MCPcopy Create free account

hub / github.com/EGO4D/episodic-memory / functions

Functions1,142 in github.com/EGO4D/episodic-memory

⨍ Functions 1,142◇ Types & classes 180
↓ 1 callersMethodforward_post
( self, tgt, memory, tgt_mask: Optional[Tensor] = None, memory_mask: O
EgoTracks/tracking/models/stark_tracker/transformer.py:474
↓ 1 callersMethodforward_pre
( self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional
EgoTracks/tracking/models/stark_tracker/transformer.py:332
↓ 1 callersMethodforward_pre
( self, tgt, memory, tgt_mask: Optional[Tensor] = None, memory_mask: O
EgoTracks/tracking/models/stark_tracker/transformer.py:520
↓ 1 callersMethodforward_transformer
(self, seq_dict, run_box_head=False, run_cls_head=False)
EgoTracks/tracking/models/stark_tracker/stark_st.py:57
↓ 1 callersFunctionframe2tensor
(frame, device)
VQ3D/camera_pose_estimation/SuperGlueMatching/models/utils.py:259
↓ 1 callersMethodframe_info
(self, frame_num)
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:128
↓ 1 callersFunctionframes_to_select
( start_frame: int, end_frame: int, original_fps: int, new_fps: int, )
VQ2D/convert_videos_to_clips.py:37
↓ 1 callersFunctionframes_to_select
( start_frame: int, end_frame: int, original_fps: int, new_fps: int, )
VQ2D/convert_videos_to_images.py:42
↓ 1 callersMethodgen_anchors
(self)
MQ/Models/AnchorGenerator.py:24
↓ 1 callersFunctiongen_or_load_dataset
(configs)
NLQ/VSLNet/utils/data_gen.py:290
↓ 1 callersFunctiongeneralized_box_iou
Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format boxes1: (N, 4) boxes2: (N, 4)
EgoTracks/tracking/models/stark_tracker/utils/box_ops.py:60
↓ 1 callersMethodget_base_anchors
(self, stride, scales)
MQ/Models/AnchorGenerator.py:33
↓ 1 callersFunctionget_blocked_videos
(api=API)
MQ/Evaluation/utils.py:8
↓ 1 callersMethodget_center_box
(self, H, W, ratio=1 / 8)
EgoTracks/tracking/dataset/trackingdataset.py:351
↓ 1 callersFunctionget_cfg
(model_type)
EgoTracks/tracking/config/config.py:7
↓ 1 callersMethodget_class_list
(self)
EgoTracks/tracking/dataset/train_datasets/coco_seq.py:102
↓ 1 callersFunctionget_dataset_uid
(split, idx)
VQ2D/process_vq_dataset.py:10
↓ 1 callersFunctionget_evaluator
Create evaluators.
VQ2D/train_siam_rcnn.py:39
↓ 1 callersFunctionget_image_id_from_data
Defines a unique image id for a given VQ data point.
VQ2D/vq2d/baselines/utils.py:119
↓ 1 callersFunctionget_images_at_peak
(all_bboxes, all_scores, all_imgs, peak_idx, topk=5)
VQ2D/perform_vq_inference.py:33
↓ 1 callersFunctionget_last_checkpoint
(model_dir, suffix="t7")
NLQ/VSLNet/utils/runner_utils.py:41
↓ 1 callersFunctionget_loss_supplement
(pred_action, gt_action, pred_start, gt_start, pred_end, gt_end)
MQ/Models/Loss.py:186
↓ 1 callersMethodget_lt_track
( self, video_uid: str, clip_uid: str, frame_number_key: str = "exported_clip_
EgoTracks/tracking/dataset/eval_datasets/ego4d_lt_tracking_dataset.py:58
↓ 1 callersMethodget_meta_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/coco_seq.py:154
↓ 1 callersFunctionget_mp4_writer
(path, fps, output_params=["-crf", "22"])
VQ2D/convert_videos_to_clips.py:23
↓ 1 callersFunctionget_mp4_writer
(path, fps, output_params=["-crf", "31"])
VQ2D/visualizations/visualize_annotations.py:95
↓ 1 callersMethodget_num_images
Number of sequences in a dataset returns: int - number of sequences in the dataset.
EgoTracks/tracking/dataset/base_image_dataset.py:41
↓ 1 callersMethodget_num_sequences
Number of sequences in a dataset returns: int - number of sequences in the dataset.
