def main():
config = yaml.load(open("./config/config.yaml", "r"),
Loader=yaml.FullLoader)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Training with: {device}")
data_transform = get_simclr_data_transforms(**config['data_transforms'])
train_dataset = datasets.STL10('/home/thalles/Downloads/',
split='train+unlabeled',
download=True,
transform=MultiViewDataInjector(
[data_transform, data_transform]))
# online network
online_network = ResNet18(**config['network']).to(device)
pretrained_folder = config['network']['fine_tune_from']
# load pre-trained model if defined
if pretrained_folder:
try:
checkpoints_folder = os.path.join('./runs', pretrained_folder,
'checkpoints')
# load pre-trained parameters
load_params = torch.load(
os.path.join(os.path.join(checkpoints_folder, 'model.pth')),
map_location=torch.device(torch.device(device)))
if 'online_network_state_dict' in load_params:
online_network.load_state_dict(
load_params['online_network_state_dict'])
print("Parameters successfully loaded.")
except FileNotFoundError:
print("Pre-trained weights not found. Training from scratch.")
# predictor network
predictor = MLPHead(
in_channels=online_network.projetion.net[-1].out_features,
**config['network']['projection_head']).to(device)
# target encoder
target_network = ResNet18(**config['network']).to(device)
optimizer = torch.optim.SGD(
list(online_network.parameters()) + list(predictor.parameters()),
**config['optimizer']['params'])
trainer = BYOLTrainer(online_network=online_network,
target_network=target_network,
optimizer=optimizer,
predictor=predictor,
device=device,
**config['trainer'])
trainer.train(train_dataset)
def main():
config = yaml.load(open("./config/config.yaml", "r"),
Loader=yaml.FullLoader)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Training with: {device}")
data_transform = get_simclr_data_transforms(**config['data_transforms'])
data_transform2 = get_simclr_data_transforms(**config['data_transforms'],
blur=1.)
# get_simclr_data_transforms_onlyglobal
# data_transform = get_simclr_data_transforms_randAugment(config['data_transforms']['input_shape'])
# data_transform2 = get_simclr_data_transforms_randAugment(config['data_transforms']['input_shape'])
train_dataset = datasets.STL10('/media/snowflake/Data/',
split='train+unlabeled',
download=True,
transform=MultiViewDataInjector(
[data_transform, data_transform2]))
# train_dataset = STL(["/home/snowflake/Descargas/STL_data/unlabeled_images",
# "/home/snowflake/Descargas/STL_data/train_images"],
# transform=MultiViewDataInjector([data_transform, data_transform2]))
# online network (the one that is trained)
online_network = ResNet(**config['network']).to(device)
# online_network = MLPmixer(**config['network']).to(device)
# target encoder
# target_network = ResNet_BN_mom(**config['network']).to(device)
target_network = ResNet(**config['network']).to(device)
# target_network = MLPmixer(**config['network']).to(device)
pretrained_folder = config['network']['fine_tune_from']
# load pre-trained model if defined
if pretrained_folder:
try:
checkpoints_folder = os.path.join('./runs', pretrained_folder,
'checkpoints')
# load pre-trained parameters
load_params = torch.load(
os.path.join(os.path.join(checkpoints_folder, 'model.pth')),
map_location=torch.device(torch.device(device)))
online_network.load_state_dict(
load_params['online_network_state_dict'])
target_network.load_state_dict(
load_params['target_network_state_dict'])
except FileNotFoundError:
print("Pre-trained weights not found. Training from scratch.")
