.pretrained:
model = load_pretrained(opt.load_pretrained)
start_index = opt.pretrained
test_results = test(tasks,
model,
opt,
visualizer=visualizer,
limit_updates=opt.limit_test_updates)
# for i in range(0,start_index):
# test_results=test(tasks,model,opt)
# task_loss_after_each_train.append(test_results)
# prev_tasks.append(tasks[i])
else:
t = tasks[0]
model = networks.__dict__[opt.model](t.name,
t.type,
t.num_classes,
encoder=opt.encoder,
decoder=opt.decoder,
setting=opt.model_setting)
for t in tasks: