def get_train_loader(dataset, height, width, batch_size, workers,
num_instances, iters, trainset=None):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.RandomHorizontalFlip(p=0.5),
T.Pad(10),
T.RandomCrop((height, width)),
T.ToTensor(),
normalizer,
T.RandomErasing(probability=0.5, mean=[0.485, 0.456, 0.406])
])
train_set = dataset.train if trainset is None else trainset
rmgs_flag = num_instances > 0
if rmgs_flag:
sampler = RandomMultipleGallerySampler(train_set, num_instances)
else:
sampler = None
train_loader = IterLoader(
DataLoader(Preprocessor(train_set, root=dataset.images_dir,
transform=train_transformer, mutual=False),
batch_size=batch_size, num_workers=workers, sampler=sampler,
shuffle=not rmgs_flag, pin_memory=True, drop_last=True), length=iters)
return train_loader
def get_data(name, split_id, data_dir, height, width, batch_size,
num_instances, workers, combine_trainval):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, num_val=0.1, split_id=split_id)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_set = dataset.trainval if combine_trainval else dataset.train
num_classes = (dataset.num_trainval_ids
if combine_trainval else dataset.num_train_ids)
train_transformer = T.Compose([
Resize((256, 128)),
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(Preprocessor(train_set,
root=dataset.images_dir,
transform=train_transformer),
batch_size=batch_size,
num_workers=workers,
sampler=RandomIdentitySampler(
train_set, num_instances),
pin_memory=True,
drop_last=True)
val_loader = DataLoader(Preprocessor(dataset.val,
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
test_loader = DataLoader(Preprocessor(
list(set(dataset.query) | set(dataset.gallery)),
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
return dataset, num_classes, train_loader, val_loader, test_loader
def get_data(dataname, data_dir, height, width, batch_size, camstyle=0, re=0, workers=8):
root = osp.join(data_dir, dataname)
dataset = datasets.create(dataname, root)
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.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
T.RandomErasing(EPSILON=re),
])
test_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(
Preprocessor(dataset.train, root=osp.join(dataset.images_dir, dataset.train_path),
transform=train_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor(dataset.query,
root=osp.join(dataset.images_dir, dataset.query_path), transform=test_transformer),
batch_size=batch_size, num_workers=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=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
if camstyle <= 0:
camstyle_loader = None
else:
camstyle_loader = DataLoader(
Preprocessor(dataset.camstyle, root=osp.join(dataset.images_dir, dataset.camstyle_path),
transform=train_transformer),
batch_size=camstyle, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
return dataset, num_classes, train_loader, query_loader, gallery_loader, camstyle_loader
def get_data(data_dir, source, target, height, width, batch_size, re=0, 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.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
T.RandomErasing(EPSILON=re),
])
test_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
source_train_loader = DataLoader(
Preprocessor(dataset.source_train, root=osp.join(dataset.source_images_dir, dataset.source_train_path),
transform=train_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
target_train_loader = DataLoader(
UnsupervisedCamStylePreprocessor(dataset.target_train,
root=osp.join(dataset.target_images_dir, dataset.target_train_path),
camstyle_root=osp.join(dataset.target_images_dir,
dataset.target_train_camstyle_path),
num_cam=dataset.target_num_cam, transform=train_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor(dataset.query,
root=osp.join(dataset.target_images_dir, dataset.query_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
gallery_loader = DataLoader(
Preprocessor(dataset.gallery,
root=osp.join(dataset.target_images_dir, dataset.gallery_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
return dataset, num_classes, source_train_loader, target_train_loader, query_loader, gallery_loader
def get_data(name, split_id, data_dir, big_height, big_width, target_height,
target_width, batch_size, num_instances, workers,
combine_trainval):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, split_id=split_id, download=True)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_set = dataset.trainval if combine_trainval else dataset.train
num_classes = (dataset.num_trainval_ids
if combine_trainval else dataset.num_train_ids)
train_transformer = T.Compose([
T.ResizeRandomCrop(big_height, big_width, target_height, target_width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
T.RandomErasing(0.5),
])
test_transformer = T.Compose([
T.RectScale(target_height, target_width),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(
Attribute_Preprocessor(train_set,
root=dataset.images_dir,
transform=train_transformer),
batch_size=batch_size,
num_workers=workers,
sampler=RandomIdentityAttributeSampler(train_set, num_instances),
pin_memory=True,
drop_last=True)
test_loader = DataLoader(Attribute_Preprocessor(
list(set(dataset.query) | set(dataset.gallery)),
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
return dataset, num_classes, train_loader, test_loader
def get_data(sourceName, mteName, split_id, data_dir, height, width,
batch_size, workers, combine,num_instances=8):
root = osp.join(data_dir, sourceName)
rootMte = osp.join(data_dir, mteName)
sourceSet = datasets.create(sourceName, root, num_val=0.1, split_id=split_id)
mteSet = datasets.create(mteName, rootMte, num_val=0.1, split_id=split_id)
num_classes = sourceSet.num_trainval_ids if combine else sourceSet.num_train_ids
class_meta = mteSet.num_trainval_ids if combine else mteSet.num_train_ids
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
defen_train_transformer = T.Compose([
Resize((height, width)),
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
meta_train_loader = DataLoader(
Preprocessor(sourceSet.trainval, root=sourceSet.images_dir,
transform=defen_train_transformer),
batch_size=batch_size, num_workers=workers,
sampler=RandomIdentitySampler(sourceSet.trainval, num_instances),
pin_memory=True, drop_last=True)
meta_test_loader=DataLoader(
Preprocessor(mteSet.trainval, root=mteSet.images_dir,
transform=defen_train_transformer),
batch_size=batch_size, num_workers=workers,
sampler=RandomIdentitySampler(mteSet.trainval, num_instances),
pin_memory=True, drop_last=True)
sc_test_loader = DataLoader(
Preprocessor(list(set(sourceSet.query) | set(sourceSet.gallery)),
root=sourceSet.images_dir, transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
return sourceSet, mteSet, num_classes, meta_train_loader, meta_test_loader,sc_test_loader,class_meta
def get_dataloader(self, dataset, training=False):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if training:
transformer = T.Compose([
T.RandomSizedRectCrop(self.data_height, self.data_width),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
else:
transformer = T.Compose([
T.Resize((self.data_height, self.data_width)),
T.ToTensor(),
normalizer,
])
if training and self.num_classes == 0:
data_loader = DataLoader(Preprocessor(dataset,
root='',
transform=transformer),
batch_size=self.batch_size,
num_workers=self.data_workers,
sampler=RandomIdentitySampler(
dataset, self.num_instances),
pin_memory=True,
drop_last=training)
else:
data_loader = DataLoader(Preprocessor(dataset,
root='',
transform=transformer),
batch_size=self.batch_size,
num_workers=self.data_workers,
shuffle=training,
pin_memory=True,
drop_last=training)
current_status = "Training" if training else "Test"
print("create dataloader for {} with batch_size {}".format(
current_status, self.batch_size))
return data_loader
def main(args):
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Redirect print to both console and log file
if not args.evaluate:
sys.stdout = Logger(osp.join(args.logs_dir, 'log.txt'))
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
## get_source_data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get_target_data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the last feature embedding layer
# Net structure: avgpool -> FC(2048) -> FC(args.features)
num_class = 0
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=num_class, num_split=args.num_split, cluster=args.dce_loss) #duke
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=num_class, num_split=args.num_split, cluster=args.dce_loss)
else:
raise RuntimeError('Please specify the number of classes (ids) of the network.')
# Load from checkpoint
start_epoch = best_top1 = 0
if args.resume:
print('Resuming checkpoints from finetuned model on another dataset...\n')
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint, strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model')
model = nn.DataParallel(model).cuda()
# Distance metric
metric = DistanceMetric(algorithm=args.dist_metric)
# Evaluator
evaluator = Evaluator(model, print_freq=args.print_freq)
print("Test with the original model trained on source domain:")
best_top1 = evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
if args.evaluate:
return
# Criterion
criterion = []
criterion.append(TripletLoss(margin=args.margin,num_instances=args.num_instances).cuda())
criterion.append(TripletLoss(margin=args.margin,num_instances=args.num_instances).cuda())
#multi lr
base_param_ids = set(map(id, model.module.base.parameters()))
new_params = [p for p in model.parameters() if
id(p) not in base_param_ids]
param_groups = [
{'params': model.module.base.parameters(), 'lr_mult': 1.0},
{'params': new_params, 'lr_mult': 1.0}]
# Optimizer
optimizer = torch.optim.SGD(param_groups, lr=args.lr,
momentum=0.9, weight_decay=args.weight_decay)
##### adjust lr
def adjust_lr(epoch):
if epoch <= 7:
lr = args.lr
elif epoch <=14:
lr = 0.3 * args.lr
else:
lr = 0.1 * args.lr
for g in optimizer.param_groups:
g['lr'] = lr * g.get('lr_mult', 1)
##### training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
Resize((args.height,args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# Start training
iter_nums = args.iteration
start_epoch = args.start_epoch
cluster_list = []
top_percent = args.rho
EF = 100 // iter_nums + 1
eug = None
for iter_n in range(start_epoch, iter_nums):
#### get source datas' feature
if args.load_dist and iter_n == 0:
dist = pickle.load(open('dist' + str(args.num_split) + '.pkl', 'rb'))
euclidean_dist_list = dist['euclidean']
rerank_dist_list = dist['rerank']
else:
source_features, _ = extract_features(model, src_extfeat_loader, for_eval=False)
if isinstance(source_features[src_dataset.trainval[0][0]], list):
len_f = len(source_features[src_dataset.trainval[0][0]])
source_features = [torch.cat([source_features[f][i].unsqueeze(0) for f, _, _ in src_dataset.trainval], 0) for i in range(len_f)]
else:
source_features = torch.cat([source_features[f].unsqueeze(0) for f, _, _ in src_dataset.trainval], 0) # synchronization feature order with s_dataset.trainval
#### extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(iter_n+1))
target_features, _ = extract_features(model, tgt_extfeat_loader, for_eval=False)
if isinstance(target_features[tgt_dataset.trainval[0][0]], list):
len_f = len(target_features[tgt_dataset.trainval[0][0]])
target_features = [torch.cat([target_features[f][i].unsqueeze(0) for f, _, _ in tgt_dataset.trainval], 0) for i in range(len_f)]
else:
target_features = torch.cat([target_features[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval], 0) # synchronization feature order with dataset.trainval
#### calculate distance and rerank result
print('Calculating feature distances...')
# target_features = target_features.numpy()
euclidean_dist_list, rerank_dist_list = compute_dist(
source_features, target_features, lambda_value=args.lambda_value, no_rerank=args.no_rerank, num_split=args.num_split) # lambda=1 means only source dist
del target_features
del source_features
labels_list, cluster_list = generate_selflabel(
euclidean_dist_list, rerank_dist_list, iter_n, args, cluster_list)
#### generate new dataset
train_loader = generate_dataloader(tgt_dataset, labels_list, train_transformer, iter_n, args)
if iter_n == 5:
u_data, l_data = updata_lable(tgt_dataset, labels_list[0], args.tgt_dataset, sample=args.sample)
eug = EUG(model_name=args.arch, batch_size=args.batch_size, mode=args.mode, num_classes=num_class,
data_dir=args.data_dir, l_data=l_data, u_data=u_data, print_freq=args.print_freq,
save_path=args.logs_dir, pretrained_model=model, rerank=True)
eug.model = model
if eug is not None:
nums_to_select = int(min((iter_n + 1) * int(len(u_data) // (iter_nums)), len(u_data)))
pred_y, pred_score = eug.estimate_label()
print('This is running {} with EF= {}%, step {}:\t Nums_to_be_select {}, \t Logs-dir {}'.format(
args.mode, EF, iter_n+1, nums_to_select, args.logs_dir
))
selected_idx = eug.select_top_data(pred_score, nums_to_select)
new_train_data = eug.generate_new_train_data(selected_idx, pred_y)
eug_dataloader = eug.get_dataloader(new_train_data, training=True)
top1 = iter_trainer(model, tgt_dataset, train_loader, eug_dataloader, test_loader, optimizer,
criterion, args.epochs, args.logs_dir, args.print_freq, args.lr)
eug.model = model
del train_loader
# del eug_dataloader
else:
top1 = iter_trainer(model, tgt_dataset, train_loader, None, test_loader, optimizer,
criterion, args.epochs, args.logs_dir, args.print_freq, args.lr)
del train_loader
is_best = top1 > best_top1
best_top1 = max(top1, best_top1)
save_checkpoint({
'state_dict': model.module.state_dict(),
'epoch': iter_n + 1,
'best_top1': best_top1,
# 'num_ids': num_ids,
}, is_best, fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar'))
print('\n * Finished epoch {:3d} top1: {:5.1%} best: {:5.1%}{}\n'.
format(iter_n+1, top1, best_top1, ' *' if is_best else ''))
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError('Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print('Resuming checkpoints from finetuned model on another dataset...\n')
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
# evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# if args.evaluate: return
# Criterion
criterion = [
# TripletLoss(args.margin, args.num_instances, isAvg=True, use_semi=True).cuda(),
SortedTripletLoss(args.margin, isAvg=True).cuda(),
# HoughTripletLoss(args.margin, args.num_instances, isAvg=True, use_semi=True).cuda(),
# None,
None, None, None
]
# Optimizer
optimizer = torch.optim.Adam(
model.parameters(), lr=args.lr
)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height,args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
evaluator = Evaluator(model, print_freq=args.print_freq)
evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
st_model = ST_Model(tgt_dataset.meta['num_cameras'])
same = None
# train_loader2 = None
best_mAP = 0
# # Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model, src_extfeat_loader, print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([source_features[f].unsqueeze(0) for f, _, _, _ in src_dataset.train], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(iter_n+1))
target_features, tarNames = extract_features(model, tgt_extfeat_loader, print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([target_features[f].unsqueeze(0) for f, _, _, _ in tgt_dataset.trainval], 0)
# target_real_label = np.asarray([tarNames[f].unsqueeze(0) for f, _, _, _ in tgt_dataset.trainval])
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features, target_features, lambda_value=args.lambda_value)
ranking = np.argsort(rerank_dist)[:, 1:]
if iter_n != 0:
st_dist = np.zeros(rerank_dist.shape)
for i, (_, _, c1, t1) in enumerate(tgt_dataset.trainval):
for j, (_, _, c2, t2) in enumerate(tgt_dataset.trainval):
if not same.in_peak(c1, c2, t1, t2, 0.25):
st_dist[i, j] = 1
rerank_dist = rerank_dist + st_dist * 10
# if iter_n > 0:
# rerank_dist = st_model.apply(rerank_dist, tgt_dataset.trainval, tgt_dataset.trainval)
cluster = HDBSCAN(metric='precomputed', min_samples=10)
# select & cluster images as training set of this epochs
clusterRes = cluster.fit(rerank_dist.astype(np.float64))
labels, label_num = clusterRes.labels_, clusterRes.labels_.max() + 1
centers = np.zeros((label_num, target_features.shape[1]))
nums = [0] * target_features.shape[1]
print('clusters num =', label_num)
# generate new dataset
new_dataset = []
index = -1
for (fname, _, cam, timestamp), label in zip(tgt_dataset.trainval, labels):
index += 1
if label == -1: continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, cam, timestamp))
centers[label] += target_features[index]
nums[label] += 1
print('Iteration {} have {} training images'.format(iter_n+1, len(new_dataset)))
# learn ST model
# if iter_n % 2 == 0:
# if iter_n == 0:
# cluster = HDBSCAN(metric='precomputed', min_samples=10)
# # select & cluster images as training set of this epochs
# clusterRes = cluster.fit(rerank_dist.astype(np.float64))
# labels, label_num = clusterRes.labels_, clusterRes.labels_.max() + 1
# centers = np.zeros((label_num, target_features.shape[1]))
# nums = [0] * target_features.shape[1]
# print('clusters num =', label_num)
#
# # generate new dataset
# new_dataset = []
# index = -1
# for (fname, _, cam, timestamp), label in zip(tgt_dataset.trainval, labels):
# index += 1
# if label == -1: continue
# # dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
# new_dataset.append((fname, label, cam, timestamp))
# centers[label] += target_features[index]
# nums[label] += 1
# print('Iteration {} have {} training images'.format(iter_n + 1, len(new_dataset)))
# same, _ = st_model.fit(new_dataset)
# st_model.fit(tgt_dataset.trainval)
same, _ = st_model.fit(new_dataset)
train_loader = DataLoader(
Preprocessor(new_dataset, root=tgt_dataset.images_dir, transform=train_transformer),
batch_size=args.batch_size, num_workers=4,
sampler=RandomIdentitySampler(new_dataset, args.num_instances),
pin_memory=True, drop_last=True
)
def filter(i, j):
_, _, c1, t1 = tgt_dataset.trainval[i]
_, _, c2, t2 = tgt_dataset.trainval[j]
return st_model.val(c1, c2, t1, t2) > 0.01
# if iter_n == 0:
# ranking = np.argsort(rerank_dist)[:, 1:]
# dukemtmc
# cluster_size = 23.535612535612536
# market1501
cluster_size = 17.22503328894807
must_conn = int(cluster_size / 2)
might_conn = int(cluster_size * 2)
length = len(tgt_dataset.trainval)
pos = [[] for _ in range(length)]
neg = [[] for _ in range(length)]
for i in range(length):
for j_ in range(might_conn):
j = ranking[i][j_]
if j_ < must_conn and i in ranking[j][:must_conn]:
pos[i].append(j)
elif i in ranking[j][:might_conn] and filter(i, j):
pos[i].append(j)
else:
neg[i].append(j)
# pos[i] = pos[i][-1:]
# neg[i] = neg[i][:1]
SP, SF, DP, DF = 0, 0, 0, 0
for i in range(length):
for j in pos[i]:
if tgt_dataset.trainval[i][1] == tgt_dataset.trainval[j][1]:
SP += 1
else:
SF += 1
for j in neg[i]:
if tgt_dataset.trainval[i][1] == tgt_dataset.trainval[j][1]:
DP += 1
else:
DF += 1
print('stat: %.1f %.1f %.3f, %.3f' % ((SP + SF) / length, (DP + DF) / length, SP / (SP + SF), DF / (DP + DF)))
train_loader2 = DataLoader(
Preprocessor(tgt_dataset.trainval, root=tgt_dataset.images_dir, transform=train_transformer),
batch_size=args.batch_size, num_workers=4,
# sampler=RandomIdentitySampler(new_dataset, args.num_instances),
# shuffle=True,
sampler=TripletSampler(tgt_dataset.trainval, pos, neg),
pin_memory=True, drop_last=True
)
# learn visual model
for i in range(label_num):
centers[i] /= nums[i]
criterion[3] = ClassificationLoss(normalize(centers, axis=1)).cuda()
classOptimizer = torch.optim.Adam([
{'params': model.parameters()},
{'params': criterion[3].classifier.parameters(), 'lr': 1e-3}
], lr=args.lr)
# trainer = HoughTrainer(model, st_model, train_loader, criterion, classOptimizer)
trainer = ClassificationTrainer(model, train_loader, criterion, classOptimizer)
trainer2 = Trainer(model, train_loader2, criterion, optimizer)
for epoch in range(args.epochs):
trainer.train(epoch)
if epoch % 8 == 0:
trainer2.train(epoch)
# evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
if rank_score.map > best_mAP:
best_mAP = rank_score.map
save_checkpoint({
'state_dict': model.module.state_dict(),
'epoch': epoch + 1, 'best_top1': rank_score.market1501[0],
}, True, fpath=osp.join(args.logs_dir, 'adapted.pth.tar'))
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
save_checkpoint({
'state_dict': model.module.state_dict(),
'epoch': epoch + 1, 'best_top1': rank_score.market1501[0],
}, False, fpath=osp.join(args.logs_dir, 'adapted.pth.tar'))
return (rank_score.map, rank_score.market1501[0])
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
# Distance metric
metric = DistanceMetric(algorithm=args.dist_metric)
# Evaluator
evaluator = Evaluator(model, print_freq=args.print_freq)
print(
"Test with the original model trained on target domain (direct transfer):"
)
evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
if args.evaluate:
return
# Criterion
criterion = [
TripletLoss(args.margin, args.num_instances).cuda(),
TripletLoss(args.margin, args.num_instances).cuda(),
]
# Optimizer
optimizer = torch.optim.SGD(
model.parameters(),
lr=args.lr,
momentum=0.9,
)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, _ = extract_features(model,
tgt_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval
], 0)
# calculate distance and rerank result
print('Calculating feature distances...')
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features,
target_features,
lambda_value=args.lambda_value)
if iter_n == 0:
# DBSCAN cluster
tri_mat = np.triu(rerank_dist, 1) # tri_mat.dim=2
tri_mat = tri_mat[np.nonzero(tri_mat)] # tri_mat.dim=1
tri_mat = np.sort(tri_mat, axis=None)
top_num = np.round(args.rho * tri_mat.size).astype(int)
eps = tri_mat[:top_num].mean()
print('eps in cluster: {:.3f}'.format(eps))
cluster = DBSCAN(eps=eps,
min_samples=4,
metric='precomputed',
n_jobs=8)
# select & cluster images as training set of this epochs
print('Clustering and labeling...')
labels = cluster.fit_predict(rerank_dist)
num_ids = len(set(labels)) - 1
print('Iteration {} have {} training ids'.format(iter_n + 1, num_ids))
# generate new dataset
new_dataset = []
for (fname, _, _), label in zip(tgt_dataset.trainval, labels):
if label == -1:
continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, 0))
print('Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
train_loader = DataLoader(Preprocessor(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# train model with new generated dataset
trainer = Trainer(model, criterion, print_freq=args.print_freq)
evaluator = Evaluator(model, print_freq=args.print_freq)
# Start training
for epoch in range(args.epochs):
trainer.train(epoch, train_loader, optimizer)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
return (rank_score.map, rank_score.market1501[0])
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
# Distance metric
# metric = DistanceMetric(algorithm=args.dist_metric)
# Evaluator
evaluator = Evaluator(model, print_freq=args.print_freq)
print(
"Test with the original model trained on source domain (direct transfer):"
)
rank_score_best = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
best_map = rank_score_best.map #market1501[0]-->rank-1
if args.evaluate:
return
# Criterion
criterion = [
TripletLoss(args.margin, args.num_instances).cuda(),
TripletLoss(args.margin, args.num_instances).cuda(),
AccumulatedLoss(args.margin, args.num_instances).cuda(),
nn.CrossEntropyLoss().cuda()
]
# Optimizer
optimizer = torch.optim.SGD(
model.parameters(),
lr=args.lr,
momentum=0.9,
)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0 #this value controls the usage of source data
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, _ = extract_features(model,
tgt_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval
], 0)
# calculate distance and rerank result
print('Calculating feature distances...')
