def create_test_data_loader(args, name, dataset):
train_transformer = T.Compose([
T.RectScale(args.height, args.width),
T.ToTensor(),
T.Normalize(mean=[0.486, 0.459, 0.408], std=[0.229, 0.224, 0.225])
])
test_transformer = T.Compose([
T.RectScale(args.height, args.width),
T.ToTensor(),
T.Normalize(mean=[0.486, 0.459, 0.408], std=[0.229, 0.224, 0.225])
])
train_loader = DataLoader(
Preprocessor(dataset.train, root=os.path.join(dataset.images_dir, dataset.train_path),
transform=train_transformer),
batch_size=args.batch_size, num_workers=args.workers,
shuffle=False, pin_memory=True, drop_last=False)
query_loader = DataLoader(
Preprocessor(dataset.query, root=os.path.join(dataset.images_dir, dataset.query_path),
transform=test_transformer),
batch_size=args.batch_size*4, num_workers=args.workers,
shuffle=False, pin_memory=True, drop_last=False)
gallery_loader = DataLoader(
Preprocessor(dataset.gallery, root=os.path.join(dataset.images_dir, dataset.gallery_path),
transform=test_transformer),
batch_size=args.batch_size*4, num_workers=args.workers,
shuffle=False, pin_memory=True, drop_last=False)
print('{} Datasets Has beed loaded.'.format(name))
return train_loader, query_loader, gallery_loader
def get_data(name, data_dir, height, width, batch_size, workers, pose_aug,
skip, rate, eraser):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root)
video_dict = None
if osp.isfile(osp.join(root, 'video.json')):
video_dict = read_json(osp.join(root, 'video.json'))
if eraser:
train_transformer = T.Compose([
T.RectScale(height, width),
T.RandomSizedEarser(),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
else:
train_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
# use combined trainval set for training as default
train_loader = DataLoader(Preprocessor(dataset.trainval,
name,
root=dataset.images_dir,
with_pose=True,
pose_root=dataset.poses_dir,
pid_imgs=dataset.trainval_query,
height=height,
width=width,
pose_aug=pose_aug,
transform=train_transformer),
sampler=RandomTripletSampler(
dataset.trainval,
video_dict=video_dict,
skip_frames=skip,
inter_rate=rate),
batch_size=batch_size,
num_workers=workers,
pin_memory=False)
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
test_loader = DataLoader(Preprocessor(
list(set(dataset.query) | set(dataset.gallery)),
name,
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=False)
return dataset, train_loader, test_loader
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_dataloader(dataset,data_dir,
training=False, height=256,
width=128, batch_size=64, workers=1):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if training:
transformer = T.Compose([
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
])
else:
transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
data_loader = DataLoader(
Preprocessor(dataset, root=data_dir,
transform=transformer),
batch_size=batch_size, num_workers=workers,
shuffle=training, pin_memory=True, drop_last=training)
return data_loader
def __init__(self, dataset, name, root=None, with_pose=False, pose_root=None, is_test=False, test_root = None,
pid_imgs=None, height=256, width=128, pose_aug='no', transform=None):
super(Preprocessor, self).__init__()
self.dataset = dataset
self.root = root
self.with_pose = with_pose
self.pose_root = pose_root
self.is_test = is_test
self.test_root = test_root
self.pid_imgs = pid_imgs
self.height = height
self.width = width
self.pose_aug = pose_aug
self.name = name
normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
if transform==None:
self.transform = transforms.Compose([
transforms.RectScale(height, width),
transforms.RandomSizedEarser(),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalizer,
])
else:
self.transform = transform
self.transform_p = transforms.Compose([
transforms.RectScale(height, width),
transforms.ToTensor(),
normalizer,
])
def get_data(data_dir, big_height, big_width, target_height, target_width, batch_size, workers, is_train=True):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_transformer = T.Compose([
T.ResizeRandomCrop(big_height, big_width, target_height, target_width),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.RectScale(target_height, target_width),
T.ToTensor(),
normalizer,
])
if is_train:
transformer = train_transformer
else:
transformer = test_transformer
data_loader = DataLoader(
Direct_Preprocessor(data_dir=data_dir,
transform=transformer, is_train=is_train),
batch_size=batch_size, num_workers=workers,
shuffle=is_train, pin_memory=True)
return data_loader
def get_loader(data,
root,
height=256,
width=128,
batch_size=32,
workers=0,
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(height, width), # 对图像进行随机裁剪并缩放.
T.RandomHorizontalFlip(), # 对给定的PIL.Image进行随机水平翻转,概率为0.5,属于数据增强.
