MCPcopy Create free account

hub / github.com/EGO4D/episodic-memory / types & classes

Types & classes180 in github.com/EGO4D/episodic-memory

↓ 45 callersClassTensorList
Container mainly used for lists of torch tensors. Extends lists with pytorch functionality.
EgoTracks/tracking/utils/tensor.py:48
↓ 13 callersClassConv1D
NLQ/VSLNet/model/layers.py:16
↓ 10 callersClassTensorDict
Container mainly used for dicts of torch tensors. Extends OrderedDict with pytorch functionality.
EgoTracks/tracking/utils/tensor.py:8
↓ 9 callersClassBBox
VQ2D/vq2d/structures.py:4
↓ 6 callersClassMultiheadAttentionBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:154
↓ 6 callersClassNestedTensor
EgoTracks/tracking/models/stark_tracker/utils/misc.py:39
↓ 6 callersClassSuperPoint
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 callersClassSequenceList
List of sequences. Supports the addition operator to concatenate sequence lists.
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:183
↓ 4 callersClassCameraIntrinsicsHelper
VQ3D/camera_pose_estimation/Camera_Intrinsics_API/get_camera_intrinsics.py:11
↓ 4 callersClassResponseTrack
VQ2D/vq2d/structures.py:34
↓ 3 callersClassAverageMeter
Computes and stores the average and current value
NLQ/2D-TAN/lib/core/utils.py:10
↓ 3 callersClassBoundingBox
VQ3D/annotation_API/API/bounding_box.py:6
↓ 3 callersClassGot10k
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 callersClassSiamPredictor
VQ2D/vq2d/baselines/predictor.py:8
↓ 3 callersClassVideoDataSet
MQ/Utils/dataset.py:21
↓ 2 callersClassAverageMeter
Computes and stores the average and current value
EgoTracks/tools/trainers/base_trainer.py:297
↓ 2 callersClassAverageMeter
Computes and stores the average and current value
EgoTracks/tracking/utils/meters.py:4
↓ 2 callersClassBoxCoder
MQ/Models/BoxCoder.py:5
↓ 2 callersClassDataset
NLQ/VSLNet/utils/data_loader.py:8
↓ 2 callersClassDynamicRNN
NLQ/VSLNet/model/layers.py:462
↓ 2 callersClassEGO4DLTTrackingDataset
EGO4D LTT dataset.
EgoTracks/tracking/dataset/eval_datasets/ego4d_lt_tracking_dataset.py:147
↓ 2 callersClassEngine
NLQ/2D-TAN/lib/core/engine.py:1
↓ 2 callersClassFeatureEncoder
NLQ/VSLNet/model/layers.py:318
↓ 2 callersClassInducedSetAttentionBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:84
↓ 2 callersClassInstanceRegistration
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 callersClassLTRLoader
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 callersClassLoss_loc_cls
MQ/Models/Loss.py:9
↓ 2 callersClassMLP
Very simple multi-layer perceptron (also called FFN)
EgoTracks/tracking/models/stark_tracker/head.py:221
↓ 2 callersClassMatterportDataset
VQ3D/camera_pose_estimation/SuperGlueMatching/extract_visual_database.py:35
↓ 2 callersClassParticleFilter
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 callersClassSTARKProcessing
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 callersClassSuperGlue
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 callersClassTrackingDataset
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 callersClassVSGN
MQ/Models/VSGN.py:11
↓ 2 callersClassVSLNet
NLQ/VSLNet/model/VSLNet.py:52
↓ 2 callersClassVisualQuery3DGroundTruth
VQ3D/VQ3D/API/get_query_3d_ground_truth.py:14
↓ 2 callersClassVisualQueryDatasetMapper
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 callersClassANETdetection
MQ/Evaluation/ego4d/eval_detection.py:20
↓ 1 callersClassAnchorGenerator
MQ/Models/AnchorGenerator.py:6
↓ 1 callersClassAttentionalGNN
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:122
↓ 1 callersClassAttentionalPropagation
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:110
↓ 1 callersClassAverageTimer
Class to help manage printing simple timing of code execution.
VQ3D/camera_pose_estimation/SuperGlueMatching/models/utils.py:57
↓ 1 callersClassAzureKinect
VQ3D/camera_pose_estimation/utils.py:259
↓ 1 callersClassAzureKinectPosePnP
VQ3D/camera_pose_estimation/SuperGlueMatching/extract_visual_database.py:194
↓ 1 callersClassBackbone
ResNet backbone with frozen BatchNorm.
EgoTracks/tracking/models/stark_tracker/backbone.py:118
↓ 1 callersClassBertEmbedding
NLQ/VSLNet/model/layers.py:148
↓ 1 callersClassBoundaryAdjust
MQ/Models/BoundaryAdjust.py:6
↓ 1 callersClassCQAttention
NLQ/VSLNet/model/layers.py:342
↓ 1 callersClassCQConcatenate
NLQ/VSLNet/model/layers.py:414
↓ 1 callersClassCharacterEmbedding
NLQ/VSLNet/model/layers.py:68
↓ 1 callersClassConditionedPredictor
NLQ/VSLNet/model/layers.py:482
