Types & classes — github.com/MaureenZOU/TSAM

CodeHub MCPcopy Create free account

hub / github.com/MaureenZOU/TSAM / types & classes

Types & classes158 in github.com/MaureenZOU/TSAM

⨍ Functions 693◇ Types & classes 158

↓ 30 callersClassFrameReader

src/utils/readers.py:168

↓ 17 callersClassConv2dBlock

src/model/blocks.py:57

↓ 12 callersClassConv3dBlock

src/model/blocks.py:13

↓ 11 callersClassUnit3D

src/model/i3d.py:35

↓ 9 callersClassGroupScale

Rescales the input PIL.Image to the given 'size'. 'size' will be the size of the smaller edge. For example, if height > width, then image wil

src/data_loader/transform_flow.py:128

↓ 9 callersClassInceptionModule

src/model/i3d.py:100

↓ 7 callersClassNetLinLayer

A single linear layer which does a 1x1 conv

libs/PerceptualSimilarity/models/networks_basic.py:210

↓ 6 callersClassConv2d

src/model/tsm/module.py:5

↓ 6 callersClassGroupToFlow

src/data_loader/transform_flow.py:44

↓ 6 callersClassSegmentationReader

src/utils/readers.py:296

↓ 5 callersClassDAVISReader

src/utils/readers.py:317

↓ 5 callersClassGroupRandomCrop

src/data_loader/transform_flow.py:14

↓ 5 callersClassMaxPool3dSamePadding

src/model/i3d.py:8

↓ 5 callersClassStack

src/data_loader/transform_flow.py:318

↓ 5 callersClassToTorchFormatTensor

Converts a PIL.Image (RGB) or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]

src/data_loader/transform_flow.py:349

↓ 5 callersClassVideoDirectories

src/utils/directory_IO.py:61

↓ 4 callersClassMaskReader

src/utils/readers.py:336

↓ 4 callersClassSequential

src/model/tsm/module.py:38

↓ 3 callersClassCompareFramesReader

src/utils/readers.py:499

↓ 3 callersClassFlowReader

src/utils/readers.py:458

↓ 3 callersClassFlowmaskReader

src/utils/readers.py:485

↓ 3 callersClassGroupRandomHorizontalFlip

Randomly horizontally flips the given PIL.Image with a probability of 0.5

src/data_loader/transform_flow.py:71

↓ 3 callersClassGroupScale

Rescales the input PIL.Image to the given 'size'. 'size' will be the size of the smaller edge. For example, if height > width, then image wil

src/data_loader/transform.py:82

↓ 3 callersClassL1LossMaskedMean

src/model/loss.py:156

↓ 3 callersClassL1LossMaskedMean

src/model/loss_module.py:164

↓ 3 callersClassRelu

src/model/tsm/module.py:22

↓ 3 callersClassStack

src/data_loader/transform.py:256

↓ 3 callersClassTemporalShift

src/model/tsm/temporal_shift.py:168

↓ 3 callersClassToTorchFormatTensor

Converts a PIL.Image (RGB) or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]

src/data_loader/transform.py:277

↓ 2 callersClassAdversarialLoss

r""" Adversarial loss https://arxiv.org/abs/1711.10337

src/model/loss.py:313

↓ 2 callersClassAdversarialLoss

r""" Adversarial loss https://arxiv.org/abs/1711.10337

src/model/loss_module.py:321

↓ 2 callersClassForegroundReader

src/utils/readers.py:420

↓ 2 callersClassGroupNormalize

src/data_loader/transform_flow.py:112

↓ 2 callersClassGroupNormalize

src/data_loader/transform.py:66

↓ 2 callersClassGroupRandomCrop

src/data_loader/transform.py:13

↓ 2 callersClassLogger

Training process logger Note: Used by BaseTrainer to save training history.

src/utils/logger.py:4

↓ 2 callersClassSNTemporalPatchGANDiscriminator

src/model/networks.py:161

↓ 2 callersClassTSN

src/model/tsm/models.py:16

↓ 2 callersClassUpSampleModule

src/model/modules.py:108

↓ 2 callersClassWriterTensorboardX

src/utils/visualization.py:5

↓ 1 callersClassAttentionDownSampleModule

src/model/modules.py:103

↓ 1 callersClassCoarseNet

src/model/networks.py:12

↓ 1 callersClassCombCN

src/model/completion_model.py:81

↓ 1 callersClassCustomDatasetDataLoader

libs/PerceptualSimilarity/data/custom_dataset_data_loader.py:19

↓ 1 callersClassDist2LogitLayer

takes 2 distances, puts through fc layers, spits out value between [0,1] (if use_sigmoid is True)

