def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'ATOM IoUNet with default settings according to the paper.'
settings.batch_size = 64
settings.num_workers = 8
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
# Train datasets
lasot_train = Lasot(settings.env.lasot_dir, split='train')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir, set_ids=list(range(11)))
coco_train = MSCOCOSeq(settings.env.coco_dir)
# Validation datasets
trackingnet_val = TrackingNet(settings.env.trackingnet_dir, set_ids=list(range(11,12)))
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = tfm.Transform(tfm.ToTensorAndJitter(0.2),
tfm.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 = tfm.Transform(tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean, std=settings.normalize_std))
# Data processing to do on the training pairs
proposal_params = {'min_iou': 0.1, 'boxes_per_frame': 16, 'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]}
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=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=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=1000*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 and actor
net = atom_models.atom_resnet18(backbone_pretrained=True)
objective = nn.MSELoss()
actor = actors.AtomActor(net=net, objective=objective)
# Optimizer
optimizer = optim.Adam(actor.net.bb_regressor.parameters(), lr=1e-3)
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(50, load_latest=True, fail_safe=True)
def run(settings):
settings.description = 'Default train settings for PrDiMP with ResNet50 as backbone.'
settings.batch_size = 10
settings.num_workers = 8
settings.multi_gpu = False
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.output_sigma_factor = 1/4
settings.target_filter_sz = 4
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 3, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0.25, 'test': 0.5}
settings.hinge_threshold = 0.05
settings.print_stats = ['Loss/total', 'Loss/bb_ce', 'ClfTrain/clf_ce']
# Train datasets
lasot_train = Lasot(settings.env.lasot_dir, split='train')
got10k_train = Got10k(settings.env.got10k_dir, split='vottrain')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir, set_ids=list(range(4)))
coco_train = MSCOCOSeq(settings.env.coco_dir)
# Validation datasets
got10k_val = Got10k(settings.env.got10k_dir, split='votval')
# Data transform
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
transform_train = tfm.Transform(tfm.ToTensorAndJitter(0.2),
tfm.Normalize(mean=settings.normalize_mean, std=settings.normalize_std))
transform_val = tfm.Transform(tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean, std=settings.normalize_std))
# The tracking pairs processing module
output_sigma = settings.output_sigma_factor / settings.search_area_factor
proposal_params = {'boxes_per_frame': 128, 'gt_sigma': (0.05, 0.05), 'proposal_sigma': [(0.05, 0.05), (0.5, 0.5)]}
label_params = {'feature_sz': settings.feature_sz, 'sigma_factor': output_sigma, 'kernel_sz': settings.target_filter_sz}
label_density_params = {'feature_sz': settings.feature_sz, 'sigma_factor': output_sigma, 'kernel_sz': settings.target_filter_sz, 'normalize': True}
data_processing_train = processing.KLDiMPProcessing(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=proposal_params,
label_function_params=label_params,
label_density_params=label_density_params,
transform=transform_train,
joint_transform=transform_joint)
data_processing_val = processing.KLDiMPProcessing(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=proposal_params,
label_function_params=label_params,
label_density_params=label_density_params,
transform=transform_val,
joint_transform=transform_joint)
# Train sampler and loader
dataset_train = sampler.DiMPSampler([lasot_train, got10k_train, trackingnet_train, coco_train], [0.25,1,1,1],
samples_per_epoch=26000, max_gap=200, num_test_frames=3, num_train_frames=3,
processing=data_processing_train)
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)
# Validation samplers and loaders
dataset_val = sampler.DiMPSampler([got10k_val], [1], samples_per_epoch=5000, max_gap=200,
num_test_frames=3, num_train_frames=3,
processing=data_processing_val)
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 and actor
net = dimpnet.klcedimpnet50(filter_size=settings.target_filter_sz, backbone_pretrained=True, optim_iter=5,
clf_feat_norm=True, clf_feat_blocks=0, final_conv=True, out_feature_dim=512,
optim_init_step=1.0, optim_init_reg=0.05, optim_min_reg=0.05,
gauss_sigma=output_sigma * settings.feature_sz, alpha_eps=0.05, normalize_label=True, init_initializer='zero')
# Wrap the network for multi GPU training
if settings.multi_gpu:
net = MultiGPU(net, dim=1)
objective = {'bb_ce': klreg_losses.KLRegression(), 'clf_ce': klreg_losses.KLRegressionGrid()}
loss_weight = {'bb_ce': 0.0025, 'clf_ce': 0.25, 'clf_ce_init': 0.25, 'clf_ce_iter': 1.0}
actor = tracking_actors.KLDiMPActor(net=net, objective=objective, loss_weight=loss_weight)
# Optimizer
optimizer = optim.Adam([{'params': actor.net.classifier.parameters(), 'lr': 1e-3},
{'params': actor.net.bb_regressor.parameters(), 'lr': 1e-3},
{'params': actor.net.feature_extractor.parameters(), 'lr': 2e-5}],
lr=2e-4)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=15, gamma=0.2)
trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer, settings, lr_scheduler)
trainer.train(50, load_latest=True, fail_safe=True)
def run(settings):
settings.description = 'Default train settings for DiMP with ResNet50 as backbone.'
