def get_data(data_dir, source, target, height, width, batch_size, num_instance=2, workers=8):
dataset = DA(data_dir, source, target)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
num_classes = dataset.num_train_ids
train_transformer = T.Compose([
T.Resize((256, 128), interpolation=3),
T.Pad(10),
T.RandomCrop((256,128)),
T.RandomHorizontalFlip(0.5),
T.RandomRotation(5),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.Resize((256, 128), interpolation=3),
T.ToTensor(),
normalizer,
])
source_train_loader = DataLoader(
Preprocessor_occluded(dataset.source_train, root=osp.join(dataset.source_images_dir, dataset.source_train_path),
transform=train_transformer, train=True),
batch_size=batch_size, num_workers=workers,
sampler=IdentitySampler(dataset.source_train, num_instance),
pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor_occluded(dataset.query,
root=osp.join(dataset.target_images_dir, dataset.query_path), transform=test_transformer),
batch_size=42, num_workers=workers,
shuffle=False, pin_memory=True)
gallery_loader = DataLoader(
Preprocessor_occluded(dataset.gallery,
root=osp.join(dataset.target_images_dir, dataset.gallery_path), transform=test_transformer),
batch_size=42, num_workers=workers,
shuffle=False, pin_memory=True)
return dataset, num_classes, source_train_loader, query_loader, gallery_loader
def get_data(data_dir, height, width, batch_size, num_instances, re=0, workers=8):
dataset = DA(data_dir)
test_dataset = TotalData(data_dir)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
num_classes = dataset.num_source_ids
train_transformer = T.Compose([
T.Resize((256, 128), interpolation=3),
T.Pad(10),
T.RandomCrop((256,128)),
T.RandomHorizontalFlip(0.5),
T.RandomRotation(5),
T.ColorJitter(brightness=(0.5, 2.0), saturation=(0.5, 2.0), hue=(-0.1, 0.1)),
T.ToTensor(),
normalizer,
# T.RandomErasing(EPSILON=re),
])
test_transformer = T.Compose([
T.Resize((256, 128), interpolation=3),
T.ToTensor(),
normalizer,
])
# Train
source_train_loader = DataLoader(
Preprocessor(dataset.source_train,
transform=train_transformer),
batch_size=batch_size, num_workers=workers,
# shuffle=True, pin_memory=True, drop_last=True)
sampler=RandomIdentitySampler(dataset.source_train, batch_size, num_instances),
pin_memory=True, drop_last=True)
# Test
grid_query_loader = DataLoader(
Preprocessor(test_dataset.grid_query,
root=osp.join(test_dataset.grid_images_dir, test_dataset.query_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
grid_gallery_loader = DataLoader(
Preprocessor(test_dataset.grid_gallery,
root=osp.join(test_dataset.grid_images_dir, test_dataset.gallery_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
prid_query_loader = DataLoader(
Preprocessor(test_dataset.prid_query,
root=osp.join(test_dataset.prid_images_dir, test_dataset.query_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
prid_gallery_loader = DataLoader(
Preprocessor(test_dataset.prid_gallery,
root=osp.join(test_dataset.prid_images_dir, test_dataset.gallery_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
viper_query_loader = DataLoader(
Preprocessor(test_dataset.viper_query,
root=osp.join(test_dataset.viper_images_dir, test_dataset.query_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
viper_gallery_loader = DataLoader(
Preprocessor(test_dataset.viper_gallery,
root=osp.join(test_dataset.viper_images_dir, test_dataset.gallery_path), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
ilid_query_loader = DataLoader(
Preprocessor(test_dataset.ilid_query,
root=osp.join(test_dataset.ilid_images_dir, "images"), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
ilid_gallery_loader = DataLoader(
Preprocessor(test_dataset.ilid_gallery,