# predictor network
predictor = MLPHead_DINO(
in_channels=online_network.projetion.net[-1].out_features,
**config['network']['projection_head']).to(device)
optimizer = torch.optim.SGD(
list(online_network.parameters()) + list(predictor.parameters()),
**config['optimizer']['params'])
trainer = BYOLTrainer(online_network=online_network,
target_network=target_network,
optimizer=optimizer,
predictor=predictor,
device=device,
**config['trainer'])
trainer.train(train_dataset)
def main():
parser = ArgumentParser()
parser.add_argument('--incr', action='store_true', help='train representation incrementally')
parser.add_argument('--id', type=str, default='', dest='experiment_id',
help='experiment id appended to saved files')
args = parser.parse_args()
config = yaml.load(open("./config/config.yaml", "r"), Loader=yaml.FullLoader)
n_class_epochs = config['other']['n_class_epochs']
eval_step = config['other']['eval_step']
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Training with: {device}")
data_transform = get_simclr_data_transforms(**config['data_transforms'])
#train_dataset = datasets.STL10('../../data', split='train+unlabeled', download=False,
# transform=MultiViewDataInjector([data_transform, data_transform]))
# online network
online_network = ResNet18(**config['network']).to(device)
pretrained_folder = config['network']['fine_tune_from']
# load pre-trained model if defined
if pretrained_folder:
try:
checkpoints_folder = os.path.join('./runs', pretrained_folder, 'checkpoints')
# load pre-trained parameters
load_params = torch.load(os.path.join(os.path.join(checkpoints_folder, 'model.pth')),
map_location=torch.device(torch.device(device)))
online_network.load_state_dict(load_params['online_network_state_dict'])
except FileNotFoundError:
print("Pre-trained weights not found. Training from scratch.")
# predictor network
predictor = MLPHead(in_channels=online_network.projection.net[-1].out_features,
**config['network']['projection_head']).to(device)
# target encoder
target_network = ResNet18(**config['network']).to(device)
optimizer = torch.optim.SGD(list(online_network.parameters()) + list(predictor.parameters()),
**config['optimizer']['params'])
trainer = BYOLTrainer(online_network=online_network,
target_network=target_network,
optimizer=optimizer,
predictor=predictor,
device=device,
**config['trainer'])
num_workers = config['trainer']['num_workers']
batch_size_train = 100
batch_size_test = 200
if args.incr:
incr_train_loaders, incr_val_loaders = get_dataloader_incr(data_dir='../../data', base='CIFAR10', num_classes=10,
img_size=224, classes_per_exposure=2, train=True,
num_workers=num_workers, batch_size_train=batch_size_train,
batch_size_test=batch_size_test,
transform=MultiViewDataInjector([data_transform, data_transform]))
# get train and val indices sampled
train_indices = np.concatenate([ldr.sampler.indices for ldr in incr_train_loaders])
train_class_dataloader = DataLoader(incr_train_loaders[0].dataset, sampler=SubsetRandomSampler(train_indices),
batch_size=batch_size_train, num_workers=num_workers)
#trainer.train(train_dataset)
trainer.train_incr(incr_train_loaders, incr_val_loaders,
n_class_epochs=n_class_epochs,
train_class_dataloader=train_class_dataloader,
experiment_id=args.experiment_id,
eval_step=eval_step)
else:
train_loader, val_loader = get_dataloader(data_dir='../../data', base='CIFAR10', num_classes=10,
img_size=224, train=True, num_workers=num_workers,
batch_size_train=batch_size_train, batch_size_test=batch_size_test,
transform=MultiViewDataInjector([data_transform, data_transform]))
trainer.train(train_loader, val_loader, n_class_epochs=n_class_epochs, experiment_id=args.experiment_id,
eval_step=eval_step)
def load_data(config):
# path
seq_dir = list()
# 视角
view = list()
# 状态
seq_type = list()
# 身份标签
label = list()
##
seqs_l = list()
# → (s = 1, input_shape = xxx)
# 增广
Transformer = get_simclr_data_transforms(**config['data_transforms'])
Transformer_test = get_test_transforms(**config['data_transforms'])
dataset_path = config['data']['dataset_path']
dataset = config['data']['dataset']
pid_num = config['data']['pid_num']
pid_shuffle = config['data']['pid_shuffle']
resolution = config['data']['resolution']
f_length = config['data']['f_length']
partition_rate = config['data']['partition_rate']
label_rate = config['data']['label_rate']
## 按身份文件进行迭代： 如从001--120
for _label in sorted(list(os.listdir(dataset_path))):