settings.batch_size = 10
settings.num_workers = 8
settings.multi_gpu = False
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.output_sigma_factor = 1 / 4
settings.target_filter_sz = 4
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 3, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0.25, 'test': 0.5}
settings.hinge_threshold = 0.05
# settings.print_stats = ['Loss/total', 'Loss/iou', 'ClfTrain/clf_ce', 'ClfTrain/test_loss']
'''
Depth Inputs:
1) raw_depth X
2) norm_depth
3) centered_norm_depth
4) centered_raw_depth X
5) colormap
6) centered_colormap
'''
# depth_inputs = 'norm_depth'
# depth_inputs = 'colormap'
depth_inputs = 'hha'
# Train datasets
# depthtrack_train = DepthTrack(root=settings.env.depthtrack_dir, split='train', dtype=depth_inputs)
coco_train = MSCOCOSeq_depth(settings.env.cocodepth_dir,
dtype=depth_inputs)
# got10k_depth_train = MSCOCOSeq_depth(settings.env.got10kdepth_dir, dtype=depth_inputs)
lasot_depth_train = Lasot_depth(root=settings.env.lasotdepth_dir,
rgb_root=settings.env.lasot_dir,
dtype=depth_inputs)
# Validation datasets
depthtrack_val = DepthTrack(root=settings.env.depthtrack_dir,
split='val',
dtype=depth_inputs)
# Data transform
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
transform_val = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# The tracking pairs processing module
output_sigma = settings.output_sigma_factor / settings.search_area_factor
proposal_params = {
'min_iou': 0.1,
'boxes_per_frame': 8,
'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]
}
label_params = {
'feature_sz': settings.feature_sz,
'sigma_factor': output_sigma,
'kernel_sz': settings.target_filter_sz
}
data_processing_train = processing.DiMPProcessing(
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=proposal_params,
label_function_params=label_params,
transform=transform_train,
joint_transform=transform_joint)
data_processing_val = processing.DiMPProcessing(
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=proposal_params,
label_function_params=label_params,
transform=transform_val,
joint_transform=transform_joint)
# Train sampler and loader
dataset_train = sampler.DiMPSampler([coco_train, lasot_depth_train],
[1, 1],
samples_per_epoch=26000,
max_gap=30,
num_test_frames=3,
num_train_frames=3,
processing=data_processing_train)
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)
# Validation samplers and loaders
dataset_val = sampler.DiMPSampler([depthtrack_val], [1],
samples_per_epoch=5000,
max_gap=30,
num_test_frames=3,
num_train_frames=3,
processing=data_processing_val)
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 and actor
net = dimpnet.dimpnet50(
filter_size=settings.target_filter_sz,
backbone_pretrained=True,
optim_iter=5, # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
# net = dimpnet.dimpnet50(filter_size=settings.target_filter_sz, backbone_pretrained=False, optim_iter=5, # !!!!!!!!!!!!!!!!!!!!!!!!!!!!
