def initialize(self):
with fluid.dygraph.guard():
if os.path.isabs(self.net_path):
net_path_full = self.net_path
else:
net_path_full = os.path.join(env_settings().network_path,
self.net_path)
self.net = atom_resnet50(
backbone_pretrained=False,
backbone_is_test=True,
iounet_is_test=True)
state_dictsm, _ = fluid.load_dygraph(net_path_full)
self.net.load_dict(state_dictsm)
self.net.train()
self.iou_predictor = self.net.bb_regressor
self.layer_stride = {
'conv0': 2,
'conv1': 2,
'block0': 4,
'block1': 8,
'block2': 16,
'block3': 32,
'classification': 16,
'fc': None
}
self.layer_dim = {
'conv0': 64,
'conv1': 64,
'block0': 256,
'block1': 512,
'block2': 1024,
'block3': 2048,
'classification': 256,
'fc': None
}
self.iounet_feature_layers = self.net.bb_regressor_layer
if isinstance(self.pool_stride, int) and self.pool_stride == 1:
self.pool_stride = [1] * len(self.output_layers)
self.feature_layers = sorted(
list(set(self.output_layers + self.iounet_feature_layers)))
self.mean = np.reshape([0.485, 0.456, 0.406], [1, -1, 1, 1])
self.std = np.reshape([0.229, 0.224, 0.225], [1, -1, 1, 1])
def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'ATOM IoUNet with default settings.'
settings.print_interval = 1 # How often to print loss and other info
settings.batch_size = 64 # Batch size
settings.num_workers = 4 # Number of workers for image loading
settings.normalize_mean = [
0.485, 0.456, 0.406
] # Normalize mean (default pytorch ImageNet values)
settings.normalize_std = [
0.229, 0.224, 0.225
] # Normalize std (default pytorch ImageNet values)
settings.search_area_factor = 5.0 # Image patch size relative to target size
settings.feature_sz = 18 # Size of feature map
settings.output_sz = settings.feature_sz * 16 # Size of input image patches
# Settings for the image sample and proposal generation
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
settings.proposal_params = {
'min_iou': 0.1,
'boxes_per_frame': 16,
'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]
}
# Train datasets
lasot_train = Lasot(split='train')
trackingnet_train = TrackingNet(set_ids=list(range(11)))
coco_train = MSCOCOSeq()
# Validation datasets
trackingnet_val = TrackingNet(set_ids=list(range(11, 12)))
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = dltransforms.ToGrayscale(probability=0.05)
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = torchvision.transforms.Compose([
dltransforms.ToTensorAndJitter(0.2),
torchvision.transforms.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std)
])
# The augmentation transform applied to the validation set (individually to each image in the pair)
transform_val = torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std)
])
# Data processing to do on the training pairs
data_processing_train = processing.ATOMProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_factor=settings.center_jitter_factor,
scale_jitter_factor=settings.scale_jitter_factor,
mode='sequence',
proposal_params=settings.proposal_params,
transform=transform_train,
joint_transform=transform_joint)
# Data processing to do on the validation pairs
data_processing_val = processing.ATOMProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_factor=settings.center_jitter_factor,
scale_jitter_factor=settings.scale_jitter_factor,
mode='sequence',
proposal_params=settings.proposal_params,
transform=transform_val,
joint_transform=transform_joint)
# The sampler for training
dataset_train = sampler.ATOMSampler(
[lasot_train, trackingnet_train, coco_train], [1, 1, 1],
samples_per_epoch=1800 * settings.batch_size,
max_gap=50,
processing=data_processing_train)
# The loader for training
loader_train = LTRLoader('train',
dataset_train,
training=True,
batch_size=settings.batch_size,
num_workers=settings.num_workers,
shuffle=True,
drop_last=True,
stack_dim=1)
# The sampler for validation
dataset_val = sampler.ATOMSampler([trackingnet_val], [1],
samples_per_epoch=500 *
settings.batch_size,
max_gap=50,
processing=data_processing_val)
# The loader for validation
loader_val = LTRLoader('val',
dataset_val,
training=False,
batch_size=settings.batch_size,
num_workers=settings.num_workers,
shuffle=False,
drop_last=True,
epoch_interval=5,
stack_dim=1)
# Create network
net = atom_models.atom_resnet50(backbone_pretrained=True)
# Set objective
objective = nn.MSELoss()
# Create actor, which wraps network and objective
actor = actors.AtomActor(net=net, objective=objective)
# Optimizer
optimizer = optim.Adam(actor.net.bb_regressor.parameters(), lr=1e-3)
# Learning rate scheduler
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,
step_size=15,
gamma=0.2)
# Create trainer
trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer,
settings, lr_scheduler)
# Run training (set fail_safe=False if you are debugging)
trainer.train(40, load_latest=True, fail_safe=False)
def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'ATOM IoUNet with ResNet50 backbone and trained with vid, lasot, coco.'