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features,
target_features,
lambda_value=args.lambda_value)
if iter_n == 0:
# DBSCAN cluster
tri_mat = np.triu(rerank_dist, 1) # tri_mat.dim=2
tri_mat = tri_mat[np.nonzero(tri_mat)] # tri_mat.dim=1
tri_mat = np.sort(tri_mat, axis=None)
top_num = np.round(args.rho * tri_mat.size).astype(int)
eps = tri_mat[:top_num].mean()
print('eps in cluster: {:.3f}'.format(eps))
cluster = DBSCAN(eps=eps,
min_samples=4,
metric='precomputed',
n_jobs=8)
# HDBSCAN cluster
import hdbscan
cluster_hdbscan = hdbscan.HDBSCAN(min_cluster_size=10,
min_samples=4,
metric='precomputed')
# select & cluster images as training set of this epochs
print('Clustering and labeling...')
if args.use_hdbscan_clustering:
print(
'Use the better chlustering algorithm HDBSCAN for clustering'
)
labels = cluster_hdbscan.fit_predict(rerank_dist)
else:
print('Use DBSCAN for clustering')
labels = cluster.fit_predict(rerank_dist)
num_ids = len(set(labels)) - 1
print('Only do once, Iteration {} have {} training ids'.format(
iter_n + 1, num_ids))
# generate new dataset
new_dataset = []
for (fname, _, _), label in zip(tgt_dataset.trainval, labels):
if label == -1:
continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, 0))
print('Only do once, Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
train_loader = DataLoader(
Preprocessor_return_index(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# init pseudo/fake labels, y_tilde in cvpr19's paper:
new_label = np.zeros([len(new_dataset), num_ids])
# init y_tilde, let softmax(y_tilde) is noisy labels
for index, (imgs, _, pids, _, index) in enumerate(train_loader):
index = index.numpy()
onehot = torch.zeros(pids.size(0),
num_ids).scatter_(1, pids.view(-1, 1),
10.0)
onehot = onehot.numpy()
new_label[index, :] = onehot
# Using clustered label to init the new classifier:
classifier = nn.Linear(2048, num_ids, bias=False)
classifier.apply(weights_init_classifier)
classifier = nn.DataParallel(classifier).cuda()
optimizer_cla = torch.optim.SGD(classifier.parameters(),
lr=args.lr * 10,
momentum=0.9)
# train model with new generated dataset
trainer = Trainer_with_learnable_label(model,
classifier,
criterion,
print_freq=args.print_freq)
evaluator = Evaluator(model, print_freq=args.print_freq)
# Start training
for epoch in range(args.epochs):
trainer.train(epoch, train_loader, new_label, optimizer,
optimizer_cla)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
#Save the best ckpt:
rank1 = rank_score.market1501[0]
mAP = rank_score.map
is_best_mAP = mAP > best_map
best_map = max(mAP, best_map)
save_checkpoint(
{
'state_dict': model.module.state_dict(),
'epoch': iter_n + 1,
'best_mAP': best_map,
# 'num_ids': num_ids,
},
is_best_mAP,
fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar'))
print(
'\n * Finished epoch {:3d} top1: {:5.1%} mAP: {:5.1%} best_mAP: {:5.1%}{}\n'
.format(iter_n + 1, rank1, mAP, best_map,
' *' if is_best_mAP else ''))
return (rank_score.map, rank_score.market1501[0])
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
# Criterion
criterion = [
TripletLoss(args.margin, args.num_instances, use_semi=False).cuda(),
TripletLoss(args.margin, args.num_instances, use_semi=False).cuda()
]
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# # Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, _ = extract_features(model,
tgt_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval
], 0)
# calculate distance and rerank result
print('Calculating feature distances...')
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features,
target_features,
lambda_value=args.lambda_value)
if iter_n == 0:
# DBSCAN cluster
tri_mat = np.triu(rerank_dist, 1) # tri_mat.dim=2
tri_mat = tri_mat[np.nonzero(tri_mat)] # tri_mat.dim=1
tri_mat = np.sort(tri_mat, axis=None)
top_num = np.round(args.rho * tri_mat.size).astype(int)
eps = tri_mat[:top_num].mean()
print('eps in cluster: {:.3f}'.format(eps))
cluster = DBSCAN(eps=eps,
min_samples=4,
metric='precomputed',
n_jobs=8)
# select & cluster images as training set of this epochs
print('Clustering and labeling...')
labels = cluster.fit_predict(rerank_dist)
num_ids = len(set(labels)) - 1
print('Iteration {} have {} training ids'.format(iter_n + 1, num_ids))
# generate new dataset
new_dataset = []
# assign label for target ones
newLab = labelNoise(torch.from_numpy(target_features),
torch.from_numpy(labels))
# unknownFeats = target_features[labels==-1,:]
counter = 0
from collections import defaultdict
realIDs, fakeIDs = defaultdict(list), []
for (fname, realID, cam), label in zip(tgt_dataset.trainval, newLab):
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, cam))
realIDs[realID].append(counter)
fakeIDs.append(label)
counter += 1
precision, recall, fscore = calScores(realIDs, np.asarray(fakeIDs))
print('Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
print(
f'precision:{precision * 100}, recall:{100 * recall}, fscore:{fscore}'
)
train_loader = DataLoader(Preprocessor(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
trainer = Trainer(model, criterion)
# Start training
for epoch in range(args.epochs):
trainer.train(epoch, train_loader, optimizer) # to at most 80%
# test only
evaluator = Evaluator(model, print_freq=args.print_freq)
# rank_score = evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
save_checkpoint(
{
'state_dict': model.module.state_dict(),
'epoch': epoch + 1,
'best_top1': rank_score.market1501[0],
},
True,
fpath=osp.join(args.logs_dir, 'adapted.pth.tar'))
return rank_score.map, rank_score.market1501[0]
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
coModel = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
coModel = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
coModel.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
coModel = nn.DataParallel(coModel).cuda()
# evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# if args.evaluate: return
# Criterion
criterion = [
TripletLoss(args.margin,
args.num_instances,
isAvg=False,
use_semi=False).cuda(),
TripletLoss(args.margin,
args.num_instances,
isAvg=False,
use_semi=False).cuda(),
]
# Optimizer
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
coOptimizer = torch.optim.Adam(coModel.parameters(), lr=args.lr)
optims = [optimizer, coOptimizer]
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# # Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, tarNames = extract_features(
model, tgt_extfeat_loader, print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval
], 0)
target_real_label = np.asarray(
[tarNames[f].unsqueeze(0) for f, _, _ in tgt_dataset.trainval])
numTarID = len(set(target_real_label))
# calculate distance and rerank result
print('Calculating feature distances...')
target_features = target_features.numpy()
cluster = KMeans(n_clusters=numTarID, n_jobs=8, n_init=1)
# select & cluster images as training set of this epochs
print('Clustering and labeling...')
