def steepest_descent_learn_filter_resnet18_newiou(filter_size=1, optim_iter=3, optim_init_step=1.0, optim_init_reg=0.01, output_activation=None,
classification_layer='layer3', backbone_pretrained=False, clf_feat_blocks=1,
clf_feat_norm=True, init_filter_norm=False, final_conv=False,
out_feature_dim=256, init_gauss_sigma=1.0, num_dist_bins=5, bin_displacement=1.0, test_loss=None,
mask_init_factor=4.0, iou_input_dim=(256,256), iou_inter_dim=(256,256),
jitter_sigma_factor=None, train_backbone=True):
# backbone
backbone_net = backbones.resnet18(pretrained=backbone_pretrained)
norm_scale = math.sqrt(1.0 / (out_feature_dim * filter_size * filter_size))
# classifier
clf_feature_extractor = clf_features.residual_basic_block(num_blocks=clf_feat_blocks, l2norm=clf_feat_norm,
final_conv=final_conv, norm_scale=norm_scale,
out_dim=out_feature_dim)
initializer = clf_initializer.FilterInitializerLinear(filter_size=filter_size, filter_norm=init_filter_norm, feature_dim=out_feature_dim)
optimizer = clf_optimizer.SteepestDescentLearn(num_iter=optim_iter, filter_size=filter_size, init_step_length=optim_init_step,
init_filter_reg=optim_init_reg, feature_dim=out_feature_dim,
init_gauss_sigma=init_gauss_sigma, num_dist_bins=num_dist_bins,
bin_displacement=bin_displacement, test_loss=test_loss, mask_init_factor=mask_init_factor)
classifier = target_clf.LinearFilter(filter_size=filter_size, filter_initializer=initializer,
filter_optimizer=optimizer, feature_extractor=clf_feature_extractor,
output_activation=output_activation, jitter_sigma_factor=jitter_sigma_factor)
# Bounding box regressor
bb_regressor = bbmodels.AtomIoUNet(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim)
net = OptimTracker(feature_extractor=backbone_net, classifier=classifier, bb_regressor=bb_regressor,
classification_layer=classification_layer, bb_regressor_layer=['layer2', 'layer3'], train_feature_extractor=train_backbone)
return net
def steepest_descent_learn_filter_resnet50_newiou(filter_size=1, optim_iter=3, optim_init_step=1.0, optim_init_reg=0.01, output_activation=None,
classification_layer='layer3', backbone_pretrained=False, clf_feat_blocks=1,
clf_feat_norm=True, init_filter_norm=False, final_conv=False,
out_feature_dim=256, init_gauss_sigma=1.0, num_dist_bins=5, bin_displacement=1.0, test_loss=None,
mask_init_factor=4.0, iou_input_dim=(256,256), iou_inter_dim=(256,256),
jitter_sigma_factor=None):
# backbone
backbone_net = backbones.resnet50(pretrained=backbone_pretrained)
norm_scale = math.sqrt(1.0 / (out_feature_dim * filter_size * filter_size))
# classifier
clf_feature_extractor = clf_features.residual_bottleneck_comb(num_blocks=clf_feat_blocks, l2norm=clf_feat_norm,
final_conv=final_conv, norm_scale=norm_scale,
out_dim=out_feature_dim)
initializer = clf_initializer.FilterInitializerLinear(filter_size=filter_size, filter_norm=init_filter_norm, feature_dim=out_feature_dim)
optimizer = clf_optimizer.SteepestDescentLearn(num_iter=optim_iter, filter_size=filter_size, init_step_length=optim_init_step,
init_filter_reg=optim_init_reg, feature_dim=out_feature_dim,
init_gauss_sigma=init_gauss_sigma, num_dist_bins=num_dist_bins,
bin_displacement=bin_displacement, test_loss=test_loss, mask_init_factor=mask_init_factor)
classifier = target_clf.LinearFilter(filter_size=filter_size, filter_initializer=initializer,
filter_optimizer=optimizer, feature_extractor=clf_feature_extractor,
output_activation=output_activation, jitter_sigma_factor=jitter_sigma_factor)
# Bounding box regressor
# combine RGB and TIR by 2*
bb_regressor = bbmodels.AtomIoUNet(input_dim=(4*128,4*256), pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim)
# load pretrained model
pretrainmodel_path='/home/lichao/projects/pytracking_lichao/pytracking/DiMP_nets/sdlearn_300_onlytestloss_lr_causal_mg30_iou_nocf_res50_lfilt512_coco/OptimTracker_ep0040.pth.tar'
pretrainmodel = loading.torch_load_legacy(pretrainmodel_path)['net']
usepretrain = True; updback = True; updcls = True; updbb = True
