MCPcopy Create free account

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

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

⨍ Functions 759◇ Types & classes 112
↓ 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_mnode.py:62
↓ 1 callersFunctionload_sam_instances
Load SAM detection annotations to Detectron2 format. Args: name: name of split dirname: dataset directory path id_ra
datasets/registration/register_sam_json.py:35
↓ 1 callersFunctionload_sam_instances
Load SAM detection annotations to Detectron2 format. Args: name: name of split dirname: dataset directory path id_ra
datasets/registration/register_sam_json_val.py:23
↓ 1 callersFunctionload_scannet_instances
Load ScanNet annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages" split (str):
datasets/registration/register_scannet_semseg.py:30
↓ 1 callersFunctionload_scannet_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_scannet_panoptic.py:43
↓ 1 callersFunctionload_semseg
(filename, loader_type)
datasets/utils/semseg_loader.py:5
↓ 1 callersFunctionload_sunrgbd_instances
Load SUN-RGBD detection annotations to Detectron2 format. Args: dirname: Contain "Annotations", "ImageSets", "JPEGImages" sp
datasets/registration/register_sunrgbd_semseg.py:22
↓ 1 callersMethodload_weights
(self, pretrained_dict=None, pretrained_layers=[], verbose=True)
semantic_sam/backbone/focal_dw.py:575
↓ 1 callersMethodload_weights
(self, pretrained_dict=None, pretrained_layers=[], verbose=True)
semantic_sam/backbone/focal.py:478
↓ 1 callersMethodload_weights
(self, pretrained_dict=None, pretrained_layers=[], verbose=True)
semantic_sam/backbone/swin.py:663
↓ 1 callersMethodmask_postprocessing
(self, masks: torch.Tensor, orig_im_size: torch.Tensor)
utils/sam_utils/onnx.py:76
↓ 1 callersMethodmemory_efficient_forward
More memory-friendly matching. Change cost to compute only certain loss in matching
semantic_sam/modules/many2many_matcher.py:107
↓ 1 callersMethodmemory_efficient_forward
More memory-friendly matching. Change cost to compute only certain loss in matching
semantic_sam/modules/matcher.py:108
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/backbone/registry.py:10
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/language/registry.py:9
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/architectures/registry.py:9
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/body/registry.py:10
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/body/encoder/registry.py:9
↓ 1 callersFunctionmodel_entrypoints
(model_name)
semantic_sam/body/decoder/registry.py:9
↓ 1 callersMethodnon_empty_mask
Returns: (H, W) array, a mask for all pixels that have a prediction
utils/visualizer.py:196
↓ 1 callersMethodoutput_shape
(self)
semantic_sam/backbone/focal.py:669
↓ 1 callersMethodoverlay_rotated_instances
Args: boxes (ndarray): an Nx5 numpy array of (x_center, y_center, width, height, angle_degrees) format
utils/visualizer.py:761
↓ 1 callersFunctionparse_option
()
demo_auto_generation.py:22
↓ 1 callersFunctionparse_option
()
demo.py:22
↓ 1 callersMethodpolygons_to_mask
(self, polygons)
utils/visualizer.py:138
↓ 1 callersMethodpostprocess_small_regions
Removes small disconnected regions and holes in masks, then reruns box NMS to remove any new duplicates. Edits mask_data in
tasks/automatic_mask_generator.py:342
↓ 1 callersMethodpred_box
:param reference: reference box coordinates from each decoder layer :param hs: content :param ref0: whether there are predict
semantic_sam/body/decoder/interactive_mask_dino.py:479
↓ 1 callersMethodpredict
produce up to 6 prediction results for each click
tasks/interactive_predictor.py:26
↓ 1 callersMethodpredict_masks
(self, image_ori, image, point=None)
tasks/interactive_predictor.py:110
↓ 1 callersMethodprep_for_dn
(self,mask_dict)
semantic_sam/modules/criterion_interactive_many_to_many.py:386
↓ 1 callersMethodprepare_for_dn_mo
Train SA-1B data with point input. This training can be regarded as a multi-granularity denoising process modified from dn-de
semantic_sam/body/decoder/interactive_mask_dino.py:338
↓ 1 callersMethodprepare_for_dn_mo_infer
(self, targets, tgt, refpoint_emb, batch_size)
semantic_sam/body/decoder/interactive_mask_dino.py:421
↓ 1 callersFunctionpreprocess_name
(name)
datasets/registration/register_lvis_eval.py:43
↓ 1 callersMethodprocess
Args: inputs: the inputs to a model. It is a list of dicts. Each dict corresponds to an image and