clusterRes = cluster.fit(target_features)
labels, centers = clusterRes.labels_, clusterRes.cluster_centers_
labels = splitLowconfi(target_features, labels, centers)
# num_ids = len(set(labels))
# print('Iteration {} have {} training ids'.format(iter_n+1, num_ids))
# generate new dataset
new_dataset, unknown_dataset = [], []
# assign label for target ones
unknownLab = labelNoise(torch.from_numpy(target_features),
torch.from_numpy(labels))
# unknownFeats = target_features[labels==-1,:]
unCounter = 0
for (fname, _, cam), label in zip(tgt_dataset.trainval, labels):
if label == -1:
unknown_dataset.append(
(fname, int(unknownLab[unCounter]), cam)) # unknown data
unCounter += 1
continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, cam))
print('Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
train_loader = DataLoader(Preprocessor(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# hard samples
unLoader = DataLoader(Preprocessor(unknown_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
unknown_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# train model with new generated dataset
trainer = CoTrainerAsy(model, coModel, train_loader, unLoader,
criterion, optims)
# trainer = CoTeaching(
# model, coModel, train_loader, unLoader, criterion, optims
# )
# trainer = CoTrainerAsySep(
# model, coModel, train_loader, unLoader, criterion, optims
# )
evaluator = Evaluator(model, print_freq=args.print_freq)
#evaluatorB = Evaluator(coModel, print_freq=args.print_freq)
# Start training
for epoch in range(args.epochs):
trainer.train(epoch,
remRate=0.2 + (0.6 / args.iteration) *
(1 + iter_n)) # to at most 80%
# trainer.train(epoch, remRate=0.7+(0.3/args.iteration)*(1+iter_n))
# test only
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
#print('co-model:\n')
#rank_score = evaluatorB.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
save_checkpoint(
{
'state_dict': model.module.state_dict(),
'epoch': epoch + 1,
'best_top1': rank_score.market1501[0],
},
True,
fpath=osp.join(args.logs_dir, 'adapted.pth.tar'))
return (rank_score.map, rank_score.market1501[0])
def get_data(data_dir, source, target, height, width, batch_size, re=0, workers=8):
dataset = DA(data_dir, source, target)
dataset_2 = DA(data_dir, target, source)
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((height, width), interpolation=3),
T.RandomHorizontalFlip(p=0.5),
T.Pad(10),
T.RandomCrop((height, width)),
T.ToTensor(),
normalizer,
# T.RandomErasing(EPSILON=re),
T.RandomErasing(probability=0.4, mean=[0.485, 0.456, 0.406])
])
train_transformer_2 = T.Compose([
T.Resize((height, width), interpolation=3),
T.RandomHorizontalFlip(p=0.5),
T.Pad(10),
T.RandomCrop((height, width)),
T.ToTensor(),
normalizer,
# T.RandomErasing(EPSILON=re),
T.RandomErasing(probability=0.4, mean=[0.485, 0.456, 0.406])
])
test_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
'''
num_instances=4
rmgs_flag = num_instances > 0
if rmgs_flag:
sampler = RandomIdentitySampler(dataset.target_train, num_instances)
else:
sampler = None
'''
source_train_loader = DataLoader(
Preprocessor(dataset.source_train, root=osp.join(dataset.source_images_dir, dataset.source_train_path),
transform=train_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
num_instances=0
rmgs_flag = num_instances > 0
if rmgs_flag:
sampler = RandomIdentitySampler(dataset.target_train, num_instances)
else:
sampler = None
target_train_loader = DataLoader(
UnsupervisedCamStylePreprocessor(dataset.target_train,
root=osp.join(dataset.target_images_dir, dataset.target_train_path),
camstyle_root=osp.join(dataset.target_images_dir,
dataset.target_train_camstyle_path),
num_cam=dataset.target_num_cam, transform=train_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor(dataset.query,
root=osp.join(dataset.target_images_dir, dataset.query_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
query_loader_2 = DataLoader(
Preprocessor(dataset_2.query,
root=osp.join(dataset_2.target_images_dir, dataset_2.query_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
gallery_loader = DataLoader(
Preprocessor(dataset.gallery,
root=osp.join(dataset.target_images_dir, dataset.gallery_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
gallery_loader_2 = DataLoader(
Preprocessor(dataset_2.gallery,
root=osp.join(dataset_2.target_images_dir, dataset_2.gallery_path), transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
return dataset,dataset_2, num_classes, source_train_loader, target_train_loader, query_loader, gallery_loader, query_loader_2, gallery_loader_2
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
# evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# if args.evaluate: return
# Criterion
criterion = [
TripletLoss(args.margin, args.num_instances, isAvg=True,
use_semi=True).cuda(),
TripletLoss(args.margin, args.num_instances, isAvg=True,
use_semi=True).cuda(), None, None
]
# Optimizer
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
evaluator = Evaluator(model, print_freq=args.print_freq)
evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# # Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, tarNames = extract_features(
model, tgt_extfeat_loader, print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0)
for f, _, _, _ in tgt_dataset.trainval
], 0)
# target_real_label = np.asarray([tarNames[f].unsqueeze(0) for f, _, _, _ in tgt_dataset.trainval])
# calculate distance and rerank result
# method 1
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features,
target_features,
lambda_value=args.lambda_value)
# method 2
# distmat_qq = calDis(source_features, source_features)
# distmat_qg = calDis(source_features, target_features)
# distmat_gg = calDis(target_features, target_features)
# rerank_dist = re_ranking2(distmat_qg.numpy(), distmat_qq.numpy(), distmat_gg.numpy())
cluster = HDBSCAN(metric='precomputed', min_samples=10)
# select & cluster images as training set of this epochs
clusterRes = cluster.fit(rerank_dist)
labels, label_num = clusterRes.labels_, clusterRes.labels_.max() + 1
centers = np.zeros((label_num, target_features.shape[1]))
nums = [0] * target_features.shape[1]
print('clusters num =', label_num)
# generate new dataset
new_dataset = []
index = -1
for (fname, _, cam, timestamp), label in zip(tgt_dataset.trainval,
labels):
index += 1
if label == -1: continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
new_dataset.append((fname, label, cam, timestamp))
centers[label] += target_features[index]
nums[label] += 1
print('Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
train_loader = DataLoader(Preprocessor(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
for i in range(label_num):
centers[i] /= nums[i]
criterion[3] = ClassificationLoss(normalize(centers, axis=1)).cuda()
classOptimizer = torch.optim.Adam(
[{
'params': model.parameters()
}, {
'params': criterion[3].classifier.parameters(),
'lr': 1e-3
}],
lr=args.lr)
class_trainer = ClassificationTrainer(model, train_loader, criterion,
classOptimizer)
for epoch in range(args.epochs):
class_trainer.train(epoch)
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
save_checkpoint(
{
'state_dict': model.module.state_dict(),
'epoch': epoch + 1,
'best_top1': rank_score.market1501[0],
},
True,
fpath=osp.join(args.logs_dir, 'adapted.pth.tar'))
return (rank_score.map, rank_score.market1501[0])
def get_data(name, data_dir, height, width, batch_size, workers,
combine_trainval, crop, tracking_icams, fps, re=0, num_instances=0, camstyle=0, zju=0, colorjitter=0):
# if name == 'market1501':
# root = osp.join(data_dir, 'Market-1501-v15.09.15')
# elif name == 'duke_reid':
# root = osp.join(data_dir, 'DukeMTMC-reID')
# elif name == 'duke_tracking':
# root = osp.join(data_dir, 'DukeMTMC')
# else:
# root = osp.join(data_dir, name)
if name == 'duke_tracking':
if tracking_icams != 0:
tracking_icams = [tracking_icams]
else:
tracking_icams = list(range(1, 9))
dataset = datasets.create(name, data_dir, data_type='tracking_gt', iCams=tracking_icams, fps=fps,
trainval=combine_trainval)
elif name == 'aic_tracking':
dataset = datasets.create(name, data_dir, data_type='tracking_gt', fps=fps, trainval=combine_trainval)
else:
dataset = datasets.create(name, data_dir)
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.ColorJitter(brightness=0.1 * colorjitter, contrast=0.1 * colorjitter, saturation=0.1 * colorjitter, hue=0),
T.Resize((height, width)),
T.RandomHorizontalFlip(),
T.Pad(10 * crop),
T.RandomCrop((height, width)),
T.ToTensor(),
normalizer,
T.RandomErasing(probability=re),
])
test_transformer = T.Compose([
T.Resize((height, width)),
# T.RectScale(height, width, interpolation=3),
T.ToTensor(),
normalizer,
])
if zju:
train_loader = DataLoader(
Preprocessor(dataset.train, root=dataset.train_path, transform=train_transformer),
batch_size=batch_size, num_workers=workers,
sampler=ZJU_RandomIdentitySampler(dataset.train, batch_size, num_instances) if num_instances else None,
shuffle=False if num_instances else True, pin_memory=True, drop_last=False if num_instances else True)
else:
train_loader = DataLoader(
Preprocessor(dataset.train, root=dataset.train_path, transform=train_transformer),
batch_size=batch_size, num_workers=workers,
sampler=RandomIdentitySampler(dataset.train, num_instances) if num_instances else None,
shuffle=False if num_instances else True, pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor(dataset.query, root=dataset.query_path, transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
gallery_loader = DataLoader(
Preprocessor(dataset.gallery, root=dataset.gallery_path, transform=test_transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
if camstyle <= 0:
camstyle_loader = None
else:
camstyle_loader = DataLoader(
Preprocessor(dataset.camstyle, root=dataset.camstyle_path, transform=train_transformer),
batch_size=camstyle, num_workers=workers,
shuffle=True, pin_memory=True, drop_last=True)
return dataset, num_classes, train_loader, query_loader, gallery_loader, camstyle_loader
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Create data loaders
assert args.num_instances > 1, "num_instances should be greater than 1"
assert args.batch_size % args.num_instances == 0, \
'num_instances should divide batch_size'
if args.height is None or args.width is None:
args.height, args.width = (144, 56) if args.arch == 'inception' else \
(256, 128)
# get source data
src_dataset, src_extfeat_loader = \
get_source_data(args.src_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# get target data
tgt_dataset, num_classes, tgt_extfeat_loader, test_loader = \
get_data(args.tgt_dataset, args.data_dir, args.height,
args.width, args.batch_size, args.workers)
# Create model
# Hacking here to let the classifier be the number of source ids
if args.src_dataset == 'dukemtmc':
model = models.create(args.arch, num_classes=632, pretrained=False)
elif args.src_dataset == 'market1501':
model = models.create(args.arch, num_classes=676, pretrained=False)
elif args.src_dataset == 'msmt17':
model = models.create(args.arch, num_classes=1041, pretrained=False)
elif args.src_dataset == 'cuhk03':
model = models.create(args.arch, num_classes=1230, pretrained=False)
else:
raise RuntimeError(
'Please specify the number of classes (ids) of the network.')