↓ 1 callersClassCorner_Predictor
Corner Predictor module
EgoTracks/tracking/models/stark_tracker/head.py:46
↓ 1 callersClassCorner_Predictor_Lite
Corner Predictor module (Lite version)
EgoTracks/tracking/models/stark_tracker/head.py:142
↓ 1 callersClassDepthwiseSeparableConvBlock
NLQ/VSLNet/model/layers.py:202
↓ 1 callersClassDotProduct
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:19
↓ 1 callersClassEGO4DLTT
Ego4D VQ response track dataset.
EgoTracks/tracking/dataset/train_datasets/ego4d_lt_tracking.py:14
↓ 1 callersClassEgo4DVQ
Ego4D VQ response track dataset.
EgoTracks/tracking/dataset/train_datasets/ego4d_vq.py:12
↓ 1 callersClassEmbedding
NLQ/VSLNet/model/layers.py:112
↓ 1 callersClassEpisodicNLQProcessor
NLQ/VSLNet/utils/data_gen.py:22
↓ 1 callersClassExtractFramesWorkflowParams
EgoTracks/tools/preprocess/extract_ego4d_clip_frames.py:20
↓ 1 callersClassFrameExtractor
VQ3D/camera_pose_estimation/Camera_Intrinsics_API/extract_frames.py:4
↓ 1 callersClassFrozenBatchNorm2d
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 callersClassHead
MQ/Models/Head.py:5
↓ 1 callersClassHighLightLayer
NLQ/VSLNet/model/layers.py:435
↓ 1 callersClassJoiner
EgoTracks/tracking/models/stark_tracker/backbone.py:152
↓ 1 callersClassKYSRunner
VQ2D/vq2d/tracking/kys.py:65
↓ 1 callersClassKYSTracker
VQ2D/vq2d/tracking/kys.py:13
↓ 1 callersClassKeypointEncoder
Joint encoding of visual appearance and location using MLPs
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:73
↓ 1 callersClassLasot
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 callersClassMSCOCOSeq
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 callersClassMatcher
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 callersClassMatching
Image Matching Frontend (SuperPoint + SuperGlue)
VQ3D/camera_pose_estimation/SuperGlueMatching/models/matching.py:49
↓ 1 callersClassMoment_Retrieval
MQ/Evaluation/ego4d/get_retrieval_performance.py:5
↓ 1 callersClassMultiHeadAttentionBlock
NLQ/VSLNet/model/layers.py:245
↓ 1 callersClassMultiHeadedAttention
Multi-head attention to increase model expressivitiy
VQ3D/camera_pose_estimation/SuperGlueMatching/models/superglue.py:92
↓ 1 callersClassNeighConv
MQ/Models/GCNs.py:47
↓ 1 callersClassObjectInstance
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 callersClassPFRunner
VQ2D/vq2d/tracking/particle_filter.py:92
↓ 1 callersClassPosePnP_points_accumulation
VQ3D/camera_pose_estimation/pnp_api.py:87
↓ 1 callersClassPositionEmbeddingLearned
Absolute pos embedding, learned.
EgoTracks/tracking/models/stark_tracker/position_encoding.py:71
↓ 1 callersClassPositionEmbeddingNone
No positional encoding.
EgoTracks/tracking/models/stark_tracker/position_encoding.py:108
↓ 1 callersClassPositionEmbeddingSine
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 callersClassPositionalEmbedding
Construct the embeddings from word, position and token_type embeddings.
NLQ/VSLNet/model/layers.py:167
↓ 1 callersClassPred_loc_cls
MQ/Models/ActionGenerator.py:6
↓ 1 callersClassPreprocessor
EgoTracks/tracking/models/stark_tracker/utils/misc.py:62
↓ 1 callersClassProgressMeter
EgoTracks/tracking/utils/meters.py:29
↓ 1 callersClassRefSetTransHead
' 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 callersClassResNet
EgoTracks/tracking/models/stark_tracker/resnet.py:39
↓ 1 callersClassResidualBlock
VQ2D/detectron2_extensions/modeling/roi_heads/set_heads.py:53
↓ 1 callersClassResidualBlock
VQ2D/detectron2_extensions/modeling/roi_heads/siam_heads.py:44
↓ 1 callersClassSTARKParams
EgoTracks/tracking/models/stark_tracker/config/stark_st2/config.py:261
↓ 1 callersClassSTARKS
This is the base class for Transformer Tracking
EgoTracks/tracking/models/stark_tracker/stark_s.py:15
↓ 1 callersClassSTARKST
This is the base class for Transformer Tracking
EgoTracks/tracking/models/stark_tracker/stark_st.py:10
↓ 1 callersClassSTARKSTTrainer
EgoTracks/tools/trainers/starkst_trainer.py:255
↓ 1 callersClassSTARKSTrainer
EgoTracks/tools/trainers/starkst_trainer.py:19
↓ 1 callersClassSequence
Class for the sequence in an evaluation.
EgoTracks/tracking/dataset/eval_datasets/base_dataset.py:25
↓ 1 callersClassSiamMaskParams
EgoTracks/tracking/utils/types.py:41
↓ 1 callersClassSiamMaskTestParams
EgoTracks/tracking/utils/types.py:8
↓ 1 callersClassSiameseHead
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 callersClassSpatioTemporalDetection
VQ2D/vq2d/metrics/spatio_temporal_metrics.py:16
next →1–100 of 180, ranked by callers