root=osp.join(test_dataset.ilid_images_dir, "images"), transform=test_transformer),
batch_size=64, num_workers=4,
shuffle=False, pin_memory=True)
return dataset, test_dataset, num_classes, source_train_loader, grid_query_loader, grid_gallery_loader,prid_query_loader, prid_gallery_loader,viper_query_loader, viper_gallery_loader, ilid_query_loader, ilid_gallery_loader
def get_data(dataname, data_dir, model, matcher, save_path, args):
root = osp.join(data_dir, dataname)
dataset = datasets.create(dataname, root, combine_all=args.combine_all)
num_classes = dataset.num_train_ids
train_transformer = T.Compose([
T.Resize((args.height, args.width),
interpolation=InterpolationMode.BICUBIC),
T.Pad(10),
T.RandomCrop((args.height, args.width)),
T.RandomHorizontalFlip(0.5),
T.RandomRotation(5),
T.ColorJitter(brightness=(0.5, 2.0),
contrast=(0.5, 2.0),
saturation=(0.5, 2.0),
hue=(-0.1, 0.1)),
T.RandomOcclusion(args.min_size, args.max_size),
T.ToTensor(),
])
test_transformer = T.Compose([
T.Resize((args.height, args.width),
interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
])
train_path = osp.join(dataset.images_dir, dataset.train_path)
train_loader = DataLoader(
Preprocessor(dataset.train,
root=train_path,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=args.workers,
sampler=GraphSampler(dataset.train, train_path, test_transformer,
model, matcher, args.batch_size,
args.num_instance, args.test_gal_batch,
args.test_prob_batch, save_path, args.gs_verbose),
pin_memory=True)
query_loader = DataLoader(Preprocessor(dataset.query,
root=osp.join(
dataset.images_dir,
dataset.query_path),
transform=test_transformer),
batch_size=args.test_fea_batch,
num_workers=args.workers,
shuffle=False,
pin_memory=True)
gallery_loader = DataLoader(Preprocessor(dataset.gallery,
root=osp.join(
dataset.images_dir,
dataset.gallery_path),
transform=test_transformer),
batch_size=args.test_fea_batch,
num_workers=args.workers,
shuffle=False,
pin_memory=True)
return dataset, num_classes, train_loader, query_loader, gallery_loader
def main(args):
cudnn.deterministic = False
cudnn.benchmark = True
exp_database_dir = osp.join(args.exp_dir, string.capwords(args.dataset))
output_dir = osp.join(exp_database_dir, args.method, args.sub_method)
log_file = osp.join(output_dir, 'log.txt')
# Redirect print to both console and log file
sys.stdout = Logger(log_file)
# Create data loaders
dataset, num_classes, train_loader, _, _ = \
get_data(args.dataset, args.data_dir, args.height, args.width, args.batch_size, args.combine_all,
args.workers, args.test_fea_batch)
# Create model
#model = seTest.resnst50().cuda()
model = resmap.create(args.arch,
ibn_type=args.ibn,
final_layer=args.final_layer,
neck=args.neck).cuda()
num_features = model.num_features
#num_features = 64
# print(model)
# print('\n')
feamap_factor = {'layer2': 8, 'layer3': 16, 'layer4': 32}
hei = args.height // feamap_factor[args.final_layer]
wid = args.width // feamap_factor[args.final_layer]
matcher = QAConv(num_features, hei, wid).cuda()
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')
# Criterion
criterion = ClassMemoryLoss(matcher, num_classes, num_features, hei, wid,
args.mem_batch_size).cuda()
# Optimizer
base_param_ids = set(map(id, model.base.parameters()))
new_params = [p for p in model.parameters() if id(p) not in base_param_ids]
param_groups = [{
'params': model.base.parameters(),
'lr': 0.1 * args.lr
}, {
'params': new_params,
'lr': args.lr
}, {
'params': criterion.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.SGD(param_groups,
lr=args.lr,
momentum=0.9,
weight_decay=5e-4,
nesterov=True)
# Load from checkpoint
start_epoch = 0
if args.resume or args.evaluate:
print('Loading checkpoint...')