# Load from checkpoint
if args.resume:
print(
'Resuming checkpoints from finetuned model on another dataset...\n'
)
checkpoint = load_checkpoint(args.resume)
model.load_state_dict(checkpoint['state_dict'], strict=False)
else:
raise RuntimeWarning('Not using a pre-trained model.')
model = nn.DataParallel(model).cuda()
evaluator = Evaluator(model, print_freq=args.print_freq)
evaluator.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# if args.evaluate: return
# Criterion
criterion = [
HoughTripletLoss(args.margin,
args.num_instances,
isAvg=False,
use_semi=False).cuda(),
HoughTripletLoss(args.margin,
args.num_instances,
isAvg=False,
use_semi=False).cuda()
]
# Optimizer
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
# training stage transformer on input images
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((args.height, args.width)),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer,
T.RandomErasing(probability=0.5, sh=0.2, r1=0.3)
])
# # Start training
for iter_n in range(args.iteration):
if args.lambda_value == 0:
source_features = 0
else:
# get source datas' feature
source_features, _ = extract_features(model,
src_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with src_dataset.train
source_features = torch.cat([
source_features[f].unsqueeze(0)
for f, _, _, _ in src_dataset.train
], 0)
# extract training images' features
print('Iteration {}: Extracting Target Dataset Features...'.format(
iter_n + 1))
target_features, _ = extract_features(model,
tgt_extfeat_loader,
print_freq=args.print_freq)
# synchronization feature order with dataset.train
target_features = torch.cat([
target_features[f].unsqueeze(0)
for f, _, _, _ in tgt_dataset.trainval
], 0)
# calculate distance and rerank result
print('Calculating feature distances...')
target_features = target_features.numpy()
rerank_dist = re_ranking(source_features,
target_features,
lambda_value=args.lambda_value)
if iter_n == 0:
# DBSCAN cluster
tri_mat = np.triu(rerank_dist, 1) # tri_mat.dim=2
tri_mat = tri_mat[np.nonzero(tri_mat)] # tri_mat.dim=1
tri_mat = np.sort(tri_mat, axis=None)
top_num = np.round(args.rho * tri_mat.size).astype(int)
eps = tri_mat[:top_num].mean()
print('eps in cluster: {:.3f}'.format(eps))
cluster = DBSCAN(eps=eps,
min_samples=4,
metric='precomputed',
n_jobs=8)
# select & cluster images as training set of this epochs
print('Clustering and labeling...')
labels = cluster.fit_predict(rerank_dist)
num_ids = len(set(labels)) - 1
print('Iteration {} have {} training ids'.format(iter_n + 1, num_ids))
# generate new dataset
new_dataset, unknown_dataset = [], []
# assign label for target ones
unknownLab = labelNoise(torch.from_numpy(target_features),
torch.from_numpy(labels))
# unknownFeats = target_features[labels==-1,:]
unCounter, index = 0, 0
from collections import defaultdict
realIDs, fakeIDs = defaultdict(list), []
record_labels = {}
hough = Hough(8, 40, 230, 2935, 25, args.short_cut)
for (fname, realPID, cam,
timestamp), label in zip(tgt_dataset.trainval, labels):
if label == -1:
unknown_dataset.append((fname, int(unknownLab[unCounter]), cam,
timestamp)) # unknown data
fakeIDs.append(int(unknownLab[unCounter]))
realIDs[realPID].append(index)
unCounter += 1
index += 1
continue
# dont need to change codes in trainer.py _parsing_input function and sampler function after add 0
if label not in record_labels:
record_labels[label] = []
for index2 in record_labels[label]:
hough.update(cam, tgt_dataset.trainval[index2][2], timestamp,
tgt_dataset.trainval[index2][3])
record_labels[label].append(index)
new_dataset.append((fname, label, cam, timestamp))
fakeIDs.append(label)
realIDs[realPID].append(index)
index += 1
print('Iteration {} have {} training images'.format(
iter_n + 1, len(new_dataset)))
precision, recall, fscore = calScores(
realIDs, np.asarray(fakeIDs)) # fakeIDs does not contain -1
print('precision:{}, recall:{}, fscore: {}'.format(
100 * precision, 100 * recall, fscore))
T_pseu, TP_pseu, T_gt, TP_gt, index = (0, 0, 0, 0, -1)
for (fname, realPID, cam,
timestamp), label in zip(tgt_dataset.trainval, labels):
index += 1
# calc by gt label
T_gt = T_gt + len(realIDs[realPID]) - 1
for index2 in realIDs[realPID]:
if index2 == index: continue
if hough.on_peak(cam, tgt_dataset.trainval[index2][2],
timestamp, tgt_dataset.trainval[index2][3]):
TP_gt += 1
# calc by pseudo label
if label == -1: continue
T_pseu = T_pseu + len(record_labels[label]) - 1
for index2 in record_labels[label]:
if index2 == index: continue
if hough.on_peak(cam, tgt_dataset.trainval[index2][2],
timestamp, tgt_dataset.trainval[index2][3]):
TP_pseu += 1
print('gt label: T = %d, TP = %d, recall = %f' %
(T_gt, TP_gt, TP_pseu / T_gt))
print('pseudo label: T = %d, TP = %d, recall = %f' %
(T_pseu, TP_pseu, TP_pseu / T_pseu))
train_loader = DataLoader(Preprocessor(new_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
new_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# hard samples
# noiseImgs = [name[1] for name in unknown_dataset]
# saveAll(noiseImgs, tgt_dataset.images_dir, 'noiseImg')
# import ipdb; ipdb.set_trace()
unLoader = DataLoader(Preprocessor(unknown_dataset,
root=tgt_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=4,
sampler=RandomIdentitySampler(
unknown_dataset, args.num_instances),
pin_memory=True,
drop_last=True)
# train model with new generated dataset
trainer1 = HoughTrainer(model, hough, train_loader, criterion,
optimizer)
trainer2 = HoughTrainer(model, hough, unLoader, criterion, optimizer)
# Start training
for epoch in range(args.epochs):
trainer1.train(epoch)
trainer2.train(epoch)
# test only
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
# print('co-model:\n')
# rank_score = evaluatorB.evaluate(test_loader, tgt_dataset.query, tgt_dataset.gallery)
# Evaluate
rank_score = evaluator.evaluate(test_loader, tgt_dataset.query,
tgt_dataset.gallery)
save_checkpoint(
{
'state_dict': model.module.state_dict(),
'epoch': epoch + 1,
'best_top1': rank_score.market1501[0],
},
True,
fpath=osp.join(args.logs_dir, 'asyCo.pth'))
return rank_score.map, rank_score.market1501[0]
def update_train_loader(dataset,
train_samples,
updated_label,
height,
width,
batch_size,
re,
workers,
all_img_cams,
sample_position=7):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.RandomHorizontalFlip(p=0.5),
T.Pad(10),
T.RandomCrop((height, width)),
T.ToTensor(), normalizer,
T.RandomErasing(EPSILON=re)
])
# obtain global accumulated label from pseudo label and cameras
pure_label = updated_label[updated_label >= 0]
pure_cams = all_img_cams[updated_label >= 0]
accumulate_labels = np.zeros(pure_label.shape, pure_label.dtype)
prev_id_count = 0
id_count_each_cam = []
for this_cam in np.unique(pure_cams):
percam_labels = pure_label[pure_cams == this_cam]
unique_id = np.unique(percam_labels)
id_count_each_cam.append(len(unique_id))
id_dict = {ID: i for i, ID in enumerate(unique_id.tolist())}
for i in range(len(percam_labels)):
percam_labels[i] = id_dict[percam_labels[i]]
accumulate_labels[pure_cams ==