EgoTracks/tracking/dataset/base_video_dataset.py:57
↓ 1 callersMethodget_num_sequences
(self)
EgoTracks/tracking/dataset/train_datasets/lasot.py:104
↓ 1 callersFunctionget_padded_mask_and_weight
(*args)
NLQ/2D-TAN/lib/models/map_modules/__init__.py:3
↓ 1 callersFunctionget_proposal_results
(scores, durations)
NLQ/2D-TAN/moment_localization/train.py:168
↓ 1 callersFunctionget_proposal_results
(scores, durations)
NLQ/2D-TAN/moment_localization/test.py:227
↓ 1 callersFunctionget_rank
()
EgoTracks/tracking/models/stark_tracker/utils/misc.py:27
↓ 1 callersMethodget_score_map
(self, x)
EgoTracks/tracking/models/stark_tracker/head.py:109
↓ 1 callersMethodget_score_map
(self, x)
EgoTracks/tracking/models/stark_tracker/head.py:200
↓ 1 callersMethodget_sequence_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/tracking_net.py:151
↓ 1 callersMethodget_sequence_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/ego4d_lt_tracking.py:38
↓ 1 callersMethodget_sequence_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/got10k.py:203
↓ 1 callersMethodget_sequence_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/coco_seq.py:128
↓ 1 callersMethodget_sequence_info
(self, seq_id)
EgoTracks/tracking/dataset/train_datasets/ego4d_vq.py:38
↓ 1 callersMethodget_sequences
(self)
EgoTracks/tracking/dataset/eval_datasets/ego4d_lt_tracking_dataset.py:29
↓ 1 callersFunctionget_text_box
(text, shape, fg_color=(255, 255, 255), bg_color=(0, 0, 0))
VQ2D/visualizations/visualize_annotations.py:115
↓ 1 callersFunctionget_tracks_parallel
(inputs)
VQ3D/camera_pose_estimation/superglue_tracker.py:204
↓ 1 callersFunctionget_train_loader
(dataset, video_features, configs)
NLQ/VSLNet/utils/data_loader.py:114
↓ 1 callersMethodget_transformation_matrix
(self)
VQ3D/annotation_API/API/bounding_box.py:42
↓ 1 callersFunctionget_value
(x)
EgoTracks/tracking/utils/load_helper.py:31
↓ 1 callersMethodget_video_features
(self, vid, duration, window_se=None, clip_se=None)
NLQ/2D-TAN/lib/datasets/ego4d_clip.py:231
↓ 1 callersMethodget_video_features
(self, vid)
NLQ/2D-TAN/lib/datasets/tacos.py:84
↓ 1 callersMethodget_video_features
(self, vid)
NLQ/2D-TAN/lib/datasets/charades.py:91
↓ 1 callersMethodget_video_features
(self, vid)
NLQ/2D-TAN/lib/datasets/activitynet.py:118
↓ 1 callersFunctionget_visual_crop_image
(reference, visual_crop, cfg)
VQ2D/vq2d/tools/get_average_detector_flops.py:67
↓ 1 callersMethodgetitem
returns: TensorDict - dict containing all the data blocks
EgoTracks/tracking/dataset/trackingdataset.py:117
↓ 1 callersMethodgetitem_cls
args: index (int): Index (Ignored since we sample randomly) aux (bool): whether the current data is for auxiliary use
EgoTracks/tracking/dataset/trackingdataset.py:226
↓ 1 callersMethodhas_score
(self)
VQ2D/vq2d/structures.py:61
↓ 1 callersFunctionimread_indexed
Load indexed image with given filename. Used to read segmentation annotations.
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:208
↓ 1 callersFunctionindex_to_time
(start_index, end_index, num_units, duration)
NLQ/VSLNet/utils/data_util.py:126
↓ 1 callersFunctioninfer_batch_selectprop
(model, index_list, input_data,
MQ/Infer.py:48
↓ 1 callersMethodinference
Args: predictions: return values of :meth:`forward()` proposals (list[Instances]): proposals that match the features
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:566
↓ 1 callersMethodinference
Args: predictions: return values of :meth:`forward()` proposals (list[Instances]): proposals that match the features
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:294
↓ 1 callersMethodinference
Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_ins
VQ2D/detectron2_extensions/modeling/meta_arch/siam_rcnn.py:101
↓ 1 callersMethodinference_img_sequence
Run tracking model on a video sequence. Args: video: torch Tensor that contains a sequence of images, [N, 3, H, W]
EgoTracks/tracking/models/tracker.py:125
↓ 1 callersMethodinference_sequence
Run tracking model on a video sequence. Since some dataset stores video as individual frames and each sequence can be quite large, it
EgoTracks/tracking/models/tracker.py:89
↓ 1 callersMethodinference_video_handler
