MCPcopy Create free account

hub / github.com/ayushjain1144/odin / functions

Functions721 in github.com/ayushjain1144/odin

⨍ Functions 721◇ Types & classes 105
↓ 1 callersMethodexport_intrinsics
(self, output_path)
data_preparation/scannet/SensorData.py:130
↓ 1 callersMethodexport_poses
(self, output_path, frame_skip=1)
data_preparation/scannet/SensorData.py:122
↓ 1 callersMethodexport_pred_benchmark
(self, processed_results, scene_name, dataset_name, benchmark=False, pcs=None)
odin/odin_model.py:657
↓ 1 callersMethodextract_instance_from_file
(self, sample_from_database)
data_preparation/base_preprocessing.py:120
↓ 1 callersFunctionfarthest_point_sampling_cuda
libs/pointops/src/sampling/sampling_cuda.cpp:7
↓ 1 callersFunctionfill_cluster_idxs_
libs/pointgroup_ops/src/bfs_cluster.cpp:102
↓ 1 callersMethodfind_build
(self, local_build, commit_id, branch, platform)
data_preparation/ai2thor/controller_custom.py:1195
↓ 1 callersFunctionfind_cc
================================== bfs_cluster ================================== */
libs/pointgroup_ops/src/bfs_cluster.cpp:53
↓ 1 callersMethodfind_platform_builds
( self, candidate_platforms, request, commits, releases_dir, local_build )
data_preparation/ai2thor/controller_custom.py:1278
↓ 1 callersFunctionfix_depth
(depth)
data_preparation/matterport3d/process_matterport.py:55
↓ 1 callersFunctionfix_intrinsics
(intrinsics)
data_preparation/matterport3d/process_matterport.py:60
↓ 1 callersMethodforward
(self, x)
odin/modeling/backbone/swin.py:41
↓ 1 callersMethodforward
(self, x)
odin/modeling/meta_arch/self_cross_attention_layers.py:208
↓ 1 callersMethodforward_features
Args: - features: dict, keys are ['res2', 'res3', 'res4', 'res5'] if self.cfg.MODEL.UPSAMPLE_
odin/modeling/pixel_decoder/msdeformattn.py:401
↓ 1 callersMethodforward_ffn
(self, src)
odin/modeling/pixel_decoder/msdeformattn.py:159
↓ 1 callersMethodforward_post
(self, tgt, tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask:
odin/modeling/meta_arch/self_cross_attention_layers.py:38
↓ 1 callersMethodforward_post
(self, tgt, memory, memory_mask: Optional[Tensor] = None, memory_key
odin/modeling/meta_arch/self_cross_attention_layers.py:101
↓ 1 callersMethodforward_post
(self, tgt)
odin/modeling/meta_arch/self_cross_attention_layers.py:167
↓ 1 callersMethodforward_pre
(self, tgt, tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask: O
odin/modeling/meta_arch/self_cross_attention_layers.py:50
↓ 1 callersMethodforward_pre
(self, tgt, memory, memory_mask: Optional[Tensor] = None, memory_key_p
odin/modeling/meta_arch/self_cross_attention_layers.py:115
↓ 1 callersMethodforward_pre
(self, tgt)
odin/modeling/meta_arch/self_cross_attention_layers.py:173
↓ 1 callersFunctiongenerate_sentence_from_labels
(positive_label_list, negative_label_list, disable_shuffle=True)
odin/data_video/sentence_utils.py:104
↓ 1 callersFunctiongenerate_xorg_conf
(devices)
data_preparation/ai2thor/startx.py:26
↓ 1 callersFunctionget_bbox_from_mask
(mask, pcs)
odin/utils/util_3d.py:397
↓ 1 callersFunctionget_clusters
input: semantic_label, int, N input: ball_query_idxs, Int, (nActive) input: start_len, int, (N, 2) output: clusters, CCs
libs/pointgroup_ops/src/bfs_cluster.cpp:85
↓ 1 callersMethodget_color_features
(self, multiview_data, images, features, shape)
odin/odin_model.py:559
↓ 1 callersFunctionget_context_records
(idx, img, scenes)
odin/data_video/datasets/scannet_context.py:117
↓ 1 callersMethodget_current_image_id
(self, dataset_dict, context)
odin/data_video/dataset_mapper_scannet.py:287
↓ 1 callersFunctionget_extensions
()
odin/modeling/pixel_decoder/ops/setup.py:26
↓ 1 callersFunctionget_index
Parse a color as a base-256 number and returns the index Args: color: A 3-tuple in RGB-order where each element \in [0, 255] Returns:
data_preparation/s3dis/convert_dataset.py:15
↓ 1 callersFunctionget_index
Parse a color as a base-256 number and returns the index Args: color: A 3-tuple in RGB-order where each element \in [0, 255] Returns:
data_preparation/s3dis/convert_dataset_raw.py:15
↓ 1 callersMethodget_instance_verts
(self, mesh_vert_instances, instance_id)
odin/data_video/segmentation_benchmark/util_3d.py:100
↓ 1 callersMethodget_instances
(self, vertices, scores)
libs/pointgroup_ops/functions/functions.py:111
↓ 1 callersMethodget_label_id
(self, instance_id)
odin/data_video/segmentation_benchmark/util_3d.py:97
↓ 1 callersMethodget_multiview_xyz
(self, dataset_dict)
odin/data_video/dataset_mapper_scannet.py:250
↓ 1 callersFunctionget_origin_T_camX
(event)
data_preparation/ai2thor/ai2thor_utils.py:34
↓ 1 callersMethodget_pos
(self, x)
odin/modeling/pixel_decoder/msdeformattn.py:376
↓ 1 callersMethodget_reference_points
(spatial_shapes, valid_ratios, device)
odin/modeling/pixel_decoder/msdeformattn.py:184
↓ 1 callersFunctionget_rotation_transform
()
odin/modeling/backproject/backproject.py:15
↓ 1 callersFunctionget_scan_ids
Load the .csv files and return a set of scan_ids.