this_cam] = percam_labels + prev_id_count
prev_id_count += len(unique_id)
print(' sum(id_count_each_cam)= {}'.format(sum(id_count_each_cam)))
new_accum_labels = -1 * np.ones(updated_label.shape, updated_label.dtype)
new_accum_labels[updated_label >= 0] = accumulate_labels
# update sample list
new_train_samples = []
for sample in train_samples:
lbl = updated_label[sample[3]]
if lbl != -1:
assert (new_accum_labels[sample[3]] >= 0)
new_sample = sample + (lbl, new_accum_labels[sample[3]])
new_train_samples.append(new_sample)
target_train_loader = DataLoader(UnsupervisedTargetPreprocessor(
new_train_samples,
root=osp.join(dataset.target_images_dir, dataset.target_train_path),
num_cam=dataset.target_num_cam,
transform=train_transformer,
has_pseudo_label=True),
batch_size=batch_size,
num_workers=workers,
pin_memory=True,
drop_last=True,
sampler=ClassUniformlySampler(
new_train_samples,
class_position=sample_position,
k=4))
return target_train_loader, len(new_train_samples)
def main(args):
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.benchmark = True
# Redirect print to both console and log file
sys.stdout = Logger(osp.join(args.logs_dir, 'log.txt'))
print(args)
shutil.copy(sys.argv[0], osp.join(args.logs_dir,
osp.basename(sys.argv[0])))
# Create data loaders
if args.height is None or args.width is None:
args.height, args.width = (256, 128)
dataset, num_classes, train_loader, val_loader, test_loader = \
get_data(args.dataset, args.split, args.data_dir, args.height,
args.width, args.batch_size * 8, args.workers,
)
# Create model
model = models.create("ft_net_inter",
num_classes=num_classes,
stride=args.stride)
# Load from checkpoint
start_epoch = 0
best_top1 = 0
top1 = 0
is_best = False
if args.checkpoint is not None:
if args.evaluate:
checkpoint = load_checkpoint(args.checkpoint)
param_dict = model.state_dict()
for k, v in checkpoint['state_dict'].items():
if 'model' in k:
param_dict[k] = v
model.load_state_dict(param_dict)
else:
model.model.load_param(args.checkpoint)
model = model.cuda()
# Distance metric
metric = None
# Evaluator
evaluator = Evaluator(model, use_cpu=args.use_cpu)
if args.evaluate:
print("Test:")
evaluator.evaluate(test_loader, dataset.query, dataset.gallery, metric)
return
train_transformer = [
T.Resize((args.height, args.width), interpolation=3),
T.RandomHorizontalFlip(),
T.Pad(10),
T.RandomCrop((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
T.RandomErasing(probability=0.5),
]
train_transformer = T.Compose(train_transformer)
for cluster_epoch in range(args.cluster_epochs):
# -------------------------Stage 1 intra camera training--------------------------
# Cluster and generate new dataset and model
cluster_result = get_intra_cam_cluster_result(model, train_loader,
args.class_number_stage1,
args.linkage)
cluster_datasets = [
datasets.create("cluster", osp.join(args.data_dir, args.dataset),
cluster_result[cam_id], cam_id)
for cam_id in cluster_result.keys()
]
cluster_dataloaders = [
DataLoader(Preprocessor(dataset.train_set,
root=dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
pin_memory=False,
drop_last=True) for dataset in cluster_datasets
]
param_dict = model.model.state_dict()
model = models.create("ft_net_intra",
num_classes=[
args.class_number_stage1
for cam_id in cluster_result.keys()
],
stride=args.stride)
model_param_dict = model.model.state_dict()
for k, v in model_param_dict.items():
if k in param_dict.keys():
model_param_dict[k] = param_dict[k]
model.model.load_state_dict(model_param_dict)
model = model.cuda()
criterion = nn.CrossEntropyLoss().cuda()
# Optimizer
param_groups = make_params(model, args.lr, args.weight_decay)
optimizer = torch.optim.SGD(param_groups, momentum=0.9)
# Trainer
trainer = IntraCameraTrainer(model,
criterion,
warm_up_epoch=args.warm_up)
print("start training")
# Start training
for epoch in range(0, args.epochs_stage1):
trainer.train(
cluster_epoch,
epoch,
cluster_dataloaders,
optimizer,
print_freq=args.print_freq,
)
# -------------------------------------------Stage 2 inter camera training-----------------------------------
mix_rate = get_mix_rate(args.mix_rate,
cluster_epoch,
args.cluster_epochs,
power=args.decay_factor)
cluster_result = get_inter_cam_cluster_result(model,
train_loader,
args.class_number_stage2,
args.linkage,
mix_rate,
use_cpu=args.use_cpu)
cluster_dataset = datasets.create(
"cluster", osp.join(args.data_dir, args.dataset), cluster_result,
0)
cluster_dataloaders = DataLoader(
Preprocessor(cluster_dataset.train_set,
root=cluster_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size_stage2,
num_workers=args.workers,
sampler=RandomIdentitySampler(cluster_dataset.train_set,
args.batch_size_stage2,
args.instances),
pin_memory=False,
drop_last=True)
param_dict = model.model.state_dict()
model = models.create("ft_net_inter",
num_classes=args.class_number_stage2,
stride=args.stride)
model.model.load_state_dict(param_dict)
model = model.cuda()
# Criterion
criterion_entropy = nn.CrossEntropyLoss().cuda()
criterion_triple = TripletLoss(margin=args.margin).cuda()
# Optimizer
param_groups = make_params(model,
args.lr * args.batch_size_stage2 / 32,
args.weight_decay)
optimizer = torch.optim.SGD(param_groups, momentum=0.9)
# Trainer
trainer = InterCameraTrainer(
model,
criterion_entropy,
criterion_triple,
warm_up_epoch=args.warm_up,
)
print("start training")
# Start training
for epoch in range(0, args.epochs_stage2):
trainer.train(cluster_epoch,
epoch,
cluster_dataloaders,
optimizer,
print_freq=args.print_freq)
if (cluster_epoch + 1) % 5 == 0:
evaluator = Evaluator(model, use_cpu=args.use_cpu)
top1, mAP = evaluator.evaluate(test_loader,
dataset.query,
dataset.gallery,
metric,
return_mAP=True)
is_best = top1 > best_top1
best_top1 = max(top1, best_top1)
save_checkpoint(
{
'state_dict': model.state_dict(),
'epoch': cluster_epoch + 1,
'best_top1': best_top1,
'cluster_epoch': cluster_epoch + 1,
},
is_best,
fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar'))
if cluster_epoch == (args.cluster_epochs - 1):
save_checkpoint(
{
'state_dict': model.state_dict(),
'epoch': cluster_epoch + 1,
'best_top1': best_top1,
'cluster_epoch': cluster_epoch + 1,
},
False,
fpath=osp.join(args.logs_dir, 'latest.pth.tar'))
print('\n * cluster_epoch: {:3d} top1: {:5.1%} best: {:5.1%}{}\n'.
format(cluster_epoch, top1, best_top1, ' *' if is_best else ''))
# Final test
print('Test with best model:')
checkpoint = load_checkpoint(osp.join(args.logs_dir, 'model_best.pth.tar'))
model.load_state_dict(checkpoint['state_dict'])
best_rank1, mAP = evaluator.evaluate(test_loader,
dataset.query,
dataset.gallery,
metric,
return_mAP=True)
def main(args):
np.random.seed(args.seed) # With the seed reset (every time), the same set of numbers will appear every time.
torch.manual_seed(args.seed) # Sets the seed for generating random numbers.
cudnn.benchmark = True # This flag allows you to enable the inbuilt cudnn auto-tuner to find the best algorithm to use for your hardware. It enables benchmark mode in cudnn.