if args.resume and (args.resume != 'ori'):
checkpoint = load_checkpoint(args.resume)
else:
checkpoint = load_checkpoint(
osp.join(output_dir, 'checkpoint.pth.tar'))
model.load_state_dict(checkpoint['model'])
criterion.load_state_dict(checkpoint['criterion'])
optimizer.load_state_dict(checkpoint['optim'])
start_epoch = checkpoint['epoch']
print("=> Start epoch {} ".format(start_epoch))
elif args.pre_epochs > 0:
pre_tr = PreTrainer(model, criterion, optimizer, train_loader,
args.pre_epochs, args.max_steps, args.num_trials)
result_file = osp.join(exp_database_dir, args.method,
'pretrain_metric.txt')
model, criterion, optimizer = pre_tr.train(result_file, args.method,
args.sub_method)
# Decay LR by a factor of 0.1 every step_size epochs
lr_scheduler = StepLR(optimizer,
step_size=args.step_size,
gamma=0.1,
last_epoch=start_epoch - 1)
model = nn.DataParallel(model).cuda()
criterion = nn.DataParallel(criterion).cuda()
enhance_data_aug = False
if not args.evaluate:
# Trainer
trainer = Trainer(model, criterion)
t0 = time.time()
# Start training
for epoch in range(start_epoch, args.epochs):
loss, acc = trainer.train(epoch, train_loader, optimizer)
lr = list(map(lambda group: group['lr'], optimizer.param_groups))
lr_scheduler.step()
train_time = time.time() - t0
print(
'* Finished epoch %d at lr=[%g, %g, %g]. Loss: %.3f. Acc: %.2f%%. Training time: %.0f seconds. \n'
%
(epoch + 1, lr[0], lr[1], lr[2], loss, acc * 100, train_time))
save_checkpoint(
{
'model': model.module.state_dict(),
'criterion': criterion.module.state_dict(),
'optim': optimizer.state_dict(),
'epoch': epoch + 1,
},
fpath=osp.join(output_dir, 'checkpoint.pth.tar'))
if not enhance_data_aug and epoch < args.epochs - 1 and acc > args.acc_thr:
enhance_data_aug = True
print('\nAcc = %.2f%% > %.2f%%. Start to Flip and Block.\n' %
(acc * 100, args.acc_thr * 100))
train_transformer = T.Compose([
T.Resize((args.height, args.width), interpolation=3),
T.Pad(10),
T.RandomCrop((args.height, args.width)),
T.RandomHorizontalFlip(0.5),
T.RandomRotation(5),
T.ColorJitter(brightness=(0.5, 2.0),
contrast=(0.5, 2.0),
saturation=(0.5, 2.0),
hue=(-0.1, 0.1)),
T.RandomOcclusion(args.min_size, args.max_size),
T.ToTensor(),
])
train_loader = DataLoader(Preprocessor(
dataset.train,
root=osp.join(dataset.images_dir, dataset.train_path),
transform=train_transformer),
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
pin_memory=True,
drop_last=True)
# Final test
print('Evaluate the learned model:')
t0 = time.time()
# Evaluator
evaluator = Evaluator(model)
avg_rank1 = 0
avg_mAP = 0
num_testsets = 0
results = {}
test_names = args.testset.strip().split(',')
for test_name in test_names:
if test_name not in datasets.names():
print('Unknown dataset: %s.' % test_name)
continue
testset, test_query_loader, test_gallery_loader = \
get_test_data(test_name, args.data_dir, args.height, args.width, args.workers, args.test_fea_batch)
if not args.do_tlift:
testset.has_time_info = False
test_rank1, test_mAP, test_rank1_rerank, test_mAP_rerank, test_rank1_tlift, test_mAP_tlift, test_dist, \
test_dist_rerank, test_dist_tlift, pre_tlift_dict = \
evaluator.evaluate(matcher, testset, test_query_loader, test_gallery_loader,
