Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/EGO4D/episodic-memory
/ types & classes
Types & classes
180 in github.com/EGO4D/episodic-memory
⨍
Functions
1,142
◇
Types & classes
180
↓ 45 callers
Class
TensorList
Container mainly used for lists of torch tensors. Extends lists with pytorch functionality.
EgoTracks/tracking/utils/tensor.py:48
↓ 13 callers
Class
Conv1D
NLQ/VSLNet/model/layers.py:16
↓ 10 callers
Class
TensorDict
Container mainly used for dicts of torch tensors. Extends OrderedDict with pytorch functionality.
EgoTracks/tracking/utils/tensor.py:8
↓ 9 callers
Class
BBox
VQ2D/vq2d/structures.py:4
↓ 6 callers
Class
MultiheadAttentionBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:154
↓ 6 callers
Class
NestedTensor
EgoTracks/tracking/models/stark_tracker/utils/misc.py:39
↓ 6 callers
Class
SuperPoint
SuperPoint Convolutional Detector and Descriptor SuperPoint: Self-Supervised Interest Point Detection and Description. Daniel DeTone, Tomasz
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superpoint.py:95
↓ 5 callers
Class
SequenceList
List of sequences. Supports the addition operator to concatenate sequence lists.
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:183
↓ 4 callers
Class
CameraIntrinsicsHelper
VQ3D/camera_pose_estimation/Camera_Intrinsics_API/get_camera_intrinsics.py:11
↓ 4 callers
Class
ResponseTrack
VQ2D/vq2d/structures.py:34
↓ 3 callers
Class
AverageMeter
Computes and stores the average and current value
NLQ/2D-TAN/lib/core/utils.py:10
↓ 3 callers
Class
BoundingBox
VQ3D/annotation_API/API/bounding_box.py:6
↓ 3 callers
Class
Got10k
GOT-10k dataset. Publication: GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild Lianghua Huang, X
EgoTracks/tracking/dataset/train_datasets/got10k.py:16
↓ 3 callers
Class
SiamPredictor
VQ2D/vq2d/baselines/predictor.py:8
↓ 3 callers
Class
VideoDataSet
MQ/Utils/dataset.py:21
↓ 2 callers
Class
AverageMeter
Computes and stores the average and current value
EgoTracks/tools/trainers/base_trainer.py:297
↓ 2 callers
Class
AverageMeter
Computes and stores the average and current value
EgoTracks/tracking/utils/meters.py:4
↓ 2 callers
Class
BoxCoder
MQ/Models/BoxCoder.py:5
↓ 2 callers
Class
Dataset
NLQ/VSLNet/utils/data_loader.py:8
↓ 2 callers
Class
DynamicRNN
NLQ/VSLNet/model/layers.py:462
↓ 2 callers
Class
EGO4DLTTrackingDataset
EGO4D LTT dataset.
EgoTracks/tracking/dataset/eval_datasets/ego4d_lt_tracking_dataset.py:147
↓ 2 callers
Class
Engine
NLQ/2D-TAN/lib/core/engine.py:1
↓ 2 callers
Class
FeatureEncoder
NLQ/VSLNet/model/layers.py:318
↓ 2 callers
Class
InducedSetAttentionBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:84
↓ 2 callers
Class
InstanceRegistration
Define the InstanceRegistration class to hold all registered instances. The instance register will esentially be a dictionary containing all
EgoTracks/tracking/models/template.py:133
↓ 2 callers
Class
LTRLoader
Data loader. Combines a dataset and a sampler, and provides single- or multi-process iterators over the dataset. Note: The only differen
EgoTracks/tracking/dataset/dataloader.py:144
↓ 2 callers
Class
Loss_loc_cls
MQ/Models/Loss.py:9
↓ 2 callers
Class
MLP
Very simple multi-layer perceptron (also called FFN)
EgoTracks/tracking/models/stark_tracker/head.py:221
↓ 2 callers
Class
MatterportDataset
VQ3D/camera_pose_estimation/SuperGlueMatching/extract_visual_database.py:35
↓ 2 callers
Class
ParticleFilter
A particle filter object which maintains the internal state of a population of particles, and can be updated given observations. Attributes:
VQ2D/vq2d/tracking/pfilter.py:189
↓ 2 callers
Class
STARKProcessing
The processing class used for training LittleBoy. The images are processed in the following way. First, the target bounding box is jittered by add
EgoTracks/tracking/dataset/processing/stark_processing.py:14
↓ 2 callers
Class
SuperGlue
SuperGlue feature matching middle-end Given two sets of keypoints and locations, we determine the correspondences by: 1. Keypoint Encod
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:177
↓ 2 callers
Class
TrackingDataset
Class responsible for sampling frames from training sequences to form batches. The sampling is done in the following ways. First a dataset is sel
EgoTracks/tracking/dataset/trackingdataset.py:11
↓ 2 callers
Class
VSGN
MQ/Models/VSGN.py:11
↓ 2 callers
Class
VSLNet
NLQ/VSLNet/model/VSLNet.py:52
↓ 2 callers
Class
VisualQuery3DGroundTruth
VQ3D/VQ3D/API/get_query_3d_ground_truth.py:14
↓ 2 callers
Class
VisualQueryDatasetMapper
A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by the model. This is modified to load
VQ2D/vq2d/baselines/dataloader.py:70
↓ 1 callers
Class
ANETdetection
MQ/Evaluation/ego4d/eval_detection.py:20
↓ 1 callers
Class
AnchorGenerator
MQ/Models/AnchorGenerator.py:6
↓ 1 callers
Class
AttentionalGNN
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:122
↓ 1 callers
Class
AttentionalPropagation
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:110
↓ 1 callers
Class
AverageTimer
Class to help manage printing simple timing of code execution.