# Redirect print to both console and log file
sys.stdout = Logger(osp.join(args.logs_dir, 'log.txt'))
print(args)
shutil.copy(sys.argv[0], osp.join(args.logs_dir,
osp.basename(sys.argv[0])))
# Create data loaders
if args.height is None or args.width is None:
args.height, args.width = (256, 128)
dataset, num_classes, train_loader, val_loader, test_loader = \
get_data(args.dataset, args.split, args.data_dir, args.height,
args.width, args.batch_size * 8, args.workers, #https://deeplizard.com/learn/video/kWVgvsejXsE#:~:text=The%20num_workers%20attribute%20tells%20the,sequentially%20inside%20the%20main%20process.
)
# Create model
model = models.create("ft_net_inter",
num_classes=num_classes, stride=args.stride)
# Load from checkpoint
start_epoch = 0
best_top1 = 0
top1 = 0
is_best = False
if args.checkpoint is not None:
if args.evaluate:
checkpoint = load_checkpoint(args.checkpoint)
param_dict = model.state_dict() # A state_dict is simply a Python dictionary object that maps each layer to its parameter tensor.
for k, v in checkpoint['state_dict'].items():
if 'model' in k:
param_dict[k] = v
model.load_state_dict(param_dict)
else:
model.model.load_param(args.checkpoint)
model = model.cuda()
# Distance metric
metric = None
# Evaluator
evaluator = Evaluator(model, use_cpu=args.use_cpu)
if args.evaluate:
print("Test:")
evaluator.evaluate(test_loader, dataset.query, dataset.gallery, metric)
return
train_transformer = [
T.Resize((args.height, args.width), interpolation=3),
T.RandomHorizontalFlip(),
T.Pad(10),
T.RandomCrop((args.height, args.width)),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
T.RandomErasing(probability=0.5),
]
train_transformer = T.Compose(train_transformer)
for cluster_epoch in range(args.cluster_epochs):
# -------------------------Stage 1 intra camera training--------------------------
# Cluster and generate new dataset and model
# Divides the training set into (subsets) and according to that each camera id is there for each image
# then it forms clustering on each subset according to the pair wise similarity
# then assigning images with in each cluster with identical label
# then cross entropy loss is used
cluster_result = get_intra_cam_cluster_result(model, train_loader,
args.class_number_stage1,
args.linkage)
cluster_datasets = [
datasets.create("cluster", osp.join(args.data_dir, args.dataset),
cluster_result[cam_id], cam_id)
for cam_id in cluster_result.keys()
]
cluster_dataloaders = [
DataLoader(Preprocessor(dataset.train_set,
root=dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size,
num_workers=args.workers,
shuffle=True,
pin_memory=False,
drop_last=True) for dataset in cluster_datasets
]
param_dict = model.model.state_dict()
model = models.create("ft_net_intra",
num_classes=[
args.class_number_stage1
for cam_id in cluster_result.keys()
],
stride=args.stride)
model_param_dict = model.model.state_dict()
for k, v in model_param_dict.items():
if k in param_dict.keys():
model_param_dict[k] = param_dict[k]
model.model.load_state_dict(model_param_dict)
model = model.cuda()
criterion = nn.CrossEntropyLoss().cuda()
# Optimizer
param_groups = make_params(model, args.lr, args.weight_decay)
optimizer = torch.optim.SGD(param_groups, momentum=0.9)
# Trainer
trainer = IntraCameraTrainer(
model, criterion, warm_up_epoch=args.warm_up)
print("start training")
# Start training
for epoch in range(0, args.epochs_stage1):
trainer.train(cluster_epoch,
epoch,
cluster_dataloaders,
optimizer,
print_freq=args.print_freq,
)
# -------------------------------------------Stage 2 inter camera training-----------------------------------
mix_rate = get_mix_rate(
args.mix_rate, cluster_epoch, args.cluster_epochs, power=args.decay_factor)
cluster_result = get_inter_cam_cluster_result(
model,
train_loader,
args.class_number_stage2,
args.linkage,
mix_rate,
use_cpu=args.use_cpu)
cluster_dataset = datasets.create(
"cluster", osp.join(args.data_dir, args.dataset), cluster_result,
0)
cluster_dataloaders = DataLoader(
Preprocessor(cluster_dataset.train_set,
root=cluster_dataset.images_dir,
transform=train_transformer),
batch_size=args.batch_size_stage2,
num_workers=args.workers,
sampler=RandomIdentitySampler(cluster_dataset.train_set,
args.batch_size_stage2,
args.instances),
pin_memory=False,
drop_last=True)
param_dict = model.model.state_dict()
model = models.create("ft_net_inter",
num_classes=args.class_number_stage2,
stride=args.stride)
model.model.load_state_dict(param_dict)
model = model.cuda()
# Criterion
criterion_entropy = nn.CrossEntropyLoss().cuda()
criterion_triple = TripletLoss(margin=args.margin).cuda()
# Optimizer
param_groups = make_params(model,
args.lr * args.batch_size_stage2 / 32,
args.weight_decay)
optimizer = torch.optim.SGD(param_groups, momentum=0.9)
# Trainer
trainer = InterCameraTrainer(model,
criterion_entropy,
criterion_triple,
warm_up_epoch=args.warm_up,
)
print("start training")
# Start training
for epoch in range(0, args.epochs_stage2):
trainer.train(cluster_epoch,
epoch,
cluster_dataloaders,
optimizer,
print_freq=args.print_freq)
if (cluster_epoch + 1) % 5 == 0: # in 4th, 9th, 14th epochs, see in the output
evaluator = Evaluator(model, use_cpu=args.use_cpu)
top1, mAP = evaluator.evaluate(
test_loader, dataset.query, dataset.gallery, metric, return_mAP=True)
is_best = top1 > best_top1
best_top1 = max(top1, best_top1)
save_checkpoint(
{
'state_dict': model.state_dict(),
'epoch': cluster_epoch + 1,
'best_top1': best_top1,
'cluster_epoch': cluster_epoch + 1,
},
is_best,
fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar'))
if cluster_epoch == (args.cluster_epochs - 1):
save_checkpoint(
{
'state_dict': model.state_dict(),
'epoch': cluster_epoch + 1,
'best_top1': best_top1,
'cluster_epoch': cluster_epoch + 1,
},
False,
fpath=osp.join(args.logs_dir, 'latest.pth.tar'))
print('\n * cluster_epoch: {:3d} top1: {:5.1%} best: {:5.1%}{}\n'.
format(cluster_epoch, top1, best_top1, ' *' if is_best else ''))
# Final test
print('Test with best model:')
checkpoint = load_checkpoint(osp.join(args.logs_dir, 'model_best.pth.tar'))
model.load_state_dict(checkpoint['state_dict'])
best_rank1, mAP = evaluator.evaluate(
test_loader, dataset.query, dataset.gallery, metric, return_mAP=True)