libs/PerceptualSimilarity/models/networks_basic.py:175

↓ 1 callersClassDistModel

libs/PerceptualSimilarity/models/dist_model.py:20

↓ 1 callersClassDownSampleModule

src/model/modules.py:40

↓ 1 callersClassGatedConv

src/model/blocks.py:277

↓ 1 callersClassGenerator

src/model/networks.py:129

↓ 1 callersClassGroupRandomSizedCrop

Random crop the given PIL.Image to a random size of (0.08 to 1.0) of the original size and and a random aspect ratio of 3/4 to 4/3 of the original

src/data_loader/transform_flow.py:271

↓ 1 callersClassGroupRandomSizedCrop

Random crop the given PIL.Image to a random size of (0.08 to 1.0) of the original size and and a random aspect ratio of 3/4 to 4/3 of the original

src/data_loader/transform.py:209

↓ 1 callersClassHTML

libs/PerceptualSimilarity/util/html.py:6

↓ 1 callersClassInceptionI3d

Inception-v1 I3D architecture. The model is introduced in: Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset Joa

src/model/i3d.py:128

↓ 1 callersClassInference

Trainer class Note: Inherited from BaseTrainer.

src/trainer/inference.py:16

↓ 1 callersClassL2LossMaskedMean

src/model/loss.py:167

↓ 1 callersClassL2LossMaskedMean

src/model/loss_module.py:175

↓ 1 callersClassManager

src/scripts/extract_frames.py:27

↓ 1 callersClassMaskGenerator

src/utils/readers.py:380

↓ 1 callersClassMaxPool2d

src/model/tsm/module.py:30

↓ 1 callersClassPartialConv

src/model/blocks.py:330

↓ 1 callersClassPerceptModel

libs/PerceptualSimilarity/perceptual_loss.py:32

↓ 1 callersClassRefineNet

src/model/networks.py:106

↓ 1 callersClassResNet

src/model/tsm/resnet.py:132

↓ 1 callersClassRootInputDirectories

src/utils/directory_IO.py:13

↓ 1 callersClassRootOutputDirectories

src/utils/directory_IO.py:43

↓ 1 callersClassSynthesizedFrameReader

src/utils/readers.py:215

↓ 1 callersClassTemporalPool

src/model/tsm/temporal_shift.py:233

↓ 1 callersClassTemporalWarpingError

src/model/loss.py:271

↓ 1 callersClassTrainer

Trainer class Note: Inherited from BaseTrainer.

src/trainer/trainer.py:16

↓ 1 callersClassUpSampleResNetSkip

src/model/modules.py:159

↓ 1 callersClassUpSampleResNetSkipGated

src/model/modules.py:223

↓ 1 callersClassVanillaConv

src/model/blocks.py:215

↓ 1 callersClassVgg16

src/model/vgg.py:8

↓ 1 callersClassVideoCN

src/model/completion_model.py:8

↓ 1 callersClassVisualizer

libs/PerceptualSimilarity/util/visualizer.py:20

↓ 1 callersClassWorker

src/scripts/extract_frames.py:33

ClassBCERankingLoss

libs/PerceptualSimilarity/models/networks_basic.py:191

src/model/blocks.py:104

ClassBaseDataLoader

Base class for all data loaders

src/base/base_data_loader.py:7

ClassBaseDataLoader

libs/PerceptualSimilarity/data/base_data_loader.py:2

ClassBaseInference

Base class for all trainers

src/base/base_inference.py:11

Base class for all models

src/base/base_model.py:6

libs/PerceptualSimilarity/models/base_model.py:7

ClassBaseModule

src/model/modules.py:17

ClassBaseTrainer

Base class for all trainers

src/base/base_trainer.py:11

ClassBasicBlock

src/model/tsm/resnet.py:44

ClassBatchNorm2d

src/model/tsm/module.py:14

ClassBatchNorm3d

src/model/blocks.py:150

ClassBottleneck

src/model/tsm/resnet.py:84

ClassBoundingBoxesListReader

src/utils/readers.py:555

ClassCelebAFrameAndMaskDataset

src/data_loader/dataset.py:920

ClassCompleteFramesReconLoss

src/model/loss.py:198

ClassCompleteFramesReconLoss

src/model/loss_module.py:206

ClassCompletionNet

src/model/completion_model.py:140

src/model/blocks.py:126

src/model/blocks.py:163

ClassCusImageFolder

src/xy_scripts/utils/helpers.py:5

libs/PerceptualSimilarity/models/networks_basic.py:244

src/model/loss.py:117

src/model/loss_module.py:126

next →1–100 of 158, ranked by callers