def atom_resnet18_DeT(iou_input_dim=(256,256), iou_inter_dim=(256,256), backbone_pretrained=True, merge_type='mean'): # backbones backbone_net = backbones.resnet18(pretrained=backbone_pretrained) backbone_net_depth = backbones.resnet18(pretrained=backbone_pretrained) # Bounding box regressor iou_predictor = bbmodels.AtomIoUNet(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) net = ATOMnet_DeT(feature_extractor=backbone_net, feature_extractor_depth=backbone_net_depth, bb_regressor=iou_predictor, bb_regressor_layer=['layer2', 'layer3'], extractor_grad=False, merge_type=merge_type) return net
def segm_resnet18(segm_input_dim=(256, 256), segm_inter_dim=(256, 256), backbone_pretrained=True, topk_pos=3, topk_neg=3, mixer_channels=2): # backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained) # segmentation dimensions segm_input_dim = (64, 64, 128, 256) segm_inter_dim = (4, 16, 32, 64) segm_dim = (64, 64) # convolutions before cosine similarity # segmentation segm_predictor = segmmodels.SegmNet(segm_input_dim=segm_input_dim, segm_inter_dim=segm_inter_dim, segm_dim=segm_dim, topk_pos=topk_pos, topk_neg=topk_neg, mixer_channels=mixer_channels) net = SegmNet(feature_extractor=backbone_net, segm_predictor=segm_predictor, segm_layers=['conv1', 'layer1', 'layer2', 'layer3'], extractor_grad=False) return net
def SBDT_resnet18(input_dim=(128, 256), locator_inter_dim=(128, 256), iou_input_dim=(256, 256), iou_inter_dim=(256, 256), backbone_pretrained=True): # backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained) # Bounding box regressor iou_predictor = bbmodels.AtomIoUNet(input_dim=input_dim, pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) # locator location_predictor = locmodels.OnlineRRNet18( input_dim=input_dim, pred_input_dim=locator_inter_dim) # SBDTNet net = SBDTNet(feature_extractor=backbone_net, feature_layer=['layer2', 'layer3'], bb_regressor=iou_predictor, location_predictor=location_predictor, extractor_grad=False) return net
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 uinet_resnet18(backbone_pretrained=True): # backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained,output_layers=['conv1', 'layer1', 'layer2', 'layer3', 'layer4']) # Bounding box regressor mask_predictor = UNET.U_Net() net = UInet(feature_extractor=backbone_net, unet=mask_predictor, extractor_grad=False) return net
def atom_resnet18(iou_input_dim=(256,256), iou_inter_dim=(256,256), backbone_pretrained=True): # backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained) # Bounding box regressor iou_predictor = bbmodels.AtomIoUNet(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) net = ATOMnet(feature_extractor=backbone_net, bb_regressor=iou_predictor, bb_regressor_layer=['layer2', 'layer3'], extractor_grad=False) return net
def klcedimpnet18(filter_size=1, optim_iter=5, optim_init_step=1.0, optim_init_reg=0.01, classification_layer='layer3', feat_stride=16, backbone_pretrained=True, clf_feat_blocks=1, clf_feat_norm=True, init_filter_norm=False, final_conv=True, out_feature_dim=256, gauss_sigma=1.0, iou_input_dim=(256, 256), iou_inter_dim=(256, 256), detach_length=float('Inf'), alpha_eps=0.0, train_feature_extractor=True, init_uni_weight=None, optim_min_reg=1e-3, init_initializer='default', normalize_label=False, label_shrink=0, softmax_reg=None, label_threshold=0, final_relu=False, init_pool_square=False, frozen_backbone_layers=()): if not train_feature_extractor: frozen_backbone_layers = 'all' # Backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained, frozen_layers=frozen_backbone_layers) # Feature normalization norm_scale = math.sqrt(1.0 / (out_feature_dim * filter_size * filter_size)) # Classifier features 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, final_relu=final_relu) # Initializer for the DiMP classifier initializer = clf_initializer.FilterInitializerLinear(filter_size=filter_size, filter_norm=init_filter_norm, feature_dim=out_feature_dim, init_weights=init_initializer, pool_square=init_pool_square) # Optimizer for the DiMP classifier optimizer = clf_optimizer.PrDiMPSteepestDescentNewton(num_iter=optim_iter, feat_stride=feat_stride, init_step_length=optim_init_step, init_filter_reg=optim_init_reg, gauss_sigma=gauss_sigma, detach_length=detach_length, alpha_eps=alpha_eps, init_uni_weight=init_uni_weight, min_filter_reg=optim_min_reg, normalize_label=normalize_label, label_shrink=label_shrink, softmax_reg=softmax_reg, label_threshold=label_threshold) # 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(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) # DiMP network net = DiMPnet(feature_extractor=backbone_net, classifier=classifier, bb_regressor=bb_regressor, classification_layer=classification_layer, bb_regressor_layer=['layer2', 'layer3']) return net