args.test_gal_batch, args.test_prob_batch,
args.tau, args.sigma, args.K, args.alpha)
results[test_name] = [test_rank1, test_mAP]
if test_name != args.dataset:
avg_rank1 += test_rank1
avg_mAP += test_mAP
num_testsets += 1
if testset.has_time_info:
print(
' %s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f,'
' rank1_rerank_tlift=%.1f, mAP_rerank_tlift=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
print(' %s: rank1=%.1f, mAP=%.1f.\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
test_name + '_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if testset.has_time_info:
f.write(
'\t%s: rank1=%.1f, mAP=%.1f, rank1_rerank=%.1f, mAP_rerank=%.1f, rank1_rerank_tlift=%.1f, '
'mAP_rerank_tlift=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100,
test_rank1_rerank * 100, test_mAP_rerank * 100,
test_rank1_tlift * 100, test_mAP_tlift * 100))
else:
f.write('\t%s: rank1=%.1f, mAP=%.1f.\n\n' %
(test_name, test_rank1 * 100, test_mAP * 100))
if args.save_score:
test_gal_list = np.array(
[fname for fname, _, _, _ in testset.gallery], dtype=np.object)
test_prob_list = np.array(
[fname for fname, _, _, _ in testset.query], dtype=np.object)
test_gal_ids = [pid for _, pid, _, _ in testset.gallery]
test_prob_ids = [pid for _, pid, _, _ in testset.query]
test_gal_cams = [c for _, _, c, _ in testset.gallery]
test_prob_cams = [c for _, _, c, _ in testset.query]
test_score_file = osp.join(exp_database_dir, args.method,
args.sub_method,
'%s_score.mat' % test_name)
sio.savemat(test_score_file, {
'score': 1. - test_dist,
'score_rerank': 1. - test_dist_rerank,
'score_tlift': 1. - test_dist_tlift,
'gal_time': pre_tlift_dict['gal_time'],
'prob_time': pre_tlift_dict['prob_time'],
'gal_list': test_gal_list,
'prob_list': test_prob_list,
'gal_ids': test_gal_ids,
'prob_ids': test_prob_ids,
'gal_cams': test_gal_cams,
'prob_cams': test_prob_cams
},
oned_as='column',
do_compression=True)
test_time = time.time() - t0
avg_rank1 /= num_testsets
avg_mAP /= num_testsets
for key in results.keys():
print('%s: rank1=%.1f%%, mAP=%.1f%%.' %
(key, results[key][0] * 100, results[key][1] * 100))
print('Average: rank1=%.2f%%, mAP=%.2f%%.\n\n' %
(avg_rank1 * 100, avg_mAP * 100))
result_file = osp.join(exp_database_dir, args.method,
args.sub_method[:-5] + '_avg_results.txt')
with open(result_file, 'a') as f:
f.write('%s/%s:\n' % (args.method, args.sub_method))
if not args.evaluate:
f.write('\t Loss: %.3f, acc: %.2f%%. ' % (loss, acc * 100))
f.write("Train: %.0fs. " % train_time)
f.write("Test: %.0fs. " % test_time)
f.write('Rank1: %.2f%%, mAP: %.2f%%.\n' %
(avg_rank1 * 100, avg_mAP * 100))
for key in results.keys():
f.write('\t %s: Rank1: %.1f%%, mAP: %.1f%%.\n' %
(key, results[key][0] * 100, results[key][1] * 100))
f.write('\n')
if not args.evaluate:
print('Finished training at epoch %d, loss = %.3f, acc = %.2f%%.\n' %
(epoch + 1, loss, acc * 100))
print(
"Total training time: %.3f sec. Average training time per epoch: %.3f sec."
% (train_time, train_time / (args.epochs - start_epoch + 1)))
print("Total testing time: %.3f sec.\n" % test_time)
for arg in sys.argv:
print('%s ' % arg, end='')
print('\n')