Run tracking model on a video sequence. Args: video: a video handler of type av.container.Container to the video file (t
EgoTracks/tracking/models/tracker.py:165
↓ 1 callersMethodinitialize_runner
(self)
VQ2D/vq2d/tracking/tracker.py:23
↓ 1 callersFunctioniou
(pred, gt)
MQ/Evaluation/ego4d/get_retrieval_performance.py:126
↓ 1 callersMethodis_blurry
(self, image: np.ndarray)
VQ3D/camera_pose_estimation/Camera_Intrinsics_API/get_camera_intrinsics.py:17
↓ 1 callersFunctionis_main_process
()
EgoTracks/tracking/models/stark_tracker/utils/misc.py:33
↓ 1 callersFunctionknn
(x, num_frms, opt, y=None, k=10)
MQ/Models/GCNs.py:7
↓ 1 callersFunctionlist_sequences
Lists all the videos in the input set_ids. Returns a list of tuples (set_id, video_name) args: root: Root directory to TrackingNet
EgoTracks/tracking/dataset/train_datasets/tracking_net.py:15
↓ 1 callersMethodload_3d_annotation
(self, data: Dict)
VQ3D/VQ3D/API/get_query_3d_ground_truth.py:45
↓ 1 callersMethodload_clip_info
(self, clip_info_path)
EgoTracks/tracking/dataset/eval_datasets/ego4d_lt_tracking_dataset.py:52
↓ 1 callersFunctionload_glove
(glove_path)
NLQ/VSLNet/utils/data_gen.py:98
↓ 1 callersMethodload_image
Read image as grayscale and resize to img_size. Inputs impath: Path to input image. Returns grayim: uint8 num
VQ3D/camera_pose_estimation/SuperGlueMatching/models/utils.py:159
↓ 1 callersFunctionload_json
(file)
MQ/Utils/dataset.py:15
↓ 1 callersFunctionload_pickle
(filename)
NLQ/VSLNet/utils/data_util.py:35
↓ 1 callersFunctionload_text_numpy
(path, delimiter, dtype)
EgoTracks/tracking/utils/load_text.py:7
↓ 1 callersFunctionload_text_pandas
(path, delimiter, dtype)
EgoTracks/tracking/utils/load_text.py:22
↓ 1 callersFunctionload_video_features
(root, max_position_length)
NLQ/VSLNet/utils/data_util.py:46
↓ 1 callersFunctionload_vq3d_annotation
(filename)
VQ3D/camera_pose_estimation/run_all_data.py:12
↓ 1 callersFunctionlog_optimal_transport
Perform Differentiable Optimal Transport in Log-space for stability
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:150
↓ 1 callersFunctionlog_sinkhorn_iterations
Perform Sinkhorn Normalization in Log-space for stability
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:141
↓ 1 callersMethodlosses
Args: predictions: return values of :meth:`forward()` proposals (list[Instances]): proposals that match the features
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:457
↓ 1 callersMethodlosses
Args: predictions: return values of :meth:`forward()` proposals (list[Instances]): proposals that match the features
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:205
↓ 1 callersFunctionmain
()
EgoTracks/tools/train_net.py:224
↓ 1 callersFunctionmain
()
EgoTracks/tools/preprocess/extract_ego4d_clip_frames.py:110
↓ 1 callersFunctionmain
(configs, parser)
NLQ/VSLNet/main.py:26
↓ 1 callersFunctionmain
(args)
NLQ/VSLNet/utils/evaluate_ego4d_nlq.py:109
↓ 1 callersFunctionmain
(cfg: DictConfig)
VQ2D/extract_vq_detection_scores.py:274
↓ 1 callersFunctionmain
(cfg: DictConfig)
VQ2D/perform_vq_inference.py:391
↓ 1 callersFunctionmain
(args)
VQ2D/convert_videos_to_clips.py:153
↓ 1 callersFunctionmain
(args)
VQ2D/convert_videos_to_images.py:135
↓ 1 callersFunctionmain
(args)
VQ2D/tools/validate_extracted_clips.py:55
↓ 1 callersFunctionmake_matching_plot_fast
(image0, image1, kpts0, kpts1, mkpts0, mkpts1, color, text, path=None,
VQ3D/camera_pose_estimation/SuperGlueMatching/models/utils.py:484
↓ 1 callersFunctionmerge_results
(args)
VQ2D/scripts/faster_evaluation/merge_results.py:18
↓ 1 callersFunctionmetric
(x, y, sigma=1)
VQ2D/vq2d/tracking/particle_filter.py:80
↓ 1 callersFunctionmodify_STARK_cfg_by_dataset
(cfg, dataset_name)
EgoTracks/tools/eval_net.py:27
↓ 1 callersMethodnew_epoch
(self)
EgoTracks/tools/trainers/base_trainer.py:320
↓ 1 callersFunctionnms
Pure Python NMS baseline.
MQ/Infer.py:130
↓ 1 callersFunctionnms
Pure Python NMS baseline.
NLQ/2D-TAN/lib/core/eval.py:32
↓ 1 callersFunctionopencv_loader
Read image using opencv's imread function and returns it in rgb format
EgoTracks/tracking/utils/utils.py:9
← previousnext →401–500 of 1,142, ranked by callers