Functions — github.com/UX-Decoder/Semantic-SAM

hub / github.com/UX-Decoder/Semantic-SAM / functions

Functions759 in github.com/UX-Decoder/Semantic-SAM

⨍ Functions 759◇ Types & classes 112

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_double

()

semantic_sam/body/encoder/ops/test.py:35

↓ 1 callersFunctioncheck_forward_equal_with_pytorch_float

()

semantic_sam/body/encoder/ops/test.py:51

↓ 1 callersFunctioncheck_gradient_numerical

(channels=4, grad_value=True, grad_sampling_loc=True, grad_attn_weight=True)

semantic_sam/body/encoder/ops/test.py:66

↓ 1 callersFunctioncoco_encode_rle

(uncompressed_rle: Dict[str, Any])

utils/sam_utils/amg.py:294

↓ 1 callersMethodcompute_noc

(self)

datasets/evaluation/interactive_evaluation.py:103

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/dataset_mappers/o365_instance_new_baseline_dataset_mapper.py:25

↓ 1 callersFunctionconvert_coco_poly_to_mask

(segmentations, height, width)

datasets/dataset_mappers/coco_instance_new_baseline_dataset_mapper.py:21

↓ 1 callersMethoddraw_and_connect_keypoints

Draws keypoints of an instance and follows the rules for keypoint connections to draw lines between appropriate keypoints. This follo

utils/visualizer.py:799

↓ 1 callersMethoddraw_box

Args: box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0 are the coordinates of th

utils/visualizer.py:909

↓ 1 callersMethoddraw_circle

Args: circle_coord (list(int) or tuple(int)): contains the x and y coordinates of the center of the circle.

utils/visualizer.py:998

↓ 1 callersMethoddraw_panoptic_seg

Draw panoptic prediction annotations or results. Args: panoptic_seg (Tensor): of shape (height, width) where the values

utils/visualizer.py:483

↓ 1 callersMethoddraw_rotated_box_with_label

Draw a rotated box with label on its top-left corner. Args: rotated_box (tuple): a tuple containing (cnt_x, cnt_y, w, h,

utils/visualizer.py:943

↓ 1 callersMethoddraw_sem_seg

Draw semantic segmentation predictions/labels. Args: sem_seg (Tensor or ndarray): the segmentation of shape (H, W).

utils/visualizer.py:447

↓ 1 callersMethodencode_json_sem_seg

Convert semantic segmentation to COCO stuff format with segments encoded as RLEs. See http://cocodataset.org/#format-results

datasets/evaluation/segmentation_evaluation.py:175

↓ 1 callersMethodevaluate

Evaluates standard semantic segmentation metrics (http://cocodataset.org/#stuff-eval): * Mean intersection-over-union averaged acros

datasets/evaluation/segmentation_evaluation.py:115

↓ 1 callersMethodevaluate_interactive

evaluate interactive segmentation on other datasets (i.e, coco)

semantic_sam/architectures/interactive_mask_dino.py:557

↓ 1 callersMethodevaluate_interactive_granularity

evaluate multiple granualrity output on a subset of sam

semantic_sam/architectures/interactive_mask_dino.py:625

↓ 1 callersFunctionfilter_empty_instances_by_box

( instances, by_box=True, by_mask=False, box_threshold=1e-5, return_mask=False )

datasets/dataset_mappers/part_data_filter_whole_new_instance_dataset_mapper.py:30

↓ 1 callersFunctionfilter_empty_instances_by_box

( instances, by_box=True, by_mask=False, box_threshold=1e-5, return_mask=False )

datasets/dataset_mappers/pascal_instance_new_baseline_dataset_mapper.py:21

↓ 1 callersFunctionfilter_empty_instances_by_box

( instances, by_box=True, by_mask=False, box_threshold=1e-5, return_mask=False )

datasets/dataset_mappers/coco_interactive_panoptic_new_baseline_dataset_mapper.py:21