clf_feat_norm=True,
clf_feat_blocks=0,
final_conv=True,
out_feature_dim=512,
optim_init_step=0.9,
optim_init_reg=0.1,
init_gauss_sigma=output_sigma * settings.feature_sz,
num_dist_bins=100,
bin_displacement=0.1,
mask_init_factor=3.0,
target_mask_act='sigmoid',
score_act='relu')
# Wrap the network for multi GPU training
if settings.multi_gpu:
net = MultiGPU(net, dim=1)
objective = {
'iou': nn.MSELoss(),
'test_clf': ltr_losses.LBHinge(threshold=settings.hinge_threshold)
}
loss_weight = {
'iou': 1,
'test_clf': 100,
'test_init_clf': 100,
'test_iter_clf': 400
}
actor = actors.DiMPActor(net=net,
objective=objective,
loss_weight=loss_weight)
# Optimizer
optimizer = optim.Adam(
[{
'params': actor.net.classifier.filter_initializer.parameters(),
'lr': 5e-5
}, {
'params': actor.net.classifier.filter_optimizer.parameters(),
'lr': 5e-4
}, {
'params': actor.net.classifier.feature_extractor.parameters(),
'lr': 5e-5
}, {
'params': actor.net.bb_regressor.parameters()
}, {
'params': actor.net.feature_extractor.parameters(),
'lr': 2e-5
}],
lr=2e-4)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,
step_size=15,
gamma=0.2)
trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer,
settings, lr_scheduler)
trainer.train(50, load_latest=True, fail_safe=True)
def run(settings):
settings.move_data_to_gpu = False
settings.description = ''
settings.batch_size = 10
settings.test_sequence_length = 50
settings.num_workers = 8
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.output_sigma_factor = 1 / 4
settings.target_filter_sz = 4
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_param = {
'train_mode': 'uniform',
'train_factor': 3.0,
'train_limit_motion': False,
'test_mode': 'uniform',
'test_factor': 4.5,
'test_limit_motion': True
}
settings.scale_jitter_param = {'train_factor': 0.25, 'test_factor': 0.3}
settings.hinge_threshold = 0.05
settings.print_stats = [
'Loss/total', 'Loss/raw/test_clf', 'Loss/raw/test_clf_acc',
'Loss/raw/dimp_clf_acc', 'Loss/raw/is_target',
'Loss/raw/is_target_after_prop', 'Loss/raw/test_seq_acc',
'Loss/raw/dimp_seq_acc'
]
lasot_train = Lasot(settings.env.lasot_dir, split='train')
got10k_train = Got10k(settings.env.got10k_dir, split='vottrain')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir,
set_ids=[0, 1, 2, 3, 4])
# Validation datasets
got10k_val = Got10k(settings.env.got10k_dir, split='votval')
# Data transform
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
transform_val = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# The tracking pairs processing module
output_sigma = settings.output_sigma_factor / settings.search_area_factor
proposal_params = None
label_params = {
'feature_sz': settings.feature_sz,
'sigma_factor': output_sigma,
'kernel_sz': settings.target_filter_sz,
'end_pad_if_even': True
}
data_processing_train = processing.KYSProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_param=settings.center_jitter_param,
scale_jitter_param=settings.scale_jitter_param,
proposal_params=proposal_params,
label_function_params=label_params,
transform=transform_train,
joint_transform=transform_joint,
min_crop_inside_ratio=0.1)
data_processing_val = processing.KYSProcessing(
search_area_factor=settings.search_area_factor,