T.ToTensor(), # 将numpy图像转换为torch图像.
normalizer,
])
else:
transformer = T.Compose([
T.RectScale(height, width), # 缩放图像.
T.ToTensor(),
normalizer,
])
batch_size = batch_size * 8
data_loader = DataLoader(Preprocessor(data,
root=root,
transform=transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=training,
pin_memory=True)
return data_loader
def get_dataloader(dataset,data_dir,
training=False, height=256,
width=128, batch_size=64, workers=1):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])#(0.1307,), (0.3081,)
# normalizer = T.Normalize(mean=[0.1307, 0.1307, 0.1307],
# std=[0.3081, 0.3081, 0.3081])#, (0.3081,)
if training:
transformer = T.Compose([
T.RectScale(config.input_size + 32, config.input_size + 32),
torchvision.transforms.RandomCrop(config.input_size),
torchvision.transforms.RandomHorizontalFlip(),
# RandomRotation(degrees=20),
T.ToTensor(),
normalizer,
])
else:
transformer = T.Compose([
T.RectScale(config.input_size, config.input_size),
T.ToTensor(),
normalizer,
])
data_loader = DataLoader(
Preprocessor(dataset, root=data_dir,
transform=transformer),
batch_size=batch_size, num_workers=workers,
shuffle=training, pin_memory=True, drop_last=training)
return data_loader
def get_data(name, data_dir, height, width, batch_size, workers, pose_aug):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root)
# use combined trainval set for training as default
train_loader = DataLoader(Preprocessor(dataset.trainval,
root=dataset.images_dir,
with_pose=True,
pose_root=dataset.poses_dir,
pid_imgs=dataset.trainval_query,
height=height,
width=width,
pose_aug=pose_aug),
sampler=RandomPairSampler(dataset.trainval,
neg_pos_ratio=3),
batch_size=batch_size,
num_workers=workers,
pin_memory=False)
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
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=False)
return dataset, train_loader, test_loader
def get_data2(args):
(name, split_id, data_dir, height, width, batch_size, num_instances,
workers, combine_trainval) = (
args.dataset,
args.split,
args.data_dir,
args.height,
args.width,
args.batch_size,
args.num_instances,
args.workers,
args.combine_trainval,
)
pin_memory = args.pin_mem
name_val = args.dataset_val or args.dataset
npy = args.has_npy
rand_ratio = args.random_ratio
dataset_train = datasets.CUB2('train')
dataset_test = datasets.CUB2('test')
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
num_classes = np.unique(dataset_train.train_labels).shape[0]
train_transformer = T.Compose([
T.ToPILImage(),
T.RandomCropFlip(height, width, area=args.area),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.ToPILImage(),
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
def get_data(name, split_id, data_dir, height, width, batch_size, workers,
combine_trainval):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, 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([
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
])
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,
shuffle=True,
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)
pid_train = np.array(list(pid for _, pid, _ in train_set))
class_weight = np.array([(pid_train == i).sum()
for i in range(num_classes)])
assert np.all(class_weight != 0)
class_weight = pid_train.shape[0] / num_classes / class_weight
class_weight = torch.Tensor(class_weight).cuda()
return dataset, num_classes, class_weight, train_loader, val_loader, test_loader
def get_source_data(name, data_dir, height, width, batch_size, workers):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, num_val=0.1)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
# use all training images on source dataset
train_set = dataset.train
num_classes = dataset.num_train_ids
transformer = T.Compose([
T.Resize((height,width)),
T.ToTensor(),
normalizer,
])
extfeat_loader = DataLoader(
Preprocessor(train_set, root=dataset.images_dir,
transform=transformer),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
return dataset, extfeat_loader
def get_real_test_data(query_dir, gallery_dir, target_height, target_width,
batch_size, workers):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
test_transformer = T.Compose([
T.RectScale(target_height, target_width),
T.ToTensor(),
normalizer,
])
query_loader = DataLoader(Flip_Preprocessor(data_dir=query_dir,
is_flip=False,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
gallery_loader = DataLoader(Flip_Preprocessor(data_dir=gallery_dir,
is_flip=False,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
return query_loader, gallery_loader
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,
])
batch_size = self.batch_size
else:
transformer = T.Compose([
T.RectScale(self.data_height, self.data_width),
T.ToTensor(),
normalizer,
])
batch_size = self.eval_bs
data_loader = DataLoader(
Preprocessor(dataset, root=self.data_dir,