settings.print_interval = 1 # How often to print loss and other info
settings.batch_size = 64 # Batch size
settings.num_workers = 4 # Number of workers for image loading
settings.normalize_mean = [0.485, 0.456, 0.406
] # Normalize mean (default ImageNet values)
settings.normalize_std = [0.229, 0.224,
0.225] # Normalize std (default ImageNet values)
settings.search_area_factor = 5.0 # Image patch size relative to target size
settings.feature_sz = 18 # Size of feature map
settings.output_sz = settings.feature_sz * 16 # Size of input image patches
# Settings for the image sample and proposal generation
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
settings.proposal_params = {
'min_iou': 0.1,
'boxes_per_frame': 16,
'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]
}
# Train datasets
vid_train = ImagenetVID()
lasot_train = Lasot(split='train')
coco_train = MSCOCOSeq()
# Validation datasets
got10k_val = Got10k(split='val')
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = dltransforms.ToGrayscale(probability=0.05)
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = dltransforms.Compose([
dltransforms.ToArrayAndJitter(0.2),
dltransforms.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std)
])
# The augmentation transform applied to the validation set (individually to each image in the pair)
transform_val = dltransforms.Compose([
dltransforms.ToArray(),
dltransforms.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std)
])
# Data processing to do on the training pairs
data_processing_train = processing.ATOMProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_factor=settings.center_jitter_factor,
scale_jitter_factor=settings.scale_jitter_factor,
mode='sequence',
proposal_params=settings.proposal_params,
transform=transform_train,
joint_transform=transform_joint)
# Data processing to do on the validation pairs
data_processing_val = processing.ATOMProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_factor=settings.center_jitter_factor,
scale_jitter_factor=settings.scale_jitter_factor,
mode='sequence',
proposal_params=settings.proposal_params,
transform=transform_val,
joint_transform=transform_joint)
# The sampler for training
dataset_train = sampler.ATOMSampler(
[vid_train, lasot_train, coco_train], [1, 1, 1],
samples_per_epoch=1000 * settings.batch_size,
max_gap=50,
processing=data_processing_train)
# The loader for training
train_loader = loader.LTRLoader('train',
dataset_train,
training=True,
batch_size=settings.batch_size,
num_workers=4,
stack_dim=1)
# The sampler for validation
dataset_val = sampler.ATOMSampler([got10k_val], [
1,
],
samples_per_epoch=500 *
settings.batch_size,
max_gap=50,
processing=data_processing_val)
# The loader for validation
val_loader = loader.LTRLoader('val',
dataset_val,
training=False,
batch_size=settings.batch_size,
num_workers=4,
epoch_interval=5,
stack_dim=1)
# creat network, set objective, creat optimizer, learning rate scheduler, trainer
with dygraph.guard():
# Create network
net = atom_resnet50(backbone_pretrained=True)
# Freeze backbone
state_dicts = net.state_dict()
for k in state_dicts.keys():
if 'feature_extractor' in k and "running" not in k:
state_dicts[k].stop_gradient = True
# Set objective
objective = fluid.layers.square_error_cost
# Create actor, which wraps network and objective
actor = actors.AtomActor(net=net, objective=objective)
# Set to training mode
actor.train()
# define optimizer and learning rate
gama = 0.2
lr = 1e-3
lr_scheduler = fluid.dygraph.PiecewiseDecay(
[15, 30, 45],
values=[lr, lr * gama, lr * gama * gama],
step=1000,
begin=0)
optimizer = fluid.optimizer.Adam(
parameter_list=net.bb_regressor.parameters(),
learning_rate=lr_scheduler)
trainer = LTRTrainer(actor, [train_loader, val_loader], optimizer,
settings, lr_scheduler)
trainer.train(40, load_latest=False, fail_safe=False)