output_sz=settings.output_sz,
center_jitter_param=settings.center_jitter_param,
scale_jitter_param=settings.scale_jitter_param,
proposal_params=proposal_params,
label_function_params=label_params,
transform=transform_val,
joint_transform=transform_joint,
min_crop_inside_ratio=0.1)
# Train sampler and loader
sequence_sample_info = {
'num_train_frames': 3,
'num_test_frames': settings.test_sequence_length,
'max_train_gap': 30,
'allow_missing_target': True,
'min_fraction_valid_frames': 0.5,
'mode': 'Sequence'
}
dataset_train = sampler.KYSSampler(
[got10k_train, trackingnet_train, lasot_train], [0.3, 0.3, 0.25],
samples_per_epoch=settings.batch_size * 150,
sequence_sample_info=sequence_sample_info,
processing=data_processing_train,
sample_occluded_sequences=True)
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)
# Validation samplers and loaders
dataset_val = sampler.KYSSampler([got10k_val], [1],
samples_per_epoch=1000,
sequence_sample_info=sequence_sample_info,
processing=data_processing_val,
sample_occluded_sequences=True)
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)
# load base dimp
dimp_weights_path = os.path.join(settings.env.pretrained_networks,
'dimp50.pth')
base_net, _ = network_loading.load_network(checkpoint=dimp_weights_path)
net = kysnet_models.kysnet_res50(optim_iter=3,
cv_kernel_size=3,
cv_max_displacement=9,
cv_stride=1,
init_gauss_sigma=output_sigma *
settings.feature_sz,
train_feature_extractor=False,
train_iounet=False,
detach_length=0,
state_dim=8,
representation_predictor_dims=(16, ),
conf_measure='entropy',
dimp_thresh=0.05)
# Move pre-trained dimp weights
net.backbone_feature_extractor.load_state_dict(
base_net.feature_extractor.state_dict())
net.dimp_classifier.load_state_dict(base_net.classifier.state_dict())
net.bb_regressor.load_state_dict(base_net.bb_regressor.state_dict())
# To be safe
for p in net.backbone_feature_extractor.parameters():
p.requires_grad_(False)
for p in net.dimp_classifier.parameters():
p.requires_grad_(False)
for p in net.bb_regressor.parameters():
p.requires_grad_(False)
objective = {
'test_clf':
ltr_losses.LBHingev2(threshold=settings.hinge_threshold,
return_per_sequence=False),
'dimp_clf':
ltr_losses.LBHingev2(threshold=settings.hinge_threshold,
return_per_sequence=False),
'is_target':
ltr_losses.IsTargetCellLoss(return_per_sequence=False),
'clf_acc':
ltr_losses.TrackingClassificationAccuracy(threshold=0.25)
}
loss_weight = {
'test_clf': 1.0 * 500,
'test_clf_orig': 50,
'is_target': 0.1 * 500,
'is_target_after_prop': 0.1 * 500
}
dimp_jitter_fn = DiMPScoreJittering(distractor_ratio=0.1,
p_distractor=0.3,
max_distractor_enhance_factor=1.3,
min_distractor_enhance_factor=0.8)
actor = actors.KYSActor(net=net,
objective=objective,
loss_weight=loss_weight,
dimp_jitter_fn=dimp_jitter_fn)
optimizer = optim.Adam([{
'params': actor.net.predictor.parameters(),
'lr': 1e-2
}],
lr=1e-2)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,
step_size=15,
gamma=0.2)
trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer,
settings, lr_scheduler)
trainer.train(40, load_latest=True, fail_safe=True)
def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'distilled ATOM IoUNet with default settings according to the paper.'