transform=transformer, is_training=training, max_frames=self.max_frames),
batch_size=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, batch_size))
return data_loader
def get_data(name, split_id, data_dir, height, width, batch_size,
num_instances, workers, combine_trainval, batch_id):
root = osp.join(data_dir, name)
if name == 'synthetic':
dataset = datasets.create(name,
root,
split_id=split_id,
batch_id=batch_id)
else:
dataset = datasets.create(name, root, 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([
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
])
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(
name,
split_id,
data_dir,
height,
width,
batch_size,
workers,
):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, 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
num_classes = dataset.num_trainval_ids
train_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(Preprocessor(train_set,
root=dataset.images_dir,
transform=train_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=False,
drop_last=False)
val_loader = DataLoader(Preprocessor(dataset.val,
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=False)
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=False)
return dataset, num_classes, train_loader, val_loader, test_loader
def get_data(
name,
split_id,
data_dir,
height,
width,
batch_size,
workers,
):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, split_id=split_id)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406], #for each channel
std=[0.229, 0.224, 0.225])
train_set = dataset.trainval # accessing through an object i.e., dataset (as object is being created at line 40)
num_classes = dataset.num_trainval_ids
train_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.Resize((height, width), interpolation=3),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(Preprocessor(train_set, # It represents a Python iterable over a dataset
root=dataset.images_dir,
transform=train_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=False, # https://discuss.pytorch.org/t/when-to-set-pin-memory-to-true/19723
drop_last=False) # https://discuss.pytorch.org/t/usage-of-drop-last-on-data-loader/66741
val_loader = DataLoader(Preprocessor(dataset.val,
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=False)
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=False)
return dataset, num_classes, train_loader, val_loader, test_loader
def test(dataset, net, perturbation, args, evaluator, epoch, name,saveRank=False):
print(">> Evaluating network on test datasets...")
net = net.cuda()
net.eval()
normalize = T.Normalize(
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
)
mean = torch.Tensor(normalize.mean).view(1, 3, 1, 1).cuda()
std = torch.Tensor(normalize.std).view(1, 3, 1, 1).cuda()
test_transformer = T.Compose([
T.RectScale(args.height, args.width),
T.ToTensor()
])
query_loader = DataLoader(
Preprocessor(dataset.query, name, root=dataset.images_dir, transform=test_transformer),
batch_size=args.batch_size, num_workers=0, shuffle=False, pin_memory=True
)
gallery_loader = DataLoader(
Preprocessor(dataset.gallery, name, root=dataset.images_dir, transform=test_transformer),
batch_size=args.batch_size, num_workers=8, shuffle=False, pin_memory=True
)
qFeats, gFeats, testQImage,noiseQIamge, qnames, gnames = [], [], [], [], [],[]
qCams, gCams = [], []
import random
with torch.no_grad():
for batch_index, (inputs, qname, _, qCam) in enumerate(query_loader):
inputs = inputs.cuda()
perturted_input = perturbation(inputs)
successful_diffs = ((perturted_input - inputs) * 3 + 0.5).clamp(0, 1)
if len(testQImage) < 8:
testQImage.append(perturted_input[0, ...])
noiseQIamge.append(successful_diffs[0, ...])
perturted_input = torch.clamp(perturted_input, 0, 1)
###normalization
norm_perturted_input = (perturted_input - mean) / std
perturbed_feature = net(norm_perturted_input)[0]
qFeats.append(perturbed_feature)
qnames.extend(qname)
qCams.append(qCam.cuda())
qFeats = torch.cat(qFeats, 0)
for (inputs, gname, _, gCam) in gallery_loader:
###normalize####
inputs = inputs.cuda()
inputs = (inputs - mean) / std
gFeats.append(net(inputs)[0])
gnames.extend(gname)
gCams.append(gCam.cuda())
gFeats = torch.cat(gFeats, 0)
gCams, qCams = torch.cat(gCams).view(1, -1), torch.cat(qCams).view(-1, 1)
distMat = calDist(qFeats, gFeats)
# evaluate on test datasets
s= evaluator.evaMat(distMat, dataset.query, dataset.gallery)
return testQImage, noiseQIamge,s
def get_data(name, data_dir, height, width, batch_size, workers):
root = osp.join(data_dir, name)
root = data_dir
dataset = datasets.create(name, 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.RectScale(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(Preprocessor(dataset.train,
root=osp.join(
dataset.images_dir,
dataset.train_path),
transform=train_transformer,
random_mask=False),