VQ3D/camera_pose_estimation/SuperGlueMatching/models/utils.py:57
↓ 1 callers
Class
AzureKinect
VQ3D/camera_pose_estimation/utils.py:259
↓ 1 callers
Class
AzureKinectPosePnP
VQ3D/camera_pose_estimation/SuperGlueMatching/extract_visual_database.py:194
↓ 1 callers
Class
Backbone
ResNet backbone with frozen BatchNorm.
EgoTracks/tracking/models/stark_tracker/backbone.py:118
↓ 1 callers
Class
BertEmbedding
NLQ/VSLNet/model/layers.py:148
↓ 1 callers
Class
BoundaryAdjust
MQ/Models/BoundaryAdjust.py:6
↓ 1 callers
Class
CQAttention
NLQ/VSLNet/model/layers.py:342
↓ 1 callers
Class
CQConcatenate
NLQ/VSLNet/model/layers.py:414
↓ 1 callers
Class
CharacterEmbedding
NLQ/VSLNet/model/layers.py:68
↓ 1 callers
Class
ConditionedPredictor
NLQ/VSLNet/model/layers.py:482
↓ 1 callers
Class
Corner_Predictor
Corner Predictor module
EgoTracks/tracking/models/stark_tracker/head.py:46
↓ 1 callers
Class
Corner_Predictor_Lite
Corner Predictor module (Lite version)
EgoTracks/tracking/models/stark_tracker/head.py:142
↓ 1 callers
Class
DepthwiseSeparableConvBlock
NLQ/VSLNet/model/layers.py:202
↓ 1 callers
Class
DotProduct
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:19
↓ 1 callers
Class
EGO4DLTT
Ego4D VQ response track dataset.
EgoTracks/tracking/dataset/train_datasets/ego4d_lt_tracking.py:14
↓ 1 callers
Class
Ego4DVQ
Ego4D VQ response track dataset.