settings.batch_size = 32
settings.num_workers = 8
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
# Train datasets
lasot_train = Lasot(settings.env.lasot_dir, split='train')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir,
set_ids=list(range(11)))
coco_train = MSCOCOSeq(settings.env.coco_dir)
# Validation datasets
trackingnet_val = TrackingNet(settings.env.trackingnet_dir,
set_ids=list(range(11, 12)))
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2),
tfm.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 = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# Data processing to do on the training pairs
proposal_params = {
'min_iou': 0.1,
'boxes_per_frame': 16,
'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]
}
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=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=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=1000 * 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)
# Load teacher network
teacher_net = atom_models.atom_resnet18(backbone_pretrained=True)
teacher_path = '/home/ddanier/CFKD/pytracking/networks/atom_default.pth'
teacher_net = loading.load_weights(teacher_net, teacher_path, strict=True)
print(
'*******************Teacher net loaded successfully*******************'
)
# Create student network and actor
student_net = atom_models.atom_mobilenetsmall(backbone_pretrained=False)
##########################################################
### Distil backbone first, turn off grad for regressor ###
##########################################################
for p in student_net.bb_regressor.parameters():
p.requires_grad_(False)
objective = distillation.CFKDLoss(
reg_loss=nn.MSELoss(),
w_ts=0.,
w_ah=0.,
w_cf=0.01,
w_fd=100.,
cf_layers=['conv1', 'layer1', 'layer2', 'layer3'])
actor = actors.AtomCompressionActor(student_net, teacher_net, objective)
# Optimizer
optimizer = optim.Adam(actor.student_net.feature_extractor.parameters(),
lr=1e-2)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,
step_size=15,
gamma=0.1)
# Create trainer
trainer = LTRDistillationTrainer(actor, [loader_train, loader_val],
optimizer, settings, lr_scheduler)
# Run training (set fail_safe=False if you are debugging)
trainer.train(50, load_latest=False, fail_safe=True)
########################################################
## Distil regressor next, turn off grad for backbone ###
########################################################
for p in trainer.actor.student_net.bb_regressor.parameters():
p.requires_grad_(True)
for p in trainer.actor.student_net.feature_extractor.parameters():
p.requires_grad_(False)
objective = distillation.CFKDLoss(reg_loss=nn.MSELoss(),
w_ts=1.,
w_ah=0.1,
w_cf=0.,
w_fd=0.)
trainer.actor.objective = objective
# Optimizer
trainer.optimizer = optim.Adam(
trainer.actor.student_net.bb_regressor.parameters(), lr=1e-2)
trainer.lr_scheduler = optim.lr_scheduler.StepLR(trainer.optimizer,
step_size=15,
gamma=0.1)
# Run training (set fail_safe=False if you are debugging)
trainer.train(100, load_latest=False, fail_safe=True)
def run(settings):
settings.description = 'Transformer-assisted tracker. Our baseline approach is SuperDiMP'
settings.batch_size = 40
settings.num_workers = 8
settings.multi_gpu = True
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 6.0
settings.output_sigma_factor = 1 / 4
settings.target_filter_sz = 4
settings.feature_sz = 22
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 3, 'test': 5.5}
settings.scale_jitter_factor = {'train': 0.25, 'test': 0.5}
settings.hinge_threshold = 0.05
# settings.print_stats = ['Loss/total', 'Loss/iou', 'ClfTrain/init_loss', 'ClfTrain/test_loss']
# Train datasets
lasot_train = Lasot(settings.env.lasot_dir, split='train')
got10k_train = Got10k(settings.env.got10k_dir, split='vottrain')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir,
set_ids=list(range(4)))
coco_train = MSCOCOSeq(settings.env.coco_dir)
# Validation datasets
got10k_val = Got10k(settings.env.got10k_dir, split='votval')
# Data transform
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05),
tfm.RandomHorizontalFlip(probability=0.5))
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2), tfm.RandomHorizontalFlip(probability=0.5),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
transform_val = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# The tracking pairs processing module