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)
return dataset, num_classes, train_loader, query_loader, gallery_loader
def get_data(name, data_dir, height, width, ratio, batch_size, workers, num_instances=8):
root = osp.join(data_dir, name)
root = data_dir
dataset = datasets.create(name, root)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
listnormalizer = T.ListNormalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
num_classes = dataset.num_train_ids + 1 # plus 1 more label for the zero-padded feature
train_transformer = T.Compose([
T.RectScale(height, width),
T.RandomHorizontalFlip(),
T.RandomVerticalCropCont(height,width),
T.ListToTensor(),
listnormalizer,
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
query_transformer = T.Compose([
T.ContVerticalCropDiscret(height,width, ratio),
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,
sampler=RandomIdentitySampler(dataset.train, num_instances),
# shuffle=True,
pin_memory=True, drop_last=True)
query_loader = DataLoader(
Preprocessor(dataset.query, root=osp.join(dataset.images_dir,dataset.query_path),
transform=query_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)
return dataset, num_classes, train_loader, query_loader, gallery_loader
def main(args):
# Load the synset words
idx2cls = list()
with open('samples/synset_words.txt') as lines:
for line in lines:
line = line.strip().split(' ', 1)[1]
line = line.split(', ', 1)[0].replace(' ', '_')
idx2cls.append(line)
# Setup a classification model
print('Loading a model...', end='')
#model = torchvision.models.resnet152(pretrained=True)
model = models.create('resnet50', num_features=256,
dropout=0.25, num_classes=5005, cut_at_pooling=False, FCN=True)
tar = torch.load('../checkpoint.pth.tar')
state_dict = tar['state_dict']
model.load_state_dict(state_dict)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
#transform = T.Compose([
# T.RectScale(256, 256),
# T.ToTensor(),
# normalizer,
# transforms.ToTensor(),
# #transforms.Normalize(mean=[0.485, 0.456, 0.406],
# # std=[0.229, 0.224, 0.225])
#])
transform = transforms.Compose([
# transforms.RectScale(256,256)
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
print('finished')
# Setup the SmoothGrad
smooth_grad = SmoothGrad(model=model, cuda=args.cuda, sigma=args.sigma,
n_samples=args.n_samples, guided=args.guided)
img = os.listdir('../dataset/train/')
idx = 3
args.image = osp.join('../dataset/train/',img[idx])
# Predict without adding noises
smooth_grad.load_image(filename=args.image, transform=transform)
prob, idx = smooth_grad.forward()
# Generate the saliency images of top 3
for i in range(0, 3):
# print('{:.5f}'.format(prob[i]))
smooth_grad.generate(
filename='results/{}'.format( i), idx=idx[i])
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, split_id=split_id)
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
# load train_set, query_set, gallery_set
mt_train_set = dataset.train
mt_num_classes = dataset.num_train_tids_sub
query_set = dataset.query
gallery_set = dataset.gallery
train_transformer = T.Compose([
T.RandomSizedRectCrop(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(), normalizer
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
# Random ID
mt_train_set = flatten_dataset(mt_train_set)
num_task = len(
mt_num_classes) # num_task equals camera number, each camera is a task
mt_train_loader = DataLoader(
Preprocessor_Image(mt_train_set,
root=dataset.dataset_dir,
transform=train_transformer),
batch_size=batch_size,
num_workers=workers,
sampler=RandomIdentitySampler(
mt_train_set, num_instances,
num_task), # Here is different between softmax_loss
pin_memory=True,
drop_last=True)
query_set = flatten_dataset(query_set)
gallery_set = flatten_dataset(gallery_set)
test_set = list(set(query_set) | set(gallery_set))
test_loader = DataLoader(Preprocessor_Image(test_set,
root=dataset.dataset_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
return mt_train_loader, mt_num_classes, test_loader, query_set, gallery_set
def get_data(dataset_name, split_id, data_dir, batch_size, workers,
num_instances, combine_trainval=False):
root = osp.join(data_dir, dataset_name)
dataset = get_dataset(dataset_name, root,
split_id=split_id, num_val=1, download=True)
normalizer = transforms.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_processor = Preprocessor(train_set, root=dataset.images_dir,
transform=transforms.Compose([
transforms.RandomSizedRectCrop(256, 128),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalizer,
]))
if num_instances > 0:
train_loader = DataLoader(
train_processor, batch_size=batch_size, num_workers=workers,
sampler=RandomIdentitySampler(train_set, num_instances),
pin_memory=True)
else:
train_loader = DataLoader(
train_processor, batch_size=batch_size, num_workers=workers,
shuffle=True, pin_memory=True)
val_loader = DataLoader(
