Functions — github.com/IRVLUTD/UnseenObjectsWithMeanShift

hub / github.com/IRVLUTD/UnseenObjectsWithMeanShift / functions

Functions680 in github.com/IRVLUTD/UnseenObjectsWithMeanShift

⨍ Functions 680◇ Types & classes 107

↓ 1 callersMethodrun_network

(self)

ros/test_images_segmentation.py:144

↓ 1 callersMethodsample_pixels

(self, labels, num=1000)

lib/datasets/tabletop_dataset.py:303

↓ 1 callersMethodsample_pixels

(self, labels, num=1000)

lib/datasets/tabletop_object.py:241

↓ 1 callersMethodsample_pixels

(self, labels, num=1000)

lib/datasets/pushing_dataset.py:284

↓ 1 callersFunctionseed_hill_climbing_ball

Runs mean shift hill climbing algorithm on the seeds. The seeds climb the distribution given by the KDE of X @param X: a [n x d] tor

lib/utils/mean_shift.py:79

↓ 1 callersFunctionseed_hill_climbing_ball

Runs mean shift hill climbing algorithm on the seeds. The seeds climb the distribution given by the KDE of X @param X: a [n x d] tor

MSMFormer/meanshiftformer/modeling/transformer_decoder/mean_shift.py:79

↓ 1 callersFunctionselect_smart_seeds

Selects seeds that are as far away as possible @param X: a [n x d] torch.FloatTensor of d-dim unit vectors @param num_seeds: number

lib/utils/mean_shift.py:128

↓ 1 callersFunctionseparate_coco_semantic_from_panoptic

Create semantic segmentation annotations from panoptic segmentation annotations, to be used by PanopticFPN. It maps all thing categories

MSMFormer/datasets/prepare_coco_semantic_annos_from_panoptic_annos.py:29

↓ 1 callersFunctiontest_sample

(cfg, sample, predictor, visualization=False, topk=False, confident_score=0.9, low_threshold=0.4)

lib/fcn/test_utils.py:169

↓ 1 callersFunctiontest_sample_crop

(cfg, sample, predictor, predictor_crop, visualization = False, topk=False, confident_score=0.7, low_threshold

lib/fcn/test_utils.py:245

↓ 1 callersFunctiontest_segnet

(test_loader, network, output_dir, network_crop)

lib/fcn/test_dataset.py:271

↓ 1 callersMethodtest_with_TTA

(cls, cfg, model)

MSMFormer/tabletop_train_net_pretrained.py:194

↓ 1 callersFunctiontrain_segnet

(train_loader, network, optimizer, epoch)

lib/fcn/train.py:37

↓ 1 callersFunctiontranslate

Translate img by tx, ty @param img: a [H x W x C] image (could be an RGB image, flow image, or label image)

lib/utils/augmentation.py:34

↓ 1 callersMethodupdate

(self, val, n=1)

lib/fcn/test_dataset.py:34

↓ 1 callersFunctionupdate_model

(model, data)

lib/networks/resnet.py:295

↓ 1 callersMethodweight_parameters

(self)

lib/networks/SEG.py:122

↓ 1 callersFunctionwindow_reverse

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

MSMFormer/meanshiftformer/modeling/backbone/swin.py:58

↓ 1 callersMethodwith_pos_embed

(tensor, pos)

MSMFormer/meanshiftformer/modeling/pixel_decoder/msdeformattn.py:113

↓ 1 callersFunctionzero_diagonal

Sets diagonal elements of x to 0 @param x: a [batch_size x S x S] torch.FloatTensor

lib/networks/embedding.py:14

↓ 1 callersFunctionzero_diagonal

Sets diagonal elements of x to 0 @param x: a [batch_size x S x S] torch.FloatTensor