output_sigma = settings.output_sigma_factor / settings.search_area_factor
proposal_params = {
'boxes_per_frame': 128,
'gt_sigma': (0.05, 0.05),
'proposal_sigma': [(0.05, 0.05), (0.5, 0.5)]
}
label_params = {
'feature_sz': settings.feature_sz,
'sigma_factor': output_sigma,
'kernel_sz': settings.target_filter_sz
}
label_density_params = {
'feature_sz': settings.feature_sz,
'sigma_factor': output_sigma,
'kernel_sz': settings.target_filter_sz
}
data_processing_train = processing.KLDiMPProcessing(
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,
crop_type='inside_major',
max_scale_change=1.5,
mode='sequence',
proposal_params=proposal_params,
label_function_params=label_params,
label_density_params=label_density_params,
transform=transform_train,
joint_transform=transform_joint)
data_processing_val = processing.KLDiMPProcessing(
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,
crop_type='inside_major',
max_scale_change=1.5,
mode='sequence',
proposal_params=proposal_params,
label_function_params=label_params,
label_density_params=label_density_params,
transform=transform_val,
joint_transform=transform_joint)
# Train sampler and loader
dataset_train = sampler.DiMPSampler(
[lasot_train, got10k_train, trackingnet_train, coco_train],
[1, 1, 1, 1],
samples_per_epoch=50000,
max_gap=500,
num_test_frames=3,
num_train_frames=3,
processing=data_processing_train)
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)
# Validation samplers and loaders
dataset_val = sampler.DiMPSampler([got10k_val], [1],
samples_per_epoch=10000,
max_gap=500,
num_test_frames=3,
num_train_frames=3,
processing=data_processing_val)
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 and actor
net = dimpnet.dimpnet50(
filter_size=settings.target_filter_sz,
backbone_pretrained=True,
optim_iter=5,
clf_feat_norm=True,
clf_feat_blocks=0,
final_conv=True,
out_feature_dim=512,
optim_init_step=0.9,
optim_init_reg=0.1,
init_gauss_sigma=output_sigma * settings.feature_sz,
num_dist_bins=100,
bin_displacement=0.1,
mask_init_factor=3.0,
target_mask_act='sigmoid',
score_act='relu',
frozen_backbone_layers=['conv1', 'bn1', 'layer1', 'layer2'])
# Wrap the network for multi GPU training
if settings.multi_gpu:
net = MultiGPU(net, dim=1)
objective = {
'bb_ce': klreg_losses.KLRegression(),
'test_clf': ltr_losses.LBHinge(threshold=settings.hinge_threshold)
}
loss_weight = {
'bb_ce': 0.01,
'test_clf': 100,
'test_init_clf': 100,
'test_iter_clf': 400
}
actor = tracking_actors.KLDiMPActor(net=net,
objective=objective,
loss_weight=loss_weight)
# Optimizer
optimizer = optim.Adam(
[{
'params': actor.net.classifier.filter_initializer.parameters(),
'lr': 5e-5
}, {
'params': actor.net.classifier.filter_optimizer.parameters(),
'lr': 5e-4
}, {
'params': actor.net.classifier.feature_extractor.parameters(),
'lr': 5e-5
}, {
'params': actor.net.classifier.transformer.parameters(),
'lr': 1e-3
}, {
'params': actor.net.bb_regressor.parameters(),
'lr': 1e-3
}, {
'params': actor.net.feature_extractor.layer3.parameters(),
'lr': 2e-5
}],
lr=2e-4)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,
step_size=15,
gamma=0.2)
trainer = LTRTrainer(actor, [loader_train, loader_val], optimizer,
settings, lr_scheduler)
trainer.train(50, load_latest=True, fail_safe=True)
def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'ATOM IoUNet with default settings, but additionally using GOT10k for training.'
settings.batch_size = 64
settings.num_workers = 8
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
# Train datasets
# lasot_train = Lasot(settings.env.lasot_dir, split='train')
# got10k_train = Got10k(settings.env.got10k_dir, split='vottrain')
# trackingnet_train = TrackingNet(settings.env.trackingnet_dir, set_ids=list(range(4)))
# coco_train = MSCOCOSeq(settings.env.coco_dir)
coco_train = MSCOCOSeq_depth(settings.env.cocodepth_dir,
dtype='rgbcolormap')
lasot_depth_train = Lasot_depth(root=settings.env.lasotdepth_dir,
dtype='rgbcolormap')
depthtrack_train = DepthTrack(root=settings.env.depthtrack_dir,
dtype='rgbcolormap')
depthtrack_horizontal_train = DepthTrack(
root=settings.env.depthtrack_horizontal_dir, dtype='rgbcolormap')
depthtrack_vertical_train = DepthTrack(
root=settings.env.depthtrack_vertical_dir, dtype='rgbcolormap')
# Validation datasets
# got10k_val = Got10k(settings.env.got10k_dir, split='votval')
cdtb_val = CDTB(settings.env.cdtb_dir, split='val', dtype='rgbcolormap')