datasets/evaluation/segmentation_evaluation.py:83
↓ 1 callersMethodprocess_multi_mask
(self, masks, ious, image_ori)
tasks/interactive_predictor.py:57
↓ 1 callersFunctionprompt_switch
(p)
tasks/automatic_mask_generator.py:35
↓ 1 callersFunctionregister_ade20k_panoptic
Register a "standard" version of ADE20k panoptic segmentation dataset named `name`. The dictionaries in this registered dataset follows detec
datasets/registration/register_ade20k_panoptic.py:271
↓ 1 callersFunctionregister_all_ade20k_full
(root)
datasets/registration/register_ade20k_full.py:962
↓ 1 callersFunctionregister_all_ade20k_instance
(root)
datasets/registration/register_ade20k_instance.py:41
↓ 1 callersFunctionregister_all_ade20k_panoptic
(root)
datasets/registration/register_ade20k_panoptic.py:370
↓ 1 callersFunctionregister_all_coco_panoptic_annos_caption_grounding_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_caption_grounding.py:205
↓ 1 callersFunctionregister_all_coco_panoptic_annos_caption_grounding_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_caption_grounding_interactive.py:205
↓ 1 callersFunctionregister_all_coco_panoptic_annos_caption_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_caption.py:179
↓ 1 callersFunctionregister_all_coco_panoptic_annos_caption_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_caption_interactive.py:179
↓ 1 callersFunctionregister_all_coco_panoptic_annos_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_semseg_interactive.py:160
↓ 1 callersFunctionregister_all_coco_panoptic_annos_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_semseg_interactive_jointboxpoint.py:160
↓ 1 callersFunctionregister_all_coco_panoptic_annos_sem_seg
(root)
datasets/registration/register_coco_panoptic_annos_semseg.py:160
↓ 1 callersFunctionregister_all_coco_stuff_10k
(root)
datasets/registration/register_coco_stuff_10k.py:200
↓ 1 callersFunctionregister_all_imagenet
(root)
datasets/registration/register_imagenet_cls.py:54
↓ 1 callersFunctionregister_all_lvis
(root)
datasets/registration/register_lvis_eval.py:128
↓ 1 callersFunctionregister_all_object365_od
(root_json, root_image)
datasets/registration/register_object365_od.py:121
↓ 1 callersFunctionregister_all_pretrain
(root)
datasets/registration/register_vlp_datasets.py:116
↓ 1 callersFunctionregister_all_refcoco
(root)
datasets/registration/register_refcoco_dataset.py:100
↓ 1 callersFunctionregister_all_sam
(root)
datasets/registration/register_sam_json.py:57
↓ 1 callersFunctionregister_all_sam
(root)
datasets/registration/register_sam_json_val.py:46
↓ 1 callersFunctionregister_all_sam_instance
(root)
datasets/registration/register_sam.py:149
↓ 1 callersFunctionregister_all_sam_instance
(root)
datasets/registration/register_sam_mnode.py:110
↓ 1 callersFunctionregister_all_scannet_panoptic
(root)
datasets/registration/register_scannet_panoptic.py:188
↓ 1 callersFunctionregister_all_scannet_panoptic
(root)
datasets/registration/register_bdd100k_panoseg.py:260
↓ 1 callersFunctionregister_all_sunrgbd_seg
(root)
datasets/registration/register_bdd100k_semseg.py:62
↓ 1 callersFunctionregister_all_sunrgbd_seg
(root)
datasets/registration/register_scannet_semseg.py:68
↓ 1 callersFunctionregister_all_sunrgbd_seg
(root)
datasets/registration/register_sunrgbd_semseg.py:64
↓ 1 callersFunctionregister_bdd_context
(name, dirname, split, class_names=BDD_SEM)
datasets/registration/register_bdd100k_semseg.py:49
↓ 1 callersFunctionregister_bdd_panoptic
Register a "standard" version of ADE20k panoptic segmentation dataset named `name`. The dictionaries in this registered dataset follows detec
datasets/registration/register_bdd100k_panoseg.py:170
↓ 1 callersFunctionregister_coco_panoptic_annos_caption_grounding_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, caption_root, grounding_root, si
datasets/registration/register_coco_panoptic_annos_caption_grounding.py:172
↓ 1 callersFunctionregister_coco_panoptic_annos_caption_grounding_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, caption_root, grounding_root, si
datasets/registration/register_coco_panoptic_annos_caption_grounding_interactive.py:172
↓ 1 callersFunctionregister_coco_panoptic_annos_caption_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, caption_root, similarity_pth, in
datasets/registration/register_coco_panoptic_annos_caption.py:146
↓ 1 callersFunctionregister_coco_panoptic_annos_caption_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, caption_root, similarity_pth, in