↓ 1 callersFunctionfilter_empty_instances_by_box

( instances, by_box=True, by_mask=False, box_threshold=1e-5, return_mask=False )

datasets/dataset_mappers/mask_former_instance_dataset_mapper.py:19

↓ 1 callersFunctionfilter_images_with_only_crowd_annotations

Filter out images with none annotations or only crowd annotations (i.e., images without non-crowd annotations). A common training-time pr

datasets/build.py:79

↓ 1 callersMethodforward

(self, x)

semantic_sam/backbone/focal_dw.py:36

↓ 1 callersMethodforward

(self, x)

semantic_sam/backbone/swin_new.py:35

↓ 1 callersMethodforward

(self, x)

semantic_sam/backbone/focal.py:36

↓ 1 callersMethodforward

(self, x)

semantic_sam/backbone/swin.py:40

↓ 1 callersMethodforward_features

(self, features)

semantic_sam/body/encoder/transformer_encoder_fpn.py:123

↓ 1 callersMethodforward_features

(self, features)

semantic_sam/body/encoder/transformer_encoder_fpn.py:276

↓ 1 callersMethodforward_ffn

(self, src)

semantic_sam/body/encoder/encoder_deform.py:127

↓ 1 callersMethodforward_ffn

(self, tgt)

semantic_sam/body/decoder/utils/dino_decoder.py:235

↓ 1 callersMethodforward_language_token

(self, texts, norm=False)

semantic_sam/language/vlpencoder.py:156

↓ 1 callersMethodforward_post

( self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional

semantic_sam/body/transformer_blocks.py:182

↓ 1 callersMethodforward_post

( self, tgt, memory, tgt_mask: Optional[Tensor] = None, memory_mask: O

semantic_sam/body/transformer_blocks.py:262

↓ 1 callersMethodforward_post

(self, tgt, tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask:

semantic_sam/body/decoder/modules.py:35

↓ 1 callersMethodforward_post

(self, tgt, memory, memory_mask: Optional[Tensor] = None, memory_key

semantic_sam/body/decoder/modules.py:93

↓ 1 callersMethodforward_post

(self, tgt)

semantic_sam/body/decoder/modules.py:157

↓ 1 callersMethodforward_pre

( self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional

semantic_sam/body/transformer_blocks.py:201

↓ 1 callersMethodforward_pre

( self, tgt, memory, tgt_mask: Optional[Tensor] = None, memory_mask: O

semantic_sam/body/transformer_blocks.py:293

↓ 1 callersMethodforward_pre

(self, tgt, tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask: O

semantic_sam/body/decoder/modules.py:47

↓ 1 callersMethodforward_pre

(self, tgt, memory, memory_mask: Optional[Tensor] = None, memory_key_p

semantic_sam/body/decoder/modules.py:106

↓ 1 callersMethodforward_pre

(self, tgt)

semantic_sam/body/decoder/modules.py:163

↓ 1 callersMethodforward_seg

Args: batched_inputs: a list, batched outputs of :class:`DatasetMapper`. Each item in the list contains the input

semantic_sam/architectures/interactive_mask_dino.py:377

↓ 1 callersMethodfrom_config

(cls, cfg, input_shape: Dict[str, ShapeSpec])

semantic_sam/body/encoder/transformer_encoder_fpn.py:112

↓ 1 callersFunctiongen_sineembed_for_position

(pos_tensor, dim=128)

semantic_sam/body/decoder/utils/utils.py:74

↓ 1 callersMethodgenerate

Generates masks for the given image. Arguments: image (np.ndarray): The image to generate masks for, in HWC uint8 format.

tasks/automatic_mask_generator.py:156

↓ 1 callersFunctiongenerate_crop_boxes

Generates a list of crop boxes of different sizes. Each layer has (2**i)**2 boxes for the ith layer.

utils/sam_utils/amg.py:200

↓ 1 callersFunctiongenerate_lineidx

(filein, idxout)

datasets/utils/tsv/io_common.py:49

↓ 1 callersFunctionget_extensions

()

semantic_sam/body/encoder/ops/setup.py:26

↓ 1 callersFunctionget_lvis_instances_meta_v1

()

datasets/registration/register_lvis_eval.py:32

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_scannet_panoptic.py:144

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_caption_grounding.py:52

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_caption.py:38

↓ 1 callersFunctionget_metadata

(name)

datasets/registration/register_vlp_datasets.py:33

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_refcoco_dataset.py:42

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_semseg_interactive.py:31

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_caption_grounding_interactive.py:52

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_semseg_interactive_jointboxpoint.py:31