# In CASIA-B, data of subject #5 is incomplete.
# Thus, we ignore it in training.
if dataset == 'CASIA-B' and _label == '005':
continue
## ID标签文件夹路径
label_path = osp.join(dataset_path, _label)
## sorted缺省升序排列: 状态文件夹路径迭代
for _seq_type in sorted(list(os.listdir(label_path))):
## 类别路径
seq_type_path = osp.join(label_path, _seq_type)
## sorted缺省升序排列: 各类视角文件夹路径迭代
for _view in sorted(list(os.listdir(seq_type_path))):
_seq_dir = osp.join(seq_type_path, _view)
## png list:身份ID(label)-状态(seq_type)-状态ID(seq_dir)-视角(view)
## -时间戳帧(i).png
seqs = os.listdir(_seq_dir)
##
## 从N张.png里面随机截取连续的T帧
if len(seqs) >= f_length:
# 时间戳顺序
seqs = sorted(seqs)
# 随机数
rand_st = np.random.randint(0, len(seqs) - f_length + 1)
rand_ed = rand_st + f_length
# slice seq
curr_seq_imgs = seqs[rand_st:rand_ed]
## [(..,..), ..., (..,..)]
seqs_l.append(
(curr_seq_imgs, _seq_dir, _label, _seq_type, _view))
# info路径 ['','','']
# seq_dir.append(_seq_dir)
# 身份标签 00x
# label.append(_label)
# 附属物标签 bg-0x
# seq_type.append(_seq_type)
# 视角标签 108
# view.append(_view)
## pid_num为partition点
partition_info = osp.join(
'partition_rate', '{}_{}_{}.npy'.format(dataset, partition_rate,
pid_shuffle))
## 分割点
partition_num = math.floor(len(seqs_l) * partition_rate)
label_num = math.floor(len(seqs_l) * label_rate)
## 保存原始文件配置信息
seqs_partition = [
seqs_l[label_num:partition_num], seqs_l[0:label_num],
seqs_l[partition_num:]
]
## 根据划分点pid_fname --- 获取训练测试的身份ID号列表
train_list = seqs_partition[0]
ft_list = seqs_partition[1]
test_list = seqs_partition[2]
## xarray list | 帧身份标签 | 视角 | 状态 | 路径
train_source = DataSet([train_list[i][0] for i in range(len(train_list))],
[train_list[i][1] for i in range(len(train_list))],
[train_list[i][2] for i in range(len(train_list))],
[train_list[i][3] for i in range(len(train_list))],
[train_list[i][4] for i in range(len(train_list))],
Transformer, resolution)
## xarray list | 帧身份标签 | 视角 | 状态 | 路径
ft_source = DataSet([train_list[i][0] for i in range(len(ft_list))],
[train_list[i][1] for i in range(len(ft_list))],
[train_list[i][2] for i in range(len(ft_list))],
[train_list[i][3] for i in range(len(ft_list))],
[train_list[i][4] for i in range(len(ft_list))],
Transformer, resolution)
## xarray list | 帧身份标签 | 视角 | 状态 | 路径
test_source = DataSet([test_list[i][0] for i in range(len(test_list))],
[test_list[i][1] for i in range(len(test_list))],
[test_list[i][2] for i in range(len(test_list))],
[test_list[i][3] for i in range(len(test_list))],
[test_list[i][4] for i in range(len(test_list))],
Transformer_test, resolution)
return train_source, ft_source, test_source
def main(args):
config = yaml.load(open("./config/config.yaml", "r"),
Loader=yaml.FullLoader)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Training with: {device}")
data_transform = get_simclr_data_transforms(**config['data_transforms'])
train_dataset_1 = datasets.CIFAR10(root='../STL_model/data',
train=True,
download=True,
transform=MultiViewDataInjector(
[data_transform, data_transform]))
data_transforms = torchvision.transforms.Compose(
[transforms.Resize(96), transforms.ToTensor()])
train_dataset_2 = datasets.CIFAR10(root='../STL_model/data',
train=True,
download=True,
transform=MultiViewDataInjector(
[data_transforms, data_transforms]))
# online network
online_network = Multi_ResNet18(args.flag_ova,
**config['network']).to(device)
pretrained_folder = config['network']['fine_tune_from']
# load pre-trained model if defined
if pretrained_folder:
try:
checkpoints_folder = os.path.join('./runs', pretrained_folder,
'checkpoints')
# load pre-trained parameters
load_params = torch.load(
os.path.join(os.path.join(checkpoints_folder, 'model.pth')),
map_location=torch.device(torch.device(device)))
online_network.load_state_dict(
load_params['online_network_state_dict'])
except FileNotFoundError:
print("Pre-trained weights not found. Training from scratch.")