datasets/registration/register_coco_panoptic_annos_caption_interactive.py:146
↓ 1 callersFunctionregister_coco_panoptic_annos_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, instances_json )
datasets/registration/register_coco_panoptic_annos_semseg_interactive.py:129
↓ 1 callersFunctionregister_coco_panoptic_annos_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, instances_json )
datasets/registration/register_coco_panoptic_annos_semseg_interactive_jointboxpoint.py:129
↓ 1 callersFunctionregister_coco_panoptic_annos_sem_seg
( name, metadata, image_root, panoptic_root, panoptic_json, sem_seg_root, instances_json )
datasets/registration/register_coco_panoptic_annos_semseg.py:129
↓ 1 callersFunctionregister_imagenet
(name, dirname, split, year, class_names=IMAGENET_CLASSES)
datasets/registration/register_imagenet_cls.py:47
↓ 1 callersFunctionregister_lvis_instances
Register a dataset in LVIS's json annotation format for instance detection and segmentation. Args: name (str): a name that identifie
datasets/registration/register_lvis_eval.py:55
↓ 1 callersFunctionregister_object365_od
( name, metadata, image_root, od_json )
datasets/registration/register_object365_od.py:106
↓ 1 callersFunctionregister_paco_part
(root)
datasets/registration/register_paco_part_all.py:79
↓ 1 callersFunctionregister_paco_part_instances
(name, metadata, json_file, image_root)
datasets/registration/register_paco_part_all.py:58
↓ 1 callersFunctionregister_partimagenet_part
(root)
datasets/registration/register_partimagenet_part_all.py:92
↓ 1 callersFunctionregister_partimagenet_part_instances
(name, metadata, json_file, image_root)
datasets/registration/register_partimagenet_part_all.py:76
↓ 1 callersFunctionregister_pascal_part
(root)
datasets/registration/register_pascal_part_all.py:252
↓ 1 callersFunctionregister_pascal_part
(root)
datasets/registration/register_pascal_part_all_interactive.py:252
↓ 1 callersFunctionregister_pascal_part_instances
(name, metadata, json_file, image_root)
datasets/registration/register_pascal_part_all.py:232
↓ 1 callersFunctionregister_pascal_part_instances
(name, metadata, json_file, image_root)
datasets/registration/register_pascal_part_all_interactive.py:232
↓ 1 callersFunctionregister_pretrain
( name, metadata, arrow_root, arrow_paths )
datasets/registration/register_vlp_datasets.py:94
↓ 1 callersFunctionregister_refcoco
( name, metadata, image_root, annot_json)
datasets/registration/register_refcoco_dataset.py:84
↓ 1 callersFunctionregister_sam
(name, dirname, id_range)
datasets/registration/register_sam_json.py:50
↓ 1 callersFunctionregister_sam
(name, dirname, id_range)
datasets/registration/register_sam_json_val.py:38
↓ 1 callersFunctionregister_sam_instances
(name, metadata, tsv_file)
datasets/registration/register_sam.py:135
↓ 1 callersFunctionregister_sam_instances
(name, metadata, tsv_file)
datasets/registration/register_sam_mnode.py:96
↓ 1 callersFunctionregister_scannet_context
(name, dirname, split, class_names=name2class)
datasets/registration/register_scannet_semseg.py:55
↓ 1 callersFunctionregister_scannet_panoptic
Register a "standard" version of ADE20k panoptic segmentation dataset named `name`. The dictionaries in this registered dataset follows detec
datasets/registration/register_scannet_panoptic.py:98
↓ 1 callersFunctionregister_sun_context
(name, dirname, split, class_names=SUN_RGBD_37)
datasets/registration/register_sunrgbd_semseg.py:51
↓ 1 callersMethodresize_longest_image_size
( input_image_size: torch.Tensor, longest_side: int )
utils/sam_utils/onnx.py:42
↓ 1 callersMethodselect_masks
( self, masks: torch.Tensor, iou_preds: torch.Tensor, num_points: int )
utils/sam_utils/onnx.py:92
↓ 1 callersMethodsemantic_masks
(self)
utils/visualizer.py:212
↓ 1 callersMethodto_numpy
(self)
utils/sam_utils/amg.py:72
↓ 1 callersFunctionuncrop_masks
( masks: torch.Tensor, crop_box: List[int], orig_h: int, orig_w: int )
utils/sam_utils/amg.py:255
↓ 1 callersFunctionvalid
(anns)
datasets/build.py:93
↓ 1 callersFunctionwindow_reverse
Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image
semantic_sam/backbone/swin_new.py:58
↓ 1 callersFunctionwindow_reverse
Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image
semantic_sam/backbone/swin.py:63
↓ 1 callersMethodwith_pos_embed
(tensor, pos)
semantic_sam/body/encoder/encoder_deform.py:124
← previousnext →301–400 of 759, ranked by callers