if usepretrain:
if updback:
# update backbone
backbone_dict = backbone_net.state_dict()
pretrain_dict = {k[len('feature_extractor.'):]: v for k, v in pretrainmodel.items() if k[len('feature_extractor.'):] in backbone_dict}
backbone_net.load_state_dict(pretrain_dict)
if updcls:
# update classifier
pretrainmodel['classifier.feature_extractor.0.weight']=torch.cat((pretrainmodel['classifier.feature_extractor.0.weight'],pretrainmodel['classifier.feature_extractor.0.weight']),1)
classifier_dict = classifier.state_dict()
pretrain_dict = {k[len('classifier.'):]: v for k, v in pretrainmodel.items() if k[len('classifier.'):] in classifier_dict}
#classifier_dict.update(pretrain_dict)
classifier.load_state_dict(pretrain_dict)
if updbb:
# update Bounding box regressor
bb_regressor_dict = bb_regressor.state_dict()
pretrain_dict = {k[len('bb_regressor.'):]: v for k, v in pretrainmodel.items() if k[len('bb_regressor.'):] in bb_regressor_dict}
bb_regressor.load_state_dict(pretrain_dict)
net = OptimTracker(feature_extractor=backbone_net, classifier=classifier, bb_regressor=bb_regressor,
classification_layer=classification_layer, bb_regressor_layer=['layer2', 'layer3'])
return net
def kysnet_res50(filter_size=4,
optim_iter=3,
appearance_feature_dim=512,
optim_init_step=0.9,
optim_init_reg=0.1,
classification_layer='layer3',
backbone_pretrained=True,
clf_feat_blocks=0,
clf_feat_norm=True,
final_conv=True,
init_filter_norm=False,
mask_init_factor=3.0,
score_act='relu',
target_mask_act='sigmoid',
num_dist_bins=100,
bin_displacement=0.1,
detach_length=float('Inf'),
train_feature_extractor=True,
train_iounet=True,
iou_input_dim=(256, 256),
iou_inter_dim=(256, 256),
cv_kernel_size=3,
cv_max_displacement=9,
cv_stride=1,
init_gauss_sigma=1.0,
state_dim=8,
representation_predictor_dims=(64, 32),
gru_ksz=3,
conf_measure='max',
dimp_thresh=None):
# ######################## backbone ########################
backbone_net = backbones.resnet50(pretrained=backbone_pretrained)
norm_scale = math.sqrt(
1.0 / (appearance_feature_dim * filter_size * filter_size))
# ######################## classifier ########################
clf_feature_extractor = clf_features.residual_bottleneck(
num_blocks=clf_feat_blocks,
l2norm=clf_feat_norm,
final_conv=final_conv,
norm_scale=norm_scale,
out_dim=appearance_feature_dim)
# Initializer for the DiMP classifier
initializer = clf_initializer.FilterInitializerLinear(
filter_size=filter_size,
filter_norm=init_filter_norm,
feature_dim=appearance_feature_dim)
# Optimizer for the DiMP classifier
optimizer = clf_optimizer.DiMPSteepestDescentGN(
num_iter=optim_iter,
feat_stride=16,
init_step_length=optim_init_step,
init_filter_reg=optim_init_reg,
init_gauss_sigma=init_gauss_sigma,
num_dist_bins=num_dist_bins,
bin_displacement=bin_displacement,
mask_init_factor=mask_init_factor,
score_act=score_act,
act_param=None,
mask_act=target_mask_act,
detach_length=detach_length)
# The classifier module
classifier = target_clf.LinearFilter(
filter_size=filter_size,
filter_initializer=initializer,
filter_optimizer=optimizer,
feature_extractor=clf_feature_extractor)
# Bounding box regressor
bb_regressor = bbmodels.AtomIoUNet(input_dim=(4 * 128, 4 * 256),
pred_input_dim=iou_input_dim,
pred_inter_dim=iou_inter_dim)
cost_volume_layer = cost_volume.CostVolume(cv_kernel_size,
cv_max_displacement,
stride=cv_stride,
abs_coordinate_output=True)
motion_response_predictor = resp_pred.ResponsePredictor(
state_dim=state_dim,
representation_predictor_dims=representation_predictor_dims,
gru_ksz=gru_ksz,
conf_measure=conf_measure,
dimp_thresh=dimp_thresh)
response_predictor = predictor_wrappers.PredictorWrapper(
cost_volume_layer, motion_response_predictor)
net = KYSNet(backbone_feature_extractor=backbone_net,
dimp_classifier=classifier,
predictor=response_predictor,
bb_regressor=bb_regressor,
classification_layer=classification_layer,
bb_regressor_layer=['layer2', 'layer3'],
train_feature_extractor=train_feature_extractor,
train_iounet=train_iounet)
return net