Preprocessor(dataset.val, root=dataset.images_dir,
transform=transforms.Compose([
transforms.RectScale(256, 128),
transforms.ToTensor(),
normalizer,
])),
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=transforms.Compose([
transforms.RectScale(256, 128),
transforms.ToTensor(),
normalizer,
])),
batch_size=batch_size, num_workers=workers,
shuffle=False, pin_memory=True)
return dataset, num_classes, train_loader, val_loader, test_loader
def get_transformer(config):
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
base_transformer = [T.ToTensor(), normalizer]
if config.training is False:
return T.Compose([T.Resize((config.height, config.width))] + base_transformer)
if config.img_translation is None:
return T.Compose([T.RandomSizedRectCrop(config.height, config.width),
T.RandomHorizontalFlip()] + base_transformer)
return T.Compose([T.RandomTranslateWithReflect(config.img_translation),
T.RandomSizedRectCrop(config.height, config.width),
T.RandomHorizontalFlip()] + base_transformer)
def __init__(self, config):
self.model_path = config.args['model_path']
self.width = config.args['width']
self.height = config.args['height']
self.model = init_model(self.model_path)
self.normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
self.test_transformer = T.Compose([
T.RectScale(self.height, self.width),
T.ToTensor(),
self.normalizer,
])
def get_data(name, split_id, data_dir, height, width, batch_size, workers,
combine_trainval, np_ratio):
root = osp.join(data_dir, name)
dataset = datasets.create(name, root, 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
train_transformer = T.Compose([
T.RandomSizedRectCrop(height, width),
T.RandomSizedEarser(),
T.RandomHorizontalFlip(),
T.ToTensor(),
normalizer,
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(Preprocessor(train_set,
root=dataset.images_dir,
transform=train_transformer),
sampler=RandomPairSampler(
train_set, neg_pos_ratio=np_ratio),
batch_size=batch_size,
num_workers=workers,
pin_memory=False)
val_loader = DataLoader(Preprocessor(dataset.val,
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=0,
shuffle=False,
pin_memory=False)
test_loader = DataLoader(Preprocessor(
list(set(dataset.query) | set(dataset.gallery)),
root=dataset.images_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=0,
shuffle=False,
pin_memory=False)
return dataset, 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_dataloader(batch_size=64, workers=4):
#prepare dataset
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
test_transformer = T.Compose([
Resize((256, 128)),
T.ToTensor(),
normalizer,
])
#test_time augmentation
#test_transformer = T.Compose([
# Resize((288, 144)),
# TenCrop((256,128)),
# Lambda(lambda crops: torch.stack([normalizer(T.ToTensor()(crop)) for crop in crops])),
# ])
single_train_dir = './data/market1501/raw/Market-1501-v15.09.15/bounding_box_train'
single_query_dir = './data/market1501/raw/Market-1501-v15.09.15/query'
multi_query_dir = './data/market1501/raw/Market-1501-v15.09.15/gt_bbox'
gallery_dir = './data/market1501/raw/Market-1501-v15.09.15/bounding_box_test'
single_train_loader = DataLoader(TestDataset(root=single_train_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
single_query_loader = DataLoader(TestDataset(root=single_query_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
multi_query_loader = DataLoader(TestDataset(root=multi_query_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
gallery_loader = DataLoader(TestDataset(root=gallery_dir,
transform=test_transformer),
batch_size=batch_size,
num_workers=workers,
shuffle=False,
pin_memory=True)
return single_train_loader, single_query_loader, multi_query_loader, gallery_loader
def get_data(split_id, data_dir, height, width, batchSize, workers, combine_trainval, train_list, \
val_list, query_list, gallery_list):
root = data_dir
normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # RGB imagenet
train_set = train_list + val_list if combine_trainval else train_list # a list
train_transformer = T.Compose([
T.RectScale(height, width),
T.RandomHorizontalFlip(),
T.ToTensor(), # [0, 255] to [0.0, 1.0]
normalizer, # normalize each channel of the input
])
test_transformer = T.Compose([
T.RectScale(height, width),
T.ToTensor(),
normalizer,
])
train_loader = DataLoader(
Preprocessor(train_set, root=root, transform=train_transformer),
batch_size=batchSize,
num_workers=workers,
sampler=RandomSampler(train_set),
# shuffle=True,
pin_memory=True,
drop_last=True)
val_loader = DataLoader(Preprocessor(val_list,
root=root,
transform=test_transformer),
batch_size=batchSize,
num_workers=workers,
shuffle=False,
pin_memory=True)
test_loader = DataLoader(Preprocessor(
list(set(query_list) | set(gallery_list)),
root=root,
transform=test_transformer),
batch_size=batchSize,
num_workers=workers,
shuffle=False,
pin_memory=True)
return train_loader, val_loader, test_loader