EgoTracks/tracking/dataset/train_datasets/ego4d_vq.py:12
↓ 1 callers
Class
Embedding
NLQ/VSLNet/model/layers.py:112
↓ 1 callers
Class
EpisodicNLQProcessor
NLQ/VSLNet/utils/data_gen.py:22
↓ 1 callers
Class
ExtractFramesWorkflowParams
EgoTracks/tools/preprocess/extract_ego4d_clip_frames.py:20
↓ 1 callers
Class
FrameExtractor
VQ3D/camera_pose_estimation/Camera_Intrinsics_API/extract_frames.py:4
↓ 1 callers
Class
FrozenBatchNorm2d
BatchNorm2d where the batch statistics and the affine parameters are fixed. Copy-paste from torchvision.misc.ops with added eps before rqsrt,
EgoTracks/tracking/models/stark_tracker/backbone.py:16
↓ 1 callers
Class
Head
MQ/Models/Head.py:5
↓ 1 callers
Class
HighLightLayer
NLQ/VSLNet/model/layers.py:435
↓ 1 callers
Class
Joiner
EgoTracks/tracking/models/stark_tracker/backbone.py:152
↓ 1 callers
Class
KYSRunner
VQ2D/vq2d/tracking/kys.py:65
↓ 1 callers
Class
KYSTracker
VQ2D/vq2d/tracking/kys.py:13
↓ 1 callers
Class
KeypointEncoder
Joint encoding of visual appearance and location using MLPs
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:73
↓ 1 callers
Class
Lasot
LaSOT dataset. Publication: LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking Heng Fan, Liting Lin, Fan Yang
EgoTracks/tracking/dataset/train_datasets/lasot.py:15
↓ 1 callers
Class
MSCOCOSeq
The COCO dataset. COCO is an image dataset. Thus, we treat each image as a sequence of length 1. Publication: Microsoft COCO: Common Obje
EgoTracks/tracking/dataset/train_datasets/coco_seq.py:13
↓ 1 callers
Class
Matcher
This class assigns to each predicted "element" (e.g., a box) a ground-truth element. Each predicted element will have exactly zero or one mat
MQ/Models/matcher.py:4
↓ 1 callers
Class
Matching
Image Matching Frontend (SuperPoint + SuperGlue)
VQ3D/camera_pose_estimation/SuperGlueMatching/models/matching.py:49
↓ 1 callers
Class
Moment_Retrieval
MQ/Evaluation/ego4d/get_retrieval_performance.py:5
↓ 1 callers
Class
MultiHeadAttentionBlock
NLQ/VSLNet/model/layers.py:245
↓ 1 callers
Class
MultiHeadedAttention
Multi-head attention to increase model expressivitiy
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:92
↓ 1 callers
Class
NeighConv
MQ/Models/GCNs.py:47
↓ 1 callers
Class
ObjectInstance
An object instance with a list of TemplateImage template images. The ObjectInstance class organizes all template images for a given instance
EgoTracks/tracking/models/template.py:68
↓ 1 callers
Class
PFRunner
VQ2D/vq2d/tracking/particle_filter.py:92
↓ 1 callers
Class
PosePnP_points_accumulation
VQ3D/camera_pose_estimation/pnp_api.py:87
↓ 1 callers
Class
PositionEmbeddingLearned
Absolute pos embedding, learned.
EgoTracks/tracking/models/stark_tracker/position_encoding.py:71
↓ 1 callers
Class
PositionEmbeddingNone
No positional encoding.
EgoTracks/tracking/models/stark_tracker/position_encoding.py:108
↓ 1 callers
Class
PositionEmbeddingSine
This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t
EgoTracks/tracking/models/stark_tracker/position_encoding.py:11
↓ 1 callers
Class
PositionalEmbedding
Construct the embeddings from word, position and token_type embeddings.
NLQ/VSLNet/model/layers.py:167
↓ 1 callers
Class
Pred_loc_cls
MQ/Models/ActionGenerator.py:6
↓ 1 callers
Class
Preprocessor
EgoTracks/tracking/models/stark_tracker/utils/misc.py:62
↓ 1 callers
Class
ProgressMeter
EgoTracks/tracking/utils/meters.py:29
↓ 1 callers
Class
RefSetTransHead
' use set transformer ' Compares two image features to see if they correspond to the same object instance.
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:193
↓ 1 callers
Class
ResNet
EgoTracks/tracking/models/stark_tracker/resnet.py:39
↓ 1 callers
Class
ResidualBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:53
↓ 1 callers
Class
ResidualBlock
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:44
↓ 1 callers
Class
STARKParams
EgoTracks/tracking/models/stark_tracker/config/stark_st2/config.py:261
↓ 1 callers
Class
STARKS
This is the base class for Transformer Tracking
EgoTracks/tracking/models/stark_tracker/stark_s.py:15
↓ 1 callers
Class
STARKST
This is the base class for Transformer Tracking
EgoTracks/tracking/models/stark_tracker/stark_st.py:10
↓ 1 callers
Class
STARKSTTrainer
EgoTracks/tools/trainers/starkst_trainer.py:255
↓ 1 callers
Class
STARKSTrainer
EgoTracks/tools/trainers/starkst_trainer.py:19
↓ 1 callers
Class
Sequence
Class for the sequence in an evaluation.
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:25
↓ 1 callers
Class
SiamMaskParams
EgoTracks/tracking/utils/types.py:41
↓ 1 callers
Class
SiamMaskTestParams
EgoTracks/tracking/utils/types.py:8
↓ 1 callers
Class
SiameseHead
Compares two image features to see if they correspond to the same object instance.
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:70
↓ 1 callers
Class
SpatioTemporalDetection
VQ2D/vq2d/metrics/spatio_temporal_metrics.py:16
next →
1–100 of 180, ranked by callers