data_preparation/scannet/download_scannet_files.py:14
↓ 1 callersFunctionget_scannet_intrinsic
(image_size, intrinsic_file=None)
odin/modeling/backproject/backproject.py:369
↓ 1 callersMethodget_valid_ratio
(self, mask)
odin/modeling/pixel_decoder/msdeformattn.py:87
↓ 1 callersFunctiongrouping_backward_cuda
libs/pointops/src/grouping/grouping_cuda.cpp:15
↓ 1 callersFunctiongrouping_forward_cuda
libs/pointops/src/grouping/grouping_cuda.cpp:7
↓ 1 callersMethodinference_2d_per_image
pred_cls: 100 X 19 pred_masks: 100 X 5 X 480 X 640
odin/odin_model.py:1248
↓ 1 callersMethodinference_scannet_ghost
pred_cls: 100 X 19 pred_masks: 100 X 5 X 480 X 640
odin/odin_model.py:1386
↓ 1 callersMethodinference_video
pred_cls: 100 X 19 pred_masks: 100 X 5 X 480 X 640
odin/odin_model.py:1301
↓ 1 callersMethodinference_video_semantic
pred_cls: 100 X 19 pred_masks: 100 X 5 X 480 X 640
odin/odin_model.py:1352
↓ 1 callersMethodinit_pe
(self)
odin/modeling/transformer_decoder/odin_transformer_decoder.py:227
↓ 1 callersMethodinit_pe
(self, latent_dim)
odin/modeling/meta_arch/cross_view_attention.py:53
↓ 1 callersMethodinit_pe
(self)
odin/modeling/pixel_decoder/msdeformattn.py:371
↓ 1 callersMethodinitialize_scene
(self)
data_preparation/ai2thor/controller_custom.py:1875
↓ 1 callersFunctioninpaint_depth
inpaints depth using opencv Input: torch tensor with depthvalues: H, W Output: torch tensor with depthvalues: H, W
odin/utils/inpaint_depth.py:15
↓ 1 callersFunctioninterpolate_depth
(xyz, multi_scale_features, method="nearest")
odin/modeling/backproject/backproject.py:141
↓ 1 callersFunctioninterpolation_backward_cuda
libs/pointops/src/interpolation/interpolation_cuda.cpp:16
↓ 1 callersFunctioninterpolation_forward_cuda
libs/pointops/src/interpolation/interpolation_cuda.cpp:7
↓ 1 callersFunctionintersection_and_union_gpu
(output, target, k, ignore_index=-1)
odin/data_video/scannet_3d_eval_semantic.py:25
↓ 1 callersMethodis_object_visible
(self, object_id)
data_preparation/ai2thor/controller_custom.py:1727
↓ 1 callersFunctionknn_query_cuda
libs/pointops/src/knn_query/knn_query_cuda.cpp:7
↓ 1 callersMethodload
(self, filename)
data_preparation/scannet/SensorData.py:52
↓ 1 callersMethodloadCats
Load cats with the specified ids. :param ids (int array) : integer ids specifying cats :return: cats (object array) : l
odin/data_video/coco.py:214
↓ 1 callersMethodloadImgs
Load anns with the specified ids. :param ids (int array) : integer ids specifying img :return: imgs (object array) : lo
odin/data_video/coco.py:225
↓ 1 callersMethodloadNumpyAnnotations
Convert result data from a numpy array [Nx7] where each row contains {imageID,x1,y1,w,h,score,class} :param data (numpy.ndarray)
odin/data_video/coco.py:401
↓ 1 callersMethodloadRes
Load result file and return a result api object. :param resFile (str) : file name of result file :return: res (obj)
odin/data_video/coco.py:306
↓ 1 callersMethodload_3d_data
(self, batched_inputs, images_shape, decoder_3d)
odin/odin_model.py:237
↓ 1 callersFunctionload_image
(path)
data_preparation/matterport3d/process_matterport.py:65
↓ 1 callersFunctionload_labels
Convenience function for loading JSON labels
data_preparation/s3dis/convert_dataset.py:25
↓ 1 callersFunctionload_labels
Convenience function for loading JSON labels
data_preparation/s3dis/convert_dataset_raw.py:25
↓ 1 callersFunctionload_matrix_from_txt
(path, shape=(4, 4))
data_preparation/matterport3d/process_matterport.py:18
↓ 1 callersFunctionload_ply
(filepath)
data_preparation/matterport3d/process_matterport_3d.py:60
↓ 1 callersFunctionload_raw_data
( poses_path, depths_path, rgbs_path, intrinsics_path, cam_uiud, output_scene_name )
data_preparation/matterport3d/process_matterport.py:70
↓ 1 callersMethodload_scannet_data
(self, batched_inputs, multiview_data, scannet_pc_list=None, do_knn=False, images=None, shape=None)
odin/odin_model.py:285
↓ 1 callersFunctionload_scannet_json_single
(json_file, image_root, dataset_name=None)
odin/data_video/datasets/scannet_context.py:154
↓ 1 callersMethodlocal_commits
(self)
data_preparation/ai2thor/controller_custom.py:1179
↓ 1 callersFunctionmain
()
data_preparation/scannet/reader.py:23
↓ 1 callersFunctionmain
Download all necessary files for all scan_ids.