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_bdd100k_panoseg.py:215

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_ade20k_panoptic.py:326

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_semseg.py:31

↓ 1 callersFunctionget_metadata

()

datasets/registration/register_coco_panoptic_annos_caption_interactive.py:38

↓ 1 callersFunctionget_o365_metadata

()

datasets/registration/register_object365_od.py:31

↓ 1 callersFunctionget_point_coords_wrt_image

Convert box-normalized [0, 1] x [0, 1] point cooordinates to image-level coordinates. Args: boxes_coords (Tensor): A tensor of shape

semantic_sam/modules/point_features.py:194

↓ 1 callersMethodget_reference_points

(spatial_shapes, valid_ratios, device)

semantic_sam/body/encoder/encoder_deform.py:152

↓ 1 callersMethodget_valid_ratio

(self, mask)

semantic_sam/body/encoder/encoder_deform.py:57

↓ 1 callersMethodget_valid_ratio

(self, mask)

semantic_sam/body/decoder/interactive_mask_dino.py:470

↓ 1 callersFunctionhook_switcher

(model, name)

utils/misc.py:23

↓ 1 callersMethodinstance_masks

(self)

utils/visualizer.py:220

↓ 1 callersMethodinteractive_forward_prediction_heads

(self, output, mask_features, pred_mask=True)

semantic_sam/body/decoder/interactive_mask_dino.py:611

↓ 1 callersFunctioniou_score_loss

(inputs, targets)

semantic_sam/modules/criterion_interactive_many_to_many.py:53

↓ 1 callersFunctioniou_score_loss

(inputs, targets)

semantic_sam/modules/criterion_interactive_many_to_one.py:72

↓ 1 callersFunctionis_box_near_crop_edge

Filter masks at the edge of a crop, but not at the edge of the original image.

utils/sam_utils/amg.py:78

↓ 1 callersFunctionis_lang_encoder

(model_name)

semantic_sam/language/LangEncoder/registry.py:17

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/backbone/registry.py:13

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/language/registry.py:12

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/architectures/registry.py:12

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/body/registry.py:13

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/body/encoder/registry.py:12

↓ 1 callersFunctionis_model

(model_name)

semantic_sam/body/decoder/registry.py:12

↓ 1 callersFunctionlang_encoders

(model_name)

semantic_sam/language/LangEncoder/registry.py:13

↓ 1 callersMethodlayers

(self, features, mask=None,targets=None, target_queries=None, target_vlp=None, prediction_switch=None, task='s

semantic_sam/body/general_head.py:98

↓ 1 callersFunctionload_ade20k_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_ade20k_panoptic.py:217

↓ 1 callersFunctionload_bdd_instances

Load BDD annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages" split (str): one

datasets/registration/register_bdd100k_semseg.py:21

↓ 1 callersFunctionload_bdd_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_bdd100k_panoseg.py:116

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_caption_grounding.py:96

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_caption.py:82

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_semseg_interactive.py:75

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_caption_grounding_interactive.py:96

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_semseg_interactive_jointboxpoint.py:75

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_semseg.py:75

↓ 1 callersFunctionload_coco_panoptic_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_coco_panoptic_annos_caption_interactive.py:82

↓ 1 callersFunctionload_imagenet_images

Load ImageNet annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages" split (str):

datasets/registration/register_imagenet_cls.py:22

↓ 1 callersFunctionload_lvis_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_lvis_eval.py:71

↓ 1 callersFunctionload_object365_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_object365_od.py:46

↓ 1 callersFunctionload_opt_from_config_files

Load opt from the config files, settings in later files can override those in previous files. Args: conf_files (list): a list of con

utils/arguments.py:47

↓ 1 callersFunctionload_pretrain_arrows

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". Returns: list[dict]: a list of dicts in Detectron2

datasets/registration/register_vlp_datasets.py:40

↓ 1 callersFunctionload_pretrain_data

(arrow_root, meta, name, pretrain_arrows)

datasets/registration/register_vlp_datasets.py:57

↓ 1 callersMethodload_pretrained

(self, pretrained='', pretrained_layers=[], verbose=True)

semantic_sam/language/LangEncoder/transformer.py:142

↓ 1 callersFunctionload_refcoco_json

Args: image_dir (str): path to the raw dataset. e.g., "~/coco/train2017". gt_dir (str): path to the raw annotations. e.g., "~/coc

datasets/registration/register_refcoco_dataset.py:47

↓ 1 callersFunctionload_sam_index

Load a json file with COCO's instances annotation format. Currently supports instance detection, instance segmentation, and person keypoi

datasets/registration/register_sam.py:62

← previous next →201–300 of 759, ranked by callers