MSMFormer/meanshiftformer/embedding.py:14

FunctionPYBIND11_MODULE

MSMFormer/meanshiftformer/modeling/pixel_decoder/ops/src/vision.cpp:18

FunctionT_inv_transform

:param T_src: :param T_tgt: :return: T_delta: delta in pixel

lib/utils/se3.py:48

Method__call__

Args: sample: a dict of a data sample # ignore: original_image (np.ndarray): an image of shape (H, W, C) (in BGR orde

lib/fcn/test_utils.py:116

Method__call__

Args: sample: a dict of a data sample # ignore: original_image (np.ndarray): an image of shape (H, W, C) (in BGR orde

lib/fcn/test_utils.py:152

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

lib/datasets/tablet_instance_mapper.py:86

Method__call__

Same input/output format as :meth:`SemanticSegmentor.forward`

MSMFormer/meanshiftformer/test_time_augmentation.py:49

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/mask_former_semantic_dataset_mapper.py:98

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/mask_former_panoptic_dataset_mapper.py:59

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/coco_panoptic_new_baseline_dataset_mapper.py:105

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/unseen_instance_dataset_mapper.py:293

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/coco_instance_new_baseline_dataset_mapper.py:121

Method__call__

Args: dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format. Returns: dict: a format that

MSMFormer/meanshiftformer/data/dataset_mappers/mask_former_instance_dataset_mapper.py:87

Method__copy_matrix

Return an exact copy of the supplied matrix

lib/utils/munkres.py:374

Method__getitem__

(self, idx)

lib/datasets/ocid_object.py:71

Method__getitem__

(self, idx)

lib/datasets/ocid_dataset.py:75

Method__getitem__

(self, idx)

lib/datasets/tabletop_dataset.py:319

Method__getitem__

(self, idx)

lib/datasets/tabletop_object.py:257

Method__getitem__

(self, idx)

lib/datasets/load_OCID_UOAIS.py:77

Method__getitem__

(self, idx)

lib/datasets/pushing_dataset.py:311

Method__getitem__

(self, idx)

lib/datasets/mixture_dataset.py:50

Method__getitem__

(self, idx)

lib/datasets/uoais_dataset.py:174

Method__getitem__

(self, idx)

lib/datasets/osd_object.py:63

Method__getitem__

(self, idx)

lib/datasets/load_OSD_UOAIS.py:153

Method__init__

Create a new instance

lib/utils/munkres.py:250

Method__init__

(self, in_channels, out_channels, num_groups, ksize=3, stride=1)

lib/networks/unets.py:16

Method__init__

(self, in_channels, out_channels, num_groups, ksize=3, stride=1)

lib/networks/unets.py:41

Method__init__

(self, in_channels, out_channels, num_groups, num_encoders, ksize=3, stride=1)

lib/networks/unets.py:66

Method__init__

(self, num_encoders, feature_dim, coordconv=False)

lib/networks/unets.py:180

Method__init__

(self, init_weights=True, batch_norm=False, in_channels=3, network_name='vgg', num_units=64,

lib/networks/SEG.py:28

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:54

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:93

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:137

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:175

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:214

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:252

Method__init__

(self, num_classes=1000, input_channels=3, pretrained=True)

lib/networks/resnet_dilated.py:290

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:332

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:361

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:399

Method__init__

(self, num_classes=1000)

lib/networks/resnet_dilated.py:436

Method__init__

(self, alpha, delta, lambda_intra, lambda_inter, metric='cosine', normalize=True)

lib/networks/embedding.py:59

Method__init__

(self, inplanes, planes, stride=1, downsample=None, dilation=1)

lib/networks/resnet.py:47

Method__init__

(self, inplanes, planes, stride=1, downsample=None, dilation=1)

lib/networks/resnet.py:79

lib/fcn/test_dataset.py:25

Method__init__

(self, image_set, ocid_object_path = None)

lib/datasets/ocid_object.py:24

Method__init__

(self, image_set, ocid_object_path = None)

lib/datasets/ocid_dataset.py:24

Method__init__

(self, image_set="train", tabletop_object_path = None, data_mapper = False, eval=False)

lib/datasets/tabletop_dataset.py:117

Method__init__

(self, image_set, tabletop_object_path = None)

lib/datasets/tabletop_object.py:97

Method__init__

(self, image_set, ocid_object_path = None)

lib/datasets/load_OCID_UOAIS.py:26

Method__init__

(self, image_set="train", pushing_object_path = None, eval=False)