data_preparation/scannet/download_scannet_files.py:36
↓ 1 callersFunctionmake_mapping
()
data_preparation/matterport3d/process_matterport_3d.py:26
↓ 1 callersMethodmake_pred_info
(self, pred: dict)
odin/data_video/segmentation_benchmark/evaluate_semantic_instance.py:298
↓ 1 callersMethodmemory_efficient_forward
More memory-friendly matching
odin/modeling/matcher.py:164
↓ 1 callersMethodmemory_efficient_forward_3d
More memory-friendly matching
odin/modeling/matcher.py:103
↓ 1 callersFunctionmerge_datasets
(datasets, mappers, balance=False)
odin/data_video/build.py:261
↓ 1 callersMethodmove_relative_points
(self, all_points, graph, position, rotation)
data_preparation/ai2thor/controller_custom.py:1503
↓ 1 callersFunctionmultiscsale_voxelize
Inputs: multi_scale_xyz: list of tensors [B, V, H, W, 3] voxel_size: list of floats of len multi_scale_xyz Outputs:
odin/modeling/backproject/backproject.py:208
↓ 1 callersMethodnormalize_scene
(scene)
data_preparation/ai2thor/controller_custom.py:650
↓ 1 callersMethodoutput_shape
(self)
odin/modeling/backbone/resnet.py:534
↓ 1 callersMethodparse_ghost
(self, input)
odin/data_video/scannet_3d_eval.py:66
↓ 1 callersMethodparse_normal
(self, input)
odin/data_video/scannet_3d_eval.py:81
↓ 1 callersMethodparse_preds
Args: outputs['instances']: all k-frames instances in detectron2 format Returns: [{ "pred_classes": predi
odin/data_video/scannet_3d_eval.py:159
↓ 1 callersMethodparse_preds
(self, output)
odin/data_video/scannet_3d_eval_semantic.py:86
↓ 1 callersFunctionpci_records
()
data_preparation/ai2thor/startx.py:12
↓ 1 callersMethodplan_horizons
(self, agent_horizon, target_horizon)
data_preparation/ai2thor/controller_custom.py:1528
↓ 1 callersMethodplan_rotations
(self, agent_rotation, target_rotation)
data_preparation/ai2thor/controller_custom.py:1543
↓ 1 callersFunctionpolygons_to_bitmask
Args: polygons (list[ndarray]): each array has shape (Nx2,) height, width (int) Returns: ndarray: a bool mask of sha
data_preparation/s3dis/s3dis2coco.py:42
↓ 1 callersMethodprepare_2d
( self, pred_masks, img_size, labels_per_image, scores_per_image, batched_inputs=None
odin/odin_model.py:1179
↓ 1 callersMethodprepare_3d
( self, pred_masks, output_height, output_width, labels_per_image, scores_per_image, v
odin/odin_model.py:1212
↓ 1 callersMethodprepare_inputs
(self, srcs, pos_embeds)
odin/modeling/pixel_decoder/msdeformattn.py:97
↓ 1 callersMethodprepare_targets
( self, targets, images, valids=None )
odin/odin_model.py:1144
↓ 1 callersFunctionprint_instances_class_histogram
Args: dataset_dicts (list[dict]): list of dataset dicts. class_names (list[str]): list of class names (zero-indexed).
odin/data_video/build.py:56
↓ 1 callersMethodprint_results
(self, avgs, logger)
odin/data_video/segmentation_benchmark/evaluate_semantic_instance.py:371
↓ 1 callersFunctionprocess_color
(frame_id, file, folder_processed)
data_preparation/s3dis/convert_dataset_raw.py:104
← previousnext →201–300 of 721, ranked by callers