def dimpnet18(filter_size=1, optim_iter=5, optim_init_step=1.0, optim_init_reg=0.01, classification_layer='layer3', feat_stride=16, backbone_pretrained=True, clf_feat_blocks=1, clf_feat_norm=True, init_filter_norm=False, final_conv=True, out_feature_dim=256, init_gauss_sigma=1.0, num_dist_bins=5, bin_displacement=1.0, mask_init_factor=4.0, iou_input_dim=(256, 256), iou_inter_dim=(256, 256), score_act='relu', act_param=None, target_mask_act='sigmoid', detach_length=float('Inf'), frozen_backbone_layers=()): # Backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained, frozen_layers=frozen_backbone_layers) # Feature normalization norm_scale = math.sqrt(1.0 / (out_feature_dim * filter_size * filter_size)) # Classifier features 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 for the DiMP classifier initializer = clf_initializer.FilterInitializerLinear(filter_size=filter_size, filter_norm=init_filter_norm, feature_dim=out_feature_dim) # Optimizer for the DiMP classifier optimizer = clf_optimizer.DiMPSteepestDescentGN(num_iter=optim_iter, feat_stride=feat_stride, 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=act_param, 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(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) # DiMP network net = DiMPnet(feature_extractor=backbone_net, classifier=classifier, bb_regressor=bb_regressor, classification_layer=classification_layer, bb_regressor_layer=['layer2', 'layer3']) return net
def L2dimpnet18(filter_size=1, optim_iter=5, optim_init_step=1.0, optim_init_reg=0.01, classification_layer='layer3', feat_stride=16, backbone_pretrained=True, clf_feat_blocks=1, clf_feat_norm=True, init_filter_norm=False, final_conv=True, out_feature_dim=256, iou_input_dim=(256, 256), iou_inter_dim=(256, 256), detach_length=float('Inf'), hinge_threshold=-999, gauss_sigma=1.0, alpha_eps=0): # Backbone backbone_net = backbones.resnet18(pretrained=backbone_pretrained) # Feature normalization norm_scale = math.sqrt(1.0 / (out_feature_dim * filter_size * filter_size)) # Classifier features 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 for the DiMP classifier initializer = clf_initializer.FilterInitializerLinear(filter_size=filter_size, filter_norm=init_filter_norm, feature_dim=out_feature_dim) # Optimizer for the DiMP classifier optimizer = clf_optimizer.DiMPL2SteepestDescentGN(num_iter=optim_iter, feat_stride=feat_stride, init_step_length=optim_init_step, hinge_threshold=hinge_threshold, init_filter_reg=optim_init_reg, gauss_sigma=gauss_sigma, detach_length=detach_length, alpha_eps=alpha_eps) # 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(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim) # DiMP network net = DiMPnet(feature_extractor=backbone_net, classifier=classifier, bb_regressor=bb_regressor, classification_layer=classification_layer, bb_regressor_layer=['layer2', 'layer3']) return net
def atom_resnet18(iou_input_dim=(256, 256), iou_inter_dim=(256, 256), backbone_pretrained=True, cpu=False): # backbone backbone_net = backbones.resnet18( output_layers=['conv1', 'layer1', 'layer2', 'layer3'], pretrained=backbone_pretrained) # Bounding box regressor iou_predictor = bbmodels.AtomIoUNet(pred_input_dim=iou_input_dim, pred_inter_dim=iou_inter_dim, cpu=cpu) # if training CPU version, then need to fine-tune regressor regressor_grad = True if cpu else False net = ATOMnet(feature_extractor=backbone_net, bb_regressor=iou_predictor, bb_regressor_layer=['layer2', 'layer3'], extractor_grad=False, regressor_grad=regressor_grad) return net