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2),
tfm.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 = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# Data processing to do on the training pairs
proposal_params = {
'min_iou': 0.1,
'boxes_per_frame': 16,
'sigma_factor': [0.01, 0.05, 0.1, 0.2, 0.3]
}
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=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=proposal_params,
transform=transform_val,
joint_transform=transform_joint)
# The sampler for training
dataset_train = sampler.ATOMSampler([
lasot_depth_train, depthtrack_train, depthtrack_horizontal_train,
depthtrack_vertical_train, coco_train
], [1, 1, 1, 1, 1],
samples_per_epoch=1000 *
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([cdtb_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 and actor
net = atom_models.atom_resnet18_DeT(
backbone_pretrained=True,
merge_type='max') # 'mean', 'conv', 'weightedSum'
objective = nn.MSELoss()
actor = actors.AtomActor(net=net, objective=objective)
# Optimizer
# optimizer = optim.Adam(actor.net.bb_regressor.parameters(), lr=1e-3)
optimizer = optim.Adam(
[
{
'params': actor.net.bb_regressor.parameters()
},
{
'params': actor.net.feature_extractor.parameters(),
'lr': 2e-5
},
{
'params': actor.net.feature_extractor_depth.parameters(),
'lr': 2e-5
},
# {'params': actor.net.merge_layer2.parameters(), 'lr': 2e-5},
# {'params': actor.net.merge_layer3.parameters(), 'lr': 2e-5},
],
lr=1e-3)
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(80, load_latest=True, fail_safe=True)
def run(settings):
# Most common settings are assigned in the settings struct
settings.description = 'ATOM using the probabilistic maximum likelihood trained regression model for bounding-box' \
'regression presented in [https://arxiv.org/abs/1909.12297].'
settings.batch_size = 64
settings.num_workers = 8
settings.print_interval = 1
settings.normalize_mean = [0.485, 0.456, 0.406]
settings.normalize_std = [0.229, 0.224, 0.225]
settings.search_area_factor = 5.0
settings.feature_sz = 18
settings.output_sz = settings.feature_sz * 16
settings.center_jitter_factor = {'train': 0, 'test': 4.5}
settings.scale_jitter_factor = {'train': 0, 'test': 0.5}
# Train datasets
lasot_train = Lasot(settings.env.lasot_dir, split='train')
got10k_train = Got10k(settings.env.got10k_dir, split='vottrain')
trackingnet_train = TrackingNet(settings.env.trackingnet_dir,
set_ids=list(range(4)))
coco_train = MSCOCOSeq(settings.env.coco_dir)
# Validation datasets
got10k_val = Got10k(settings.env.got10k_dir, split='votval')
# The joint augmentation transform, that is applied to the pairs jointly
transform_joint = tfm.Transform(tfm.ToGrayscale(probability=0.05))
# The augmentation transform applied to the training set (individually to each image in the pair)
transform_train = tfm.Transform(
tfm.ToTensorAndJitter(0.2),
tfm.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 = tfm.Transform(
tfm.ToTensor(),
tfm.Normalize(mean=settings.normalize_mean,
std=settings.normalize_std))
# Data processing to do on the training pairs
proposal_params = {
'boxes_per_frame': 128,
'gt_sigma': (0, 0),
'proposal_sigma': [(0.05, 0.05), (0.5, 0.5)],
'add_mean_box': True
}
data_processing_train = processing.KLBBregProcessing(
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=proposal_params,
transform=transform_train,
joint_transform=transform_joint)
# Data processing to do on the validation pairs
data_processing_val = processing.KLBBregProcessing(
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=proposal_params,
transform=transform_val,
joint_transform=transform_joint)
# The sampler for training
dataset_train = sampler.ATOMSampler(
[lasot_train, got10k_train, trackingnet_train, coco_train],
[1, 1, 1, 1],
samples_per_epoch=1000 * settings.batch_size,
max_gap=200,
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([got10k_val], [1],
samples_per_epoch=500 *
settings.batch_size,
max_gap=200,
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 and actor
net = atom_models.atom_resnet18(backbone_pretrained=True)
objective = klreg_losses.MLRegression()
actor = bbreg_actors.AtomBBKLActor(net=net, objective=objective)
# Optimizer
optimizer = optim.Adam(actor.net.bb_regressor.parameters(), lr=1e-3)
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(50, load_latest=True, fail_safe=True)