# predictor network
predictor = MLPHead(
in_channels=online_network.projetion.net[-1].out_features,
**config['network']['projection_head']).to(device)
# target encoder
target_network = Multi_ResNet18(args.flag_ova,
**config['network']).to(device)
optimizer = torch.optim.SGD(
list(online_network.parameters()) + list(predictor.parameters()),
**config['optimizer']['params'])
trainer = BYOLTrainer(online_network=online_network,
target_network=target_network,
optimizer=optimizer,
predictor=predictor,
device=device,
model_path=args.model_path,
**config['trainer'])
trainer.train((train_dataset_1, train_dataset_2), args.flag_ova)
def get_acc():
batch_size = 8
data_transforms = torchvision.transforms.Compose([transforms.ToTensor()])
config = yaml.load(open("/content/BYOL-UCMerced/config/config.yaml", "r"), Loader=yaml.FullLoader)
data_transform = get_simclr_data_transforms(**config['data_transforms'])
train_dataset = MyDataset(txt='/content/BYOL-UCMerced/data/UCMerced_LandUse/Images/train.txt', transform=MultiViewDataInjector([data_transform, data_transform]))
test_dataset = MyDataset(txt='/content/BYOL-UCMerced/data/UCMerced_LandUse/Images/test.txt', transform=MultiViewDataInjector([data_transform, data_transform]))
print("Input shape:", len(train_dataset))
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size,
num_workers=0, drop_last=False, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size,
num_workers=0, drop_last=False, shuffle=True)
print(type(train_loader))
device = 'cuda' if torch.cuda.is_available() else 'cpu' #'cuda' if torch.cuda.is_available() else 'cpu'
encoder = ResNet18(**config['network'])
output_feature_dim = encoder.projetion.net[0].in_features
#load pre-trained parameters
load_params = torch.load(os.path.join('/content/BYOL-UCMerced/checkpoints/model.pth'),
map_location=torch.device(torch.device(device)))
if 'online_network_state_dict' in load_params:
encoder.load_state_dict(load_params['online_network_state_dict'])
print("Parameters successfully loaded.")
# remove the projection head
encoder = torch.nn.Sequential(*list(encoder.children())[:-1])
encoder = encoder.to(device)
encoder.eval()
logreg = LogisticRegression(output_feature_dim, 21)
logreg = logreg.to(device)
x_train, y_train = get_features_from_encoder(encoder, train_loader)
x_test, y_test = get_features_from_encoder(encoder, test_loader)
if len(x_train.shape) > 2:
x_train = torch.mean(x_train, dim=[2, 3])
x_test = torch.mean(x_test, dim=[2, 3])
print("Training data shape:", x_train.shape, y_train.shape)
print("Testing data shape:", x_test.shape, y_test.shape)
scaler = preprocessing.StandardScaler()
scaler.fit(x_train.cpu())
x_train = scaler.transform(x_train.cpu()).astype(np.float32)
x_test = scaler.transform(x_test.cpu()).astype(np.float32)
train_loader, test_loader = create_data_loaders_from_arrays(torch.from_numpy(x_train), y_train, torch.from_numpy(x_test), y_test)
optimizer = torch.optim.Adam(logreg.parameters(), lr=3e-4)
criterion = torch.nn.CrossEntropyLoss()
eval_every_n_epochs = 10
for epoch in range(200):
# train_acc = []
for x, y in train_loader:
x = x.to(device)
y = y.to(device)
# zero the parameter gradients
optimizer.zero_grad()
logits = logreg(x)
predictions = torch.argmax(logits, dim=1)
loss = criterion(logits, y)
loss.backward()
optimizer.step()
if epoch % eval_every_n_epochs == 0:
train_total,total = 0,0
train_correct,correct = 0,0
for x, y in train_loader:
x = x.to(device)
y = y.to(device)
logits = logreg(x)
predictions = torch.argmax(logits, dim=1)
train_total += y.size(0)
train_correct += (predictions == y).sum().item()
for x, y in test_loader:
x = x.to(device)
y = y.to(device)
logits = logreg(x)
predictions = torch.argmax(logits, dim=1)
total += y.size(0)
correct += (predictions == y).sum().item()
train_acc= train_correct / train_total
acc = correct / total
print(f"Training accuracy: {np.mean(train_acc)}")
print(f"Testing accuracy: {np.mean(acc)}")