lib/datasets/pushing_dataset.py:99

Method__init__

NOTE: this interface is experimental. Args: is_train: for training or inference augmentations: a list of augm

lib/datasets/tablet_instance_mapper.py:32

Method__init__

(self, image_set="train", eval=False)

lib/datasets/mixture_dataset.py:30

Method__init__

(self, image_set="train", uoais_object_path = None, eval=False)

lib/datasets/uoais_dataset.py:75

Method__init__

(self, image_set, osd_object_path = None)

lib/datasets/osd_object.py:24

Method__init__

(self)

lib/datasets/imdb.py:16

Method__init__

(self, image_set, osd_object_path = None)

lib/datasets/load_OSD_UOAIS.py:114

Method__init__

(self, predictor, predictor_crop, cfg_transformer, cfg_transformer_crop)

ros/test_images_segmentation_transformer.py:52

Method__init__

(self, network, network_crop)

ros/test_images_segmentation.py:50

Method__init__

(self)

ros/collect_images_realsense.py:24

Method__init__

Args: cfg (CfgNode): model (SemanticSegmentor): a SemanticSegmentor to apply TTA on. tta_mapper (callable

MSMFormer/meanshiftformer/test_time_augmentation.py:27

Method__init__

Args: backbone: a backbone module, must follow detectron2's backbone interface sem_seg_head: a module that predicts s

MSMFormer/meanshiftformer/pretrained_meanshiftformer_model.py:57

Method__init__

Args: backbone: a backbone module, must follow detectron2's backbone interface sem_seg_head: a module that predicts s

MSMFormer/meanshiftformer/meanshiftformer_model.py:48

Method__init__

(self, alpha, delta, lambda_intra, lambda_inter, metric='cosine', normalize=True)

MSMFormer/meanshiftformer/embedding.py:59

Method__init__

Creates the matcher Params: cost_class: This is the relative weight of the classification error in the matching cost

MSMFormer/meanshiftformer/modeling/matcher.py:78

Method__init__

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category ma

MSMFormer/meanshiftformer/modeling/criterion.py:97

Method__init__

(self, encoder_layer, num_layers, norm=None)

MSMFormer/meanshiftformer/modeling/transformer_decoder/transformer.py:79

Method__init__

(self, decoder_layer, num_layers, norm=None, return_intermediate=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/transformer.py:106

Method__init__

( self, d_model, nhead, dim_feedforward=2048, dropout=0.1, act

MSMFormer/meanshiftformer/modeling/transformer_decoder/transformer.py:155

Method__init__

( self, d_model, nhead, dim_feedforward=2048, dropout=0.1, act

MSMFormer/meanshiftformer/modeling/transformer_decoder/transformer.py:231

Method__init__

NOTE: this interface is experimental. Args: in_channels: channels of the input features mask_classification:

MSMFormer/meanshiftformer/modeling/transformer_decoder/maskformer_transformer_decoder.py:33

Method__init__

(self, embed_dim, num_heads=1, dropout=0., bias=True, add_bias_kv=False, add_zero_attn=False,

MSMFormer/meanshiftformer/modeling/transformer_decoder/attention_util.py:469

Method__init__

(self, d_model, nhead, dropout=0.0, activation="relu", normalize_before=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:29

Method__init__

(self, d_model, nhead, dropout=0.0, activation="relu", normalize_before=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:87

Method__init__

(self, d_model, nhead, dropout=0.0, activation="relu", normalize_before=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:150

Method__init__

(self, d_model, nhead=1, dropout=0.0, activation="relu", layer_normalize_before=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:210

Method__init__

(self, d_model, dim_feedforward=2048, dropout=0.0, activation="relu", normalize_before=False)

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:277

Method__init__

NOTE: this interface is experimental. Args: in_channels: channels of the input features mask_classification:

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:372

Method__init__

NOTE: this interface is experimental. Args: in_channels: channels of the input features mask_classification:

MSMFormer/meanshiftformer/modeling/transformer_decoder/meanshiftformer_transformer_decoder.py:726

← previous next →301–400 